Compare commits

..

1 Commits

Author SHA1 Message Date
Yuan Teoh
e347fab270 chore: add samples for multi agent blog 2025-08-25 16:07:43 -07:00
406 changed files with 4339 additions and 9565 deletions

View File

@@ -464,7 +464,7 @@ steps:
"OceanBase" \
oceanbase \
oceanbase
- id: "firestore"
name: golang:1
waitFor: ["compile-test-binary"]
@@ -575,28 +575,6 @@ steps:
firebird \
firebirdsql firebirdexecutesql
- id: "clickhouse"
name : golang:1
waitFor: ["compile-test-binary"]
entrypoint: /bin/bash
env:
- "GOPATH=/gopath"
- "CLICKHOUSE_DATABASE=$_CLICKHOUSE_DATABASE"
- "CLICKHOUSE_PORT=$_CLICKHOUSE_PORT"
- "CLICKHOUSE_PROTOCOL=$_CLICKHOUSE_PROTOCOL"
- "SERVICE_ACCOUNT_EMAIL=$SERVICE_ACCOUNT_EMAIL"
secretEnv: ["CLICKHOUSE_HOST", "CLICKHOUSE_USER", "CLIENT_ID"]
volumes:
- name: "go"
path: "/gopath"
args:
- -c
- |
.ci/test_with_coverage.sh \
"ClickHouse" \
clickhouse \
clickhouse
- id: "trino"
name: golang:1
waitFor: ["compile-test-binary"]
@@ -682,10 +660,6 @@ availableSecrets:
env: TIDB_USER
- versionName: projects/$PROJECT_ID/secrets/tidb_pass/versions/latest
env: TIDB_PASS
- versionName: projects/$PROJECT_ID/secrets/clickhouse_host/versions/latest
env: CLICKHOUSE_HOST
- versionName: projects/$PROJECT_ID/secrets/clickhouse_user/versions/latest
env: CLICKHOUSE_USER
- versionName: projects/$PROJECT_ID/secrets/firebird_user/versions/latest
env: FIREBIRD_USER
- versionName: projects/$PROJECT_ID/secrets/firebird_pass/versions/latest
@@ -733,9 +707,6 @@ substitutions:
_LOOKER_VERIFY_SSL: "true"
_TIDB_HOST: 127.0.0.1
_TIDB_PORT: "4000"
_CLICKHOUSE_DATABASE: "default"
_CLICKHOUSE_PORT: "8123"
_CLICKHOUSE_PROTOCOL: "http"
_FIREBIRD_HOST: 127.0.0.1
_FIREBIRD_PORT: "3050"
_TRINO_HOST: 127.0.0.1

View File

@@ -1,19 +1,16 @@
## Description
---
> Should include a concise description of the changes (bug or feature), it's
> impact, along with a summary of the solution
## PR Checklist
---
> Thank you for opening a Pull Request! Before submitting your PR, there are a
> few things you can do to make sure it goes smoothly:
- [ ] Make sure you reviewed
[CONTRIBUTING.md](https://github.com/googleapis/genai-toolbox/blob/main/CONTRIBUTING.md)
- [ ] Make sure to open an issue as a
[bug/issue](https://github.com/googleapis/genai-toolbox/issues/new/choose)
[bug/issue](https://github.com/googleapis/langchain-google-alloydb-pg-python/issues/new/choose)
before writing your code! That way we can discuss the change, evaluate
designs, and agree on the general idea
- [ ] Ensure the tests and linter pass
@@ -21,4 +18,4 @@
- [ ] Appropriate docs were updated (if necessary)
- [ ] Make sure to add `!` if this involve a breaking change
🛠️ Fixes #<issue_number_goes_here>
🛠️ Fixes #<issue_number_goes_here>

View File

@@ -20,5 +20,3 @@ sourceFileExtensions:
- 'go'
- 'yaml'
- 'yml'
ignoreFiles:
- 'docs/en/getting-started/quickstart/**'

View File

@@ -1,36 +1,5 @@
# Changelog
## [0.13.0](https://github.com/googleapis/genai-toolbox/compare/v0.12.0...v0.13.0) (2025-08-27)
### ⚠ BREAKING CHANGES
* **prebuilt/alloydb:** Add bearer token support for alloydb-wait-for-operation ([#1183](https://github.com/googleapis/genai-toolbox/issues/1183))
### Features
* Add capability to set default for environment variable in config ([#1248](https://github.com/googleapis/genai-toolbox/issues/1248)) ([5bcd52e](https://github.com/googleapis/genai-toolbox/commit/5bcd52e7dcd0773ded723585f4abe29d044e1540))
* **firebird:** Add Firebird SQL 2.5+ source and tool ([#1011](https://github.com/googleapis/genai-toolbox/issues/1011)) ([4f6b806](https://github.com/googleapis/genai-toolbox/commit/4f6b806de947efc4e12bdb50dff7781aedb7b966))
* **oceanbase:** Add Oceanbase source and tool ([#895](https://github.com/googleapis/genai-toolbox/issues/895)) ([6fc4982](https://github.com/googleapis/genai-toolbox/commit/6fc49826d43f46c84028e752ebebddf3d94b3d13))
* **server/mcp:** Support `ping` mechanism ([#1178](https://github.com/googleapis/genai-toolbox/issues/1178)) ([5dcc66c](https://github.com/googleapis/genai-toolbox/commit/5dcc66c84fa72c75ec50a9ac5198018212ec2979))
* **server:** Fail-fast on environment variable substitution ([#1177](https://github.com/googleapis/genai-toolbox/issues/1177)) ([212aaba](https://github.com/googleapis/genai-toolbox/commit/212aaba74c8b431de8a5f7b9822a0af4afcaaa0e))
* **server:** Implement Tool call auth error propagation ([#1235](https://github.com/googleapis/genai-toolbox/issues/1235)) ([b94a021](https://github.com/googleapis/genai-toolbox/commit/b94a021ca11c6637cf8038449483b5e75f2012b3))
* **sources/bigquery:** Add support for user-credential passthrough ([#1067](https://github.com/googleapis/genai-toolbox/issues/1067)) ([650e2e2](https://github.com/googleapis/genai-toolbox/commit/650e2e26f51bff75ce66343f64944d0a89a58b69))
* **tool/looker:** Add support for `description` field in looker tool ([#1199](https://github.com/googleapis/genai-toolbox/issues/1199)) ([97f0dd2](https://github.com/googleapis/genai-toolbox/commit/97f0dd2acf26caf28ecad65abea8779c196a27f1))
* **tools/bigquery-ask-data-insights:** Add bigquery `ask-data-insights` tool ([#932](https://github.com/googleapis/genai-toolbox/issues/932)) ([7651357](https://github.com/googleapis/genai-toolbox/commit/7651357d424a2b6656d8b6818cebc5c8a86ed053))
* **tools/bigquery-forecast:** Add bigqueryforecast tool ([#1148](https://github.com/googleapis/genai-toolbox/issues/1148)) ([2ad0ccf](https://github.com/googleapis/genai-toolbox/commit/2ad0ccf83df542340087742468d6762f81eedee6))
* **tools/firestore-add-documents:** Add firestore-add-documents tool ([#1107](https://github.com/googleapis/genai-toolbox/issues/1107)) ([ee4a70a](https://github.com/googleapis/genai-toolbox/commit/ee4a70a0e82b346b07b5b4c60dfa060da2273f50))
* **tools/firestore-update-document:** Add firestore-update-document tool ([#1191](https://github.com/googleapis/genai-toolbox/issues/1191)) ([0010123](https://github.com/googleapis/genai-toolbox/commit/00101232a39c70288aac5715649c184858d351e3))
* **tools/looker:** Control over whether hidden objects are surfaced ([#1222](https://github.com/googleapis/genai-toolbox/issues/1222)) ([bc91559](https://github.com/googleapis/genai-toolbox/commit/bc91559cc4e5b20385b84cc562b624fabf7e47a8))
* **trino:** Add Trino source and tools ([#948](https://github.com/googleapis/genai-toolbox/issues/948)) ([7dd123b](https://github.com/googleapis/genai-toolbox/commit/7dd123b3d76b8eb2b74b5d960959c1f90684b37e))
### Bug Fixes
* **tools/looker:** Lookergetdashboards uses proper Authorized helper func ([#1255](https://github.com/googleapis/genai-toolbox/issues/1255)) ([00866bc](https://github.com/googleapis/genai-toolbox/commit/00866bc7fc33115c547213e60316ae889735fdbb))
* **tools/mongodb-find-one:** ProjectPayload unmarshaling ([#1167](https://github.com/googleapis/genai-toolbox/issues/1167)) ([8ea6a98](https://github.com/googleapis/genai-toolbox/commit/8ea6a98bd9096ba97722e5f807366887e864004f))
* **tools/mysql:** Fix encoded text for mysql ([#1161](https://github.com/googleapis/genai-toolbox/issues/1161)) ([a37cfa8](https://github.com/googleapis/genai-toolbox/commit/a37cfa841d151b9995d4fab73cfc5e4d30d2cc57)), closes [#840](https://github.com/googleapis/genai-toolbox/issues/840)
## [0.12.0](https://github.com/googleapis/genai-toolbox/compare/v0.11.0...v0.12.0) (2025-08-14)

View File

@@ -25,42 +25,33 @@ This project follows
## Contribution process
> [!NOTE]
> New contributions should always include both unit and integration tests.
### Code reviews
All submissions, including submissions by project members, require review. We
use GitHub pull requests for this purpose. Consult
[GitHub Help](https://help.github.com/articles/about-pull-requests/) for more
information on using pull requests.
### Code reviews
* Within 2-5 days, a reviewer will review your PR. They may approve it, or request
changes.
* When requesting changes, reviewers should self-assign the PR to ensure
Within 2-5 days, a reviewer will review your PR. They may approve it, or request
changes. When requesting changes, reviewers should self-assign the PR to ensure
they are aware of any updates.
* If additional changes are needed, push additional commits to your PR branch -
this helps the reviewer know which parts of the PR have changed.
* Commits will be
If additional changes are needed, push additional commits to your PR branch -
this helps the reviewer know which parts of the PR have changed. Commits will be
squashed when merged.
* Please follow up with changes promptly.
* If a PR is awaiting changes by the
Please follow up with changes promptly. If a PR is awaiting changes by the
author for more than 10 days, maintainers may mark that PR as Draft. PRs that
are inactive for more than 30 days may be closed.
## Adding a New Database Source or Tool
### Adding a New Database Source and Tool
Please create an
We recommend creating an
[issue](https://github.com/googleapis/genai-toolbox/issues) before
implementation to ensure we can accept the contribution and no duplicated work. This issue
should include an overview of the API design. If you have any questions, reach out on our
[Discord](https://discord.gg/Dmm69peqjh) to chat directly with the team.
implementation to ensure we can accept the contribution and no duplicated work.
If you have any questions, reach out on our
[Discord](https://discord.gg/Dmm69peqjh) to chat directly with the team. New
contributions should be added with both unit tests and integration tests.
> [!NOTE]
> New tools can be added for [pre-existing data sources](https://github.com/googleapis/genai-toolbox/tree/main/internal/sources). However, any new database source should also include at least one new tool type.
### Adding a New Database Source
#### 1. Implement the New Data Source
We recommend looking at an [example source
implementation](https://github.com/googleapis/genai-toolbox/blob/main/internal/sources/postgres/postgres.go).
@@ -75,7 +66,7 @@ implementation](https://github.com/googleapis/genai-toolbox/blob/main/internal/s
* **Implement the
[`SourceConfig`](https://github.com/googleapis/genai-toolbox/blob/fd300dc606d88bf9f7bba689e2cee4e3565537dd/internal/sources/sources.go#L57)
interface**. This interface requires two methods:
* `SourceConfigType() string`: Returns a unique string identifier for your
* `SourceConfigKind() string`: Returns a unique string identifier for your
data source (e.g., `"newdb"`).
* `Initialize(ctx context.Context, tracer trace.Tracer) (Source, error)`:
Creates a new instance of your data source and establishes a connection to
@@ -83,11 +74,11 @@ implementation](https://github.com/googleapis/genai-toolbox/blob/main/internal/s
* **Implement the
[`Source`](https://github.com/googleapis/genai-toolbox/blob/fd300dc606d88bf9f7bba689e2cee4e3565537dd/internal/sources/sources.go#L63)
interface**. This interface requires one method:
* `SourceType() string`: Returns the same string identifier as `SourceConfigType()`.
* `SourceKind() string`: Returns the same string identifier as `SourceConfigKind()`.
* **Implement `init()`** to register the new Source.
* **Implement Unit Tests** in a file named `newdb_test.go`.
### Adding a New Tool
#### 2. Implement the New Tool
We recommend looking at an [example tool
implementation](https://github.com/googleapis/genai-toolbox/tree/main/internal/tools/postgres/postgressql).
@@ -100,7 +91,7 @@ tools.
* **Implement the
[`ToolConfig`](https://github.com/googleapis/genai-toolbox/blob/fd300dc606d88bf9f7bba689e2cee4e3565537dd/internal/tools/tools.go#L61)
interface**. This interface requires one method:
* `ToolConfigType() string`: Returns a unique string identifier for your tool
* `ToolConfigKind() string`: Returns a unique string identifier for your tool
(e.g., `"newdb"`).
* `Initialize(sources map[string]Source) (Tool, error)`: Creates a new
instance of your tool and validates that it can connect to the specified
@@ -120,7 +111,7 @@ tools.
* **Implement `init()`** to register the new Tool.
* **Implement Unit Tests** in a file named `newdb_test.go`.
### Adding Integration Tests
#### 3. Add Integration Tests
* **Add a test file** under a new directory `tests/newdb`.
* **Add pre-defined integration test suites** in the
@@ -162,7 +153,7 @@ tools.
[temp-param-doc]:
https://googleapis.github.io/genai-toolbox/resources/tools/#template-parameters
### Adding Documentation
#### 4. Add Documentation
* **Update the documentation** to include information about your new data source
and tool. This includes:
@@ -172,7 +163,7 @@ tools.
* **(Optional) Add samples** to the `docs/en/samples/<newdb>` directory.
### (Optional) Adding Prebuilt Tools
#### (Optional) 5. Add Prebuilt Tools
You can provide developers with a set of "build-time" tools to aid common
software development user journeys like viewing and creating tables/collections
@@ -186,7 +177,7 @@ and data.
[internal/prebuiltconfigs/prebuiltconfigs_test.go](internal/prebuiltconfigs/prebuiltconfigs_test.go)
and [cmd/root_test.go](cmd/root_test.go).
## Submitting a Pull Request
#### 6. Submit a Pull Request
Submit a pull request to the repository with your changes. Be sure to include a
detailed description of your changes and any requests for long term testing
@@ -215,7 +206,7 @@ resources.
| style | Update src code, with only formatting and whitespace updates (e.g. code formatter or linter changes). |
Pull requests should always add scope whenever possible. The scope is
formatted as `<scope-type>/<scope-type>` (e.g., `sources/postgres`, or
formatted as `<scope-type>/<scope-kind>` (e.g., `sources/postgres`, or
`tools/mssql-sql`).
Ideally, **each PR covers only one scope**, if this is
@@ -227,4 +218,4 @@ resources.
* **PR Description:** PR description should **always** be included. It should
include a concise description of the changes, it's impact, along with a
summary of the solution. If the PR is related to a specific issue, the issue
number should be mentioned in the PR description (e.g. `Fixes #1`).
number should be mentioned in the PR description (e.g. `Fixes #1`).

View File

@@ -117,7 +117,7 @@ To install Toolbox as a binary:
<!-- {x-release-please-start-version} -->
```sh
# see releases page for other versions
export VERSION=0.13.0
export VERSION=0.12.0
curl -O https://storage.googleapis.com/genai-toolbox/v$VERSION/linux/amd64/toolbox
chmod +x toolbox
```
@@ -130,7 +130,7 @@ You can also install Toolbox as a container:
```sh
# see releases page for other versions
export VERSION=0.13.0
export VERSION=0.12.0
docker pull us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:$VERSION
```
@@ -154,7 +154,7 @@ To install from source, ensure you have the latest version of
[Go installed](https://go.dev/doc/install), and then run the following command:
```sh
go install github.com/googleapis/genai-toolbox@v0.13.0
go install github.com/googleapis/genai-toolbox@v0.12.0
```
<!-- {x-release-please-end} -->
@@ -165,66 +165,22 @@ go install github.com/googleapis/genai-toolbox@v0.13.0
[Configure](#configuration) a `tools.yaml` to define your tools, and then
execute `toolbox` to start the server:
<details open>
<summary>Binary</summary>
To run Toolbox from binary:
```sh
./toolbox --tools-file "tools.yaml"
```
**NOTE:**
Toolbox enables dynamic reloading by default. To disable, use the `--disable-reload` flag.
> [!NOTE]
> Toolbox enables dynamic reloading by default. To disable, use the
> `--disable-reload` flag.
</details>
#### Homebrew Users
<details>
<summary>Container image</summary>
To run the server after pulling the [container image](#installing-the-server):
```sh
export VERSION=0.11.0 # Use the version you pulled
docker run -p 5000:5000 \
-v $(pwd)/tools.yaml:/app/tools.yaml \
us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:$VERSION \
--tools-file "/app/tools.yaml"
```
**NOTE:**
The `-v` flag mounts your local `tools.yaml` into the container, and `-p` maps the container's port `5000` to your host's port `5000`.
</details>
<details>
<summary>Source</summary>
To run the server directly from source, navigate to the project root directory and run:
```sh
go run .
```
**NOTE:**
This command runs the project from source, and is more suitable for development and testing. It does **not** compile a binary into your `$GOPATH`. If you want to compile a binary instead, refer the [Developer Documentation](./DEVELOPER.md#building-the-binary).
</details>
<details>
<summary>Homebrew</summary>
If you installed Toolbox using [Homebrew](https://brew.sh/), the `toolbox` binary is available in your system path. You can start the server with the same command:
If you installed Toolbox using Homebrew, the `toolbox` binary is available in your system path. You can start the server with the same command:
```sh
toolbox --tools-file "tools.yaml"
```
</details>
You can use `toolbox help` for a full list of flags! To stop the server, send a
terminate signal (`ctrl+c` on most platforms).
@@ -232,7 +188,6 @@ For more detailed documentation on deploying to different environments, check
out the resources in the [How-to
section](https://googleapis.github.io/genai-toolbox/how-to/)
### Integrating your application
Once your server is up and running, you can load the tools into your
@@ -726,7 +681,7 @@ For more details on configuring different types of sources, see the
### Tools
The `tools` section of a `tools.yaml` define the actions an agent can take: what
type of tool it is, which source(s) it affects, what parameters it uses, etc.
kind of tool it is, which source(s) it affects, what parameters it uses, etc.
```yaml
tools:

View File

@@ -15,7 +15,6 @@
package cmd
import (
"bytes"
"context"
_ "embed"
"fmt"
@@ -44,7 +43,6 @@ import (
// Import tool packages for side effect of registration
_ "github.com/googleapis/genai-toolbox/internal/tools/alloydbainl"
_ "github.com/googleapis/genai-toolbox/internal/tools/bigquery/bigqueryconversationalanalytics"
_ "github.com/googleapis/genai-toolbox/internal/tools/bigquery/bigqueryexecutesql"
_ "github.com/googleapis/genai-toolbox/internal/tools/bigquery/bigqueryforecast"
_ "github.com/googleapis/genai-toolbox/internal/tools/bigquery/bigquerygetdatasetinfo"
@@ -53,8 +51,6 @@ import (
_ "github.com/googleapis/genai-toolbox/internal/tools/bigquery/bigquerylisttableids"
_ "github.com/googleapis/genai-toolbox/internal/tools/bigquery/bigquerysql"
_ "github.com/googleapis/genai-toolbox/internal/tools/bigtable"
_ "github.com/googleapis/genai-toolbox/internal/tools/clickhouse/clickhouseexecutesql"
_ "github.com/googleapis/genai-toolbox/internal/tools/clickhouse/clickhousesql"
_ "github.com/googleapis/genai-toolbox/internal/tools/couchbase"
_ "github.com/googleapis/genai-toolbox/internal/tools/dataplex/dataplexlookupentry"
_ "github.com/googleapis/genai-toolbox/internal/tools/dataplex/dataplexsearchaspecttypes"
@@ -123,7 +119,6 @@ import (
_ "github.com/googleapis/genai-toolbox/internal/sources/alloydbpg"
_ "github.com/googleapis/genai-toolbox/internal/sources/bigquery"
_ "github.com/googleapis/genai-toolbox/internal/sources/bigtable"
_ "github.com/googleapis/genai-toolbox/internal/sources/clickhouse"
_ "github.com/googleapis/genai-toolbox/internal/sources/cloudsqlmssql"
_ "github.com/googleapis/genai-toolbox/internal/sources/cloudsqlmysql"
_ "github.com/googleapis/genai-toolbox/internal/sources/cloudsqlpg"
@@ -220,9 +215,6 @@ func NewCommand(opts ...Option) *Command {
o(cmd)
}
// Do not print Usage on runtime error
cmd.SilenceUsage = true
// Set server version
cmd.cfg.Version = versionString
@@ -265,15 +257,15 @@ func NewCommand(opts ...Option) *Command {
type ToolsFile struct {
Sources server.SourceConfigs `yaml:"sources"`
AuthSources server.AuthServiceConfigs `yaml:"authSources"` // Deprecated: Kept for compatibility.
AuthServices server.AuthServiceConfigs `yaml:"authServices"`
Tools server.ToolConfigs `yaml:"tools"`
Toolsets server.ToolsetConfigs `yaml:"toolsets"`
}
// parseEnv replaces environment variables ${ENV_NAME} with their values.
// also support ${ENV_NAME:default_value}.
func parseEnv(input string) (string, error) {
re := regexp.MustCompile(`\$\{(\w+)(:(\w*))?\}`)
re := regexp.MustCompile(`\$\{(\w+)\}`)
var err error
output := re.ReplaceAllStringFunc(input, func(match string) string {
@@ -284,85 +276,12 @@ func parseEnv(input string) (string, error) {
if value, found := os.LookupEnv(variableName); found {
return value
}
if parts[2] != "" {
return parts[3]
}
err = fmt.Errorf("environment variable not found: %q", variableName)
return ""
})
return output, err
}
func convertToolsFile(ctx context.Context, raw []byte) ([]byte, error) {
logger, err := util.LoggerFromContext(ctx)
if err != nil {
panic(err)
}
keysToCheck := []string{"sources", "authServices", "authSources", "tools", "toolsets"}
var input map[string]any
if err := yaml.Unmarshal(raw, &input); err != nil {
return nil, fmt.Errorf("error unmarshaling tools file: %s", err)
}
// convert to tools file v2
var toolsFileV1 bool
var buf bytes.Buffer
for _, kind := range keysToCheck {
resource, ok := input[kind]
if !ok {
// if this is skipped for all keys, the tools file is in v2
continue
}
toolsFileV1 = true
// convert `authSources` to `authServices`
if kind == "authSources" {
logger.WarnContext(ctx, "`authSources` is deprecated, use `authServices` instead")
kind = "authServices"
}
r, ok := resource.(map[string]any)
if !ok {
return nil, fmt.Errorf("'%s' is not a map", kind)
}
for name, d := range r {
buf.WriteString(fmt.Sprintf("kind: %s\n", kind))
buf.WriteString(fmt.Sprintf("name: %s\n", name))
if kind == "toolsets" {
b, err := yaml.Marshal(d)
if err != nil {
return nil, fmt.Errorf("error marshaling: %s", err)
}
buf.WriteString(fmt.Sprintf("tools:\n%s", b))
} else {
fields, ok := d.(map[string]any)
if !ok {
return nil, fmt.Errorf("fields for %s is not a map", name)
}
// Copy all existing fields, renaming 'kind' to 'type'.
buf.WriteString(fmt.Sprintf("type: %s\n", fields["kind"]))
for key, value := range fields {
if key == "kind" {
continue
}
o := map[string]any{key: value}
b, err := yaml.Marshal(o)
if err != nil {
return nil, fmt.Errorf("error marshaling: %s", err)
}
buf.Write(b)
}
}
buf.WriteString("---\n")
}
}
if !toolsFileV1 {
return raw, nil
}
return buf.Bytes(), nil
}
// parseToolsFile parses the provided yaml into appropriate configs.
func parseToolsFile(ctx context.Context, raw []byte) (ToolsFile, error) {
var toolsFile ToolsFile
@@ -373,13 +292,8 @@ func parseToolsFile(ctx context.Context, raw []byte) (ToolsFile, error) {
}
raw = []byte(output)
raw, err = convertToolsFile(ctx, raw)
if err != nil {
return toolsFile, fmt.Errorf("error converting tools file: %s", err)
}
// Parse contents
toolsFile.Sources, toolsFile.AuthServices, toolsFile.Tools, toolsFile.Toolsets, err = server.UnmarshalResourceConfig(ctx, raw)
err = yaml.UnmarshalContext(ctx, raw, &toolsFile, yaml.Strict())
if err != nil {
return toolsFile, err
}
@@ -409,6 +323,15 @@ func mergeToolsFiles(files ...ToolsFile) (ToolsFile, error) {
}
}
// Check for conflicts and merge authSources (deprecated, but still support)
for name, authSource := range file.AuthSources {
if _, exists := merged.AuthSources[name]; exists {
conflicts = append(conflicts, fmt.Sprintf("authSource '%s' (file #%d)", name, fileIndex+1))
} else {
merged.AuthSources[name] = authSource
}
}
// Check for conflicts and merge authServices
for name, authService := range file.AuthServices {
if _, exists := merged.AuthServices[name]; exists {
@@ -864,6 +787,11 @@ func run(cmd *Command) error {
}
cmd.cfg.SourceConfigs, cmd.cfg.AuthServiceConfigs, cmd.cfg.ToolConfigs, cmd.cfg.ToolsetConfigs = toolsFile.Sources, toolsFile.AuthServices, toolsFile.Tools, toolsFile.Toolsets
authSourceConfigs := toolsFile.AuthSources
if authSourceConfigs != nil {
cmd.logger.WarnContext(ctx, "`authSources` is deprecated, use `authServices` instead")
cmd.cfg.AuthServiceConfigs = authSourceConfigs
}
instrumentation, err := telemetry.CreateTelemetryInstrumentation(versionString)
if err != nil {
@@ -901,7 +829,7 @@ func run(cmd *Command) error {
}
cmd.logger.InfoContext(ctx, "Server ready to serve!")
if cmd.cfg.UI {
cmd.logger.InfoContext(ctx, fmt.Sprintf("Toolbox UI is up and running at: http://%s:%d/ui", cmd.cfg.Address, cmd.cfg.Port))
cmd.logger.InfoContext(ctx, fmt.Sprintf("Toolbox UI is up and running at: http://localhost:%d/ui", cmd.cfg.Port))
}
go func() {

View File

@@ -23,7 +23,6 @@ import (
"os"
"path"
"path/filepath"
"reflect"
"regexp"
"runtime"
"strings"
@@ -32,7 +31,6 @@ import (
"github.com/google/go-cmp/cmp"
yaml "github.com/goccy/go-yaml"
"github.com/googleapis/genai-toolbox/internal/auth/google"
"github.com/googleapis/genai-toolbox/internal/log"
"github.com/googleapis/genai-toolbox/internal/prebuiltconfigs"
@@ -208,72 +206,6 @@ func TestServerConfigFlags(t *testing.T) {
}
}
func TestParseEnv(t *testing.T) {
tcs := []struct {
desc string
env map[string]string
in string
want string
err bool
errString string
}{
{
desc: "without default without env",
in: "${FOO}",
want: "",
err: true,
errString: `environment variable not found: "FOO"`,
},
{
desc: "without default with env",
env: map[string]string{
"FOO": "bar",
},
in: "${FOO}",
want: "bar",
},
{
desc: "with empty default",
in: "${FOO:}",
want: "",
},
{
desc: "with default",
in: "${FOO:bar}",
want: "bar",
},
{
desc: "with default with env",
env: map[string]string{
"FOO": "hello",
},
in: "${FOO:bar}",
want: "hello",
},
}
for _, tc := range tcs {
t.Run(tc.desc, func(t *testing.T) {
if tc.env != nil {
for k, v := range tc.env {
t.Setenv(k, v)
}
}
got, err := parseEnv(tc.in)
if tc.err {
if err == nil {
t.Fatalf("expected error not found")
}
if tc.errString != err.Error() {
t.Fatalf("incorrect error string: got %s, want %s", err, tc.errString)
}
}
if tc.want != got {
t.Fatalf("unexpected want: got %s, want %s", got, tc.want)
}
})
}
}
func TestToolFileFlag(t *testing.T) {
tcs := []struct {
desc string
@@ -457,200 +389,6 @@ func TestDefaultLogLevel(t *testing.T) {
}
}
func TestConvertToolsFile(t *testing.T) {
ctx, cancelCtx := context.WithTimeout(context.Background(), time.Minute)
defer cancelCtx()
pr, pw := io.Pipe()
defer pw.Close()
defer pr.Close()
logger, err := log.NewStdLogger(pw, pw, "DEBUG")
if err != nil {
t.Fatalf("failed to setup logger %s", err)
}
ctx = util.WithLogger(ctx, logger)
tcs := []struct {
desc string
in string
want string
isErr bool
errStr string
}{
{
desc: "basic convert",
in: `
sources:
my-pg-instance:
kind: cloud-sql-postgres
project: my-project
region: my-region
instance: my-instance
database: my_db
user: my_user
password: my_pass
tools:
example_tool:
kind: postgres-sql
source: my-pg-instance
description: some description
statement: |
SELECT * FROM SQL_STATEMENT;
parameters:
- name: country
type: string
description: some description
toolsets:
example_toolset:
- example_tool`,
want: `
kind: sources
name: my-pg-instance
type: cloud-sql-postgres
project: my-project
region: my-region
instance: my-instance
database: my_db
user: my_user
password: my_pass
---
kind: tools
name: example_tool
type: postgres-sql
source: my-pg-instance
description: some description
statement: |
SELECT * FROM SQL_STATEMENT;
parameters:
- name: country
type: string
description: some description
---
kind: toolsets
name: example_toolset
tools:
- example_tool`,
},
{
desc: "no convertion needed",
in: `
kind: sources
name: my-pg-instance
type: cloud-sql-postgres
project: my-project
region: my-region
instance: my-instance
database: my_db
user: my_user
password: my_pass
---
kind: tools
name: example_tool
type: postgres-sql
source: my-pg-instance
description: some description
statement: |
SELECT * FROM SQL_STATEMENT;
parameters:
- name: country
type: string
description: some description
---
kind: toolsets
name: example_toolset
tools:
- example_tool`,
want: `
kind: sources
name: my-pg-instance
type: cloud-sql-postgres
project: my-project
region: my-region
instance: my-instance
database: my_db
user: my_user
password: my_pass
---
kind: tools
name: example_tool
type: postgres-sql
source: my-pg-instance
description: some description
statement: |
SELECT * FROM SQL_STATEMENT;
parameters:
- name: country
type: string
description: some description
---
kind: toolsets
name: example_toolset
tools:
- example_tool`,
},
{
desc: "invalid source",
in: `sources: invalid`,
isErr: true,
errStr: "'sources' is not a map",
},
{
desc: "invalid toolset",
in: `toolsets: invalid`,
isErr: true,
errStr: "'toolsets' is not a map",
},
}
for _, tc := range tcs {
t.Run(tc.desc, func(t *testing.T) {
output, err := convertToolsFile(ctx, []byte(tc.in))
if tc.isErr {
if err == nil {
t.Fatalf("missing error: %s", tc.errStr)
}
if err.Error() != tc.errStr {
t.Fatalf("invalid error string: got %s, want %s", err, tc.errStr)
}
return
}
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
outputObj, err := unmarshalYAMLUtil(output)
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
wantObj, err := unmarshalYAMLUtil([]byte(tc.want))
if err != nil {
t.Fatalf("unexpected error: %s", err)
}
if !reflect.DeepEqual(outputObj, wantObj) {
t.Fatalf("incorrect output: got %s, want %s", outputObj, wantObj)
}
})
}
}
// unmarshalYAMLUtil decodes a multi-document YAML string into a slice of generic maps.
func unmarshalYAMLUtil(yamlStr []byte) ([]map[string]any, error) {
decoder := yaml.NewDecoder(bytes.NewReader(yamlStr))
var docs []map[string]any
for {
var doc map[string]any
err := decoder.Decode(&doc)
if err != nil {
if err.Error() == "EOF" {
break
}
return nil, err
}
docs = append(docs, doc)
}
return docs, nil
}
func TestParseToolFile(t *testing.T) {
ctx, err := testutils.ContextWithNewLogger()
if err != nil {
@@ -692,7 +430,7 @@ func TestParseToolFile(t *testing.T) {
Sources: server.SourceConfigs{
"my-pg-instance": cloudsqlpgsrc.Config{
Name: "my-pg-instance",
Type: cloudsqlpgsrc.SourceType,
Kind: cloudsqlpgsrc.SourceKind,
Project: "my-project",
Region: "my-region",
Instance: "my-instance",
@@ -705,72 +443,7 @@ func TestParseToolFile(t *testing.T) {
Tools: server.ToolConfigs{
"example_tool": postgressql.Config{
Name: "example_tool",
Type: "postgres-sql",
Source: "my-pg-instance",
Description: "some description",
Statement: "SELECT * FROM SQL_STATEMENT;\n",
Parameters: []tools.Parameter{
tools.NewStringParameter("country", "some description"),
},
AuthRequired: []string{},
},
},
Toolsets: server.ToolsetConfigs{
"example_toolset": tools.ToolsetConfig{
Name: "example_toolset",
ToolNames: []string{"example_tool"},
},
},
},
},
{
description: "basic example",
in: `
kind: sources
name: my-pg-instance
type: cloud-sql-postgres
project: my-project
region: my-region
instance: my-instance
database: my_db
user: my_user
password: my_pass
---
kind: tools
name: example_tool
type: postgres-sql
source: my-pg-instance
description: some description
statement: |
SELECT * FROM SQL_STATEMENT;
parameters:
- name: country
type: string
description: some description
---
kind: toolsets
name: example_toolset
tools:
- example_tool
`,
wantToolsFile: ToolsFile{
Sources: server.SourceConfigs{
"my-pg-instance": cloudsqlpgsrc.Config{
Name: "my-pg-instance",
Type: cloudsqlpgsrc.SourceType,
Project: "my-project",
Region: "my-region",
Instance: "my-instance",
IPType: "public",
Database: "my_db",
User: "my_user",
Password: "my_pass",
},
},
Tools: server.ToolConfigs{
"example_tool": postgressql.Config{
Name: "example_tool",
Type: "postgres-sql",
Kind: "postgres-sql",
Source: "my-pg-instance",
Description: "some description",
Statement: "SELECT * FROM SQL_STATEMENT;\n",
@@ -876,7 +549,7 @@ func TestParseToolFileWithAuth(t *testing.T) {
Sources: server.SourceConfigs{
"my-pg-instance": cloudsqlpgsrc.Config{
Name: "my-pg-instance",
Type: cloudsqlpgsrc.SourceType,
Kind: cloudsqlpgsrc.SourceKind,
Project: "my-project",
Region: "my-region",
Instance: "my-instance",
@@ -889,19 +562,19 @@ func TestParseToolFileWithAuth(t *testing.T) {
AuthServices: server.AuthServiceConfigs{
"my-google-service": google.Config{
Name: "my-google-service",
Type: google.AuthServiceType,
Kind: google.AuthServiceKind,
ClientID: "my-client-id",
},
"other-google-service": google.Config{
Name: "other-google-service",
Type: google.AuthServiceType,
Kind: google.AuthServiceKind,
ClientID: "other-client-id",
},
},
Tools: server.ToolConfigs{
"example_tool": postgressql.Config{
Name: "example_tool",
Type: "postgres-sql",
Kind: "postgres-sql",
Source: "my-pg-instance",
Description: "some description",
Statement: "SELECT * FROM SQL_STATEMENT;\n",
@@ -975,7 +648,7 @@ func TestParseToolFileWithAuth(t *testing.T) {
Sources: server.SourceConfigs{
"my-pg-instance": cloudsqlpgsrc.Config{
Name: "my-pg-instance",
Type: cloudsqlpgsrc.SourceType,
Kind: cloudsqlpgsrc.SourceKind,
Project: "my-project",
Region: "my-region",
Instance: "my-instance",
@@ -985,22 +658,22 @@ func TestParseToolFileWithAuth(t *testing.T) {
Password: "my_pass",
},
},
AuthServices: server.AuthServiceConfigs{
AuthSources: server.AuthServiceConfigs{
"my-google-service": google.Config{
Name: "my-google-service",
Type: google.AuthServiceType,
Kind: google.AuthServiceKind,
ClientID: "my-client-id",
},
"other-google-service": google.Config{
Name: "other-google-service",
Type: google.AuthServiceType,
Kind: google.AuthServiceKind,
ClientID: "other-client-id",
},
},
Tools: server.ToolConfigs{
"example_tool": postgressql.Config{
Name: "example_tool",
Type: "postgres-sql",
Kind: "postgres-sql",
Source: "my-pg-instance",
Description: "some description",
Statement: "SELECT * FROM SQL_STATEMENT;\n",
@@ -1076,7 +749,7 @@ func TestParseToolFileWithAuth(t *testing.T) {
Sources: server.SourceConfigs{
"my-pg-instance": cloudsqlpgsrc.Config{
Name: "my-pg-instance",
Type: cloudsqlpgsrc.SourceType,
Kind: cloudsqlpgsrc.SourceKind,
Project: "my-project",
Region: "my-region",
Instance: "my-instance",
@@ -1089,19 +762,19 @@ func TestParseToolFileWithAuth(t *testing.T) {
AuthServices: server.AuthServiceConfigs{
"my-google-service": google.Config{
Name: "my-google-service",
Type: google.AuthServiceType,
Kind: google.AuthServiceKind,
ClientID: "my-client-id",
},
"other-google-service": google.Config{
Name: "other-google-service",
Type: google.AuthServiceType,
Kind: google.AuthServiceKind,
ClientID: "other-client-id",
},
},
Tools: server.ToolConfigs{
"example_tool": postgressql.Config{
Name: "example_tool",
Type: "postgres-sql",
Kind: "postgres-sql",
Source: "my-pg-instance",
Description: "some description",
Statement: "SELECT * FROM SQL_STATEMENT;\n",
@@ -1233,7 +906,7 @@ func TestEnvVarReplacement(t *testing.T) {
Sources: server.SourceConfigs{
"my-http-instance": httpsrc.Config{
Name: "my-http-instance",
Type: httpsrc.SourceType,
Kind: httpsrc.SourceKind,
BaseURL: "http://test_server/",
Timeout: "10s",
DefaultHeaders: map[string]string{"Authorization": "ACTUAL_HEADER"},
@@ -1243,19 +916,19 @@ func TestEnvVarReplacement(t *testing.T) {
AuthServices: server.AuthServiceConfigs{
"my-google-service": google.Config{
Name: "my-google-service",
Type: google.AuthServiceType,
Kind: google.AuthServiceKind,
ClientID: "ACTUAL_CLIENT_ID",
},
"other-google-service": google.Config{
Name: "other-google-service",
Type: google.AuthServiceType,
Kind: google.AuthServiceKind,
ClientID: "ACTUAL_CLIENT_ID_2",
},
},
Tools: server.ToolConfigs{
"example_tool": http.Config{
Name: "example_tool",
Type: "http",
Kind: "http",
Source: "my-instance",
Method: "GET",
Path: "search?name=alice&pet=cat",
@@ -1493,7 +1166,6 @@ func TestPrebuiltTools(t *testing.T) {
alloydb_admin_config, _ := prebuiltconfigs.Get("alloydb-postgres-admin")
alloydb_config, _ := prebuiltconfigs.Get("alloydb-postgres")
bigquery_config, _ := prebuiltconfigs.Get("bigquery")
clickhouse_config, _ := prebuiltconfigs.Get("clickhouse")
cloudsqlpg_config, _ := prebuiltconfigs.Get("cloud-sql-postgres")
cloudsqlmysql_config, _ := prebuiltconfigs.Get("cloud-sql-mysql")
cloudsqlmssql_config, _ := prebuiltconfigs.Get("cloud-sql-mssql")
@@ -1526,13 +1198,6 @@ func TestPrebuiltTools(t *testing.T) {
t.Setenv("ALLOYDB_POSTGRES_USER", "your_alloydb_user")
t.Setenv("ALLOYDB_POSTGRES_PASSWORD", "your_alloydb_password")
t.Setenv("CLICKHOUSE_PROTOCOL", "your_clickhouse_protocol")
t.Setenv("CLICKHOUSE_DATABASE", "your_clickhouse_database")
t.Setenv("CLICKHOUSE_PASSWORD", "your_clickhouse_password")
t.Setenv("CLICKHOUSE_USER", "your_clickhouse_user")
t.Setenv("CLICKHOUSE_HOST", "your_clickhosue_host")
t.Setenv("CLICKHOUSE_PORT", "8123")
t.Setenv("CLOUD_SQL_POSTGRES_PROJECT", "your_pg_project")
t.Setenv("CLOUD_SQL_POSTGRES_INSTANCE", "your_pg_instance")
t.Setenv("CLOUD_SQL_POSTGRES_DATABASE", "your_pg_db")
@@ -1614,17 +1279,7 @@ func TestPrebuiltTools(t *testing.T) {
wantToolset: server.ToolsetConfigs{
"bigquery-database-tools": tools.ToolsetConfig{
Name: "bigquery-database-tools",
ToolNames: []string{"ask_data_insights", "execute_sql", "forecast", "get_dataset_info", "get_table_info", "list_dataset_ids", "list_table_ids"},
},
},
},
{
name: "clickhouse prebuilt tools",
in: clickhouse_config,
wantToolset: server.ToolsetConfigs{
"clickhouse-database-tools": tools.ToolsetConfig{
Name: "clickhouse-database-tools",
ToolNames: []string{"execute_sql"},
ToolNames: []string{"execute_sql", "forecast", "get_dataset_info", "get_table_info", "list_dataset_ids", "list_table_ids"},
},
},
},

View File

@@ -1 +1 @@
0.13.0
0.12.0

View File

@@ -64,7 +64,7 @@ The structured logging outputs log as JSON:
"timestamp":"2024-11-04T16:45:11.987299-08:00",
"severity":"ERROR",
"logging.googleapis.com/sourceLocation":{...},
"message":"unable to parse tool file at \"tools.yaml\": \"cloud-sql-postgres1\" is not a valid type of data source"
"message":"unable to parse tool file at \"tools.yaml\": \"cloud-sql-postgres1\" is not a valid kind of data source"
}
```

View File

@@ -234,7 +234,7 @@
},
"outputs": [],
"source": [
"version = \"0.13.0\" # x-release-please-version\n",
"version = \"0.12.0\" # x-release-please-version\n",
"! curl -O https://storage.googleapis.com/genai-toolbox/v{version}/linux/amd64/toolbox\n",
"\n",
"# Make the binary executable\n",

View File

@@ -22,11 +22,6 @@ etc., you could use environment variables instead with the format `${ENV_NAME}`.
user: ${USER_NAME}
password: ${PASSWORD}
```
A default value can be specified like `${ENV_NAME:default}`.
```yaml
port: ${DB_PORT:3306}
```
### Sources
@@ -51,7 +46,7 @@ For more details on configuring different types of sources, see the
### Tools
The `tools` section of your `tools.yaml` defines the actions your agent can
take: what type of tool it is, which source(s) it affects, what parameters it
take: what kind of tool it is, which source(s) it affects, what parameters it
uses, etc.
```yaml

View File

@@ -86,7 +86,7 @@ To install Toolbox as a binary:
```sh
# see releases page for other versions
export VERSION=0.13.0
export VERSION=0.12.0
curl -O https://storage.googleapis.com/genai-toolbox/v$VERSION/linux/amd64/toolbox
chmod +x toolbox
```
@@ -97,7 +97,7 @@ You can also install Toolbox as a container:
```sh
# see releases page for other versions
export VERSION=0.13.0
export VERSION=0.12.0
docker pull us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:$VERSION
```
@@ -115,7 +115,7 @@ To install from source, ensure you have the latest version of
[Go installed](https://go.dev/doc/install), and then run the following command:
```sh
go install github.com/googleapis/genai-toolbox@v0.13.0
go install github.com/googleapis/genai-toolbox@v0.12.0
```
{{% /tab %}}

View File

@@ -94,23 +94,305 @@ pip install google-genai
code to create an agent:
{{< tabpane persist=header >}}
{{< tab header="ADK" lang="python" >}}
from google.adk.agents import Agent
from google.adk.runners import Runner
from google.adk.sessions import InMemorySessionService
from google.adk.artifacts.in_memory_artifact_service import InMemoryArtifactService
from google.genai import types
from toolbox_core import ToolboxSyncClient
{{< include "quickstart/python/adk/quickstart.py" >}}
import asyncio
import os
# TODO(developer): replace this with your Google API key
os.environ['GOOGLE_API_KEY'] = 'your-api-key'
async def main():
with ToolboxSyncClient("<http://127.0.0.1:5000>") as toolbox_client:
prompt = """
You're a helpful hotel assistant. You handle hotel searching, booking and
cancellations. When the user searches for a hotel, mention it's name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
"""
root_agent = Agent(
model='gemini-2.0-flash-001',
name='hotel_agent',
description='A helpful AI assistant.',
instruction=prompt,
tools=toolbox_client.load_toolset("my-toolset"),
)
session_service = InMemorySessionService()
artifacts_service = InMemoryArtifactService()
session = await session_service.create_session(
state={}, app_name='hotel_agent', user_id='123'
)
runner = Runner(
app_name='hotel_agent',
agent=root_agent,
artifact_service=artifacts_service,
session_service=session_service,
)
queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
]
for query in queries:
content = types.Content(role='user', parts=[types.Part(text=query)])
events = runner.run(session_id=session.id,
user_id='123', new_message=content)
responses = (
part.text
for event in events
for part in event.content.parts
if part.text is not None
)
for text in responses:
print(text)
asyncio.run(main())
{{< /tab >}}
{{< tab header="LangChain" lang="python" >}}
import asyncio
{{< include "quickstart/python/langchain/quickstart.py" >}}
from langgraph.prebuilt import create_react_agent
# TODO(developer): replace this with another import if needed
from langchain_google_vertexai import ChatVertexAI
# from langchain_google_genai import ChatGoogleGenerativeAI
# from langchain_anthropic import ChatAnthropic
from langgraph.checkpoint.memory import MemorySaver
from toolbox_langchain import ToolboxClient
prompt = """
You're a helpful hotel assistant. You handle hotel searching, booking and
cancellations. When the user searches for a hotel, mention it's name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
"""
queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
]
async def run_application():
# TODO(developer): replace this with another model if needed
model = ChatVertexAI(model_name="gemini-2.0-flash-001")
# model = ChatGoogleGenerativeAI(model="gemini-2.0-flash-001")
# model = ChatAnthropic(model="claude-3-5-sonnet-20240620")
# Load the tools from the Toolbox server
async with ToolboxClient("http://127.0.0.1:5000") as client:
tools = await client.aload_toolset()
agent = create_react_agent(model, tools, checkpointer=MemorySaver())
config = {"configurable": {"thread_id": "thread-1"}}
for query in queries:
inputs = {"messages": [("user", prompt + query)]}
response = agent.invoke(inputs, stream_mode="values", config=config)
print(response["messages"][-1].content)
asyncio.run(run_application())
{{< /tab >}}
{{< tab header="LlamaIndex" lang="python" >}}
import asyncio
import os
{{< include "quickstart/python/llamaindex/quickstart.py" >}}
from llama_index.core.agent.workflow import AgentWorkflow
from llama_index.core.workflow import Context
# TODO(developer): replace this with another import if needed
from llama_index.llms.google_genai import GoogleGenAI
# from llama_index.llms.anthropic import Anthropic
from toolbox_llamaindex import ToolboxClient
prompt = """
You're a helpful hotel assistant. You handle hotel searching, booking and
cancellations. When the user searches for a hotel, mention it's name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
"""
queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
]
async def run_application():
# TODO(developer): replace this with another model if needed
llm = GoogleGenAI(
model="gemini-2.0-flash-001",
vertexai_config={"project": "project-id", "location": "us-central1"},
)
# llm = GoogleGenAI(
# api_key=os.getenv("GOOGLE_API_KEY"),
# model="gemini-2.0-flash-001",
# )
# llm = Anthropic(
# model="claude-3-7-sonnet-latest",
# api_key=os.getenv("ANTHROPIC_API_KEY")
# )
# Load the tools from the Toolbox server
async with ToolboxClient("http://127.0.0.1:5000") as client:
tools = await client.aload_toolset()
agent = AgentWorkflow.from_tools_or_functions(
tools,
llm=llm,
system_prompt=prompt,
)
ctx = Context(agent)
for query in queries:
response = await agent.run(user_msg=query, ctx=ctx)
print(f"---- {query} ----")
print(str(response))
asyncio.run(run_application())
{{< /tab >}}
{{< tab header="Core" lang="python" >}}
import asyncio
{{< include "quickstart/python/core/quickstart.py" >}}
from google import genai
from google.genai.types import (
Content,
FunctionDeclaration,
GenerateContentConfig,
Part,
Tool,
)
from toolbox_core import ToolboxClient
prompt = """
You're a helpful hotel assistant. You handle hotel searching, booking and
cancellations. When the user searches for a hotel, mention it's name, id,
location and price tier. Always mention hotel id while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
"""
queries = [
"Find hotels in Basel with Basel in its name.",
"Please book the hotel Hilton Basel for me.",
"This is too expensive. Please cancel it.",
"Please book Hyatt Regency for me",
"My check in dates for my booking would be from April 10, 2024 to April 19, 2024.",
]
async def run_application():
async with ToolboxClient("<http://127.0.0.1:5000>") as toolbox_client:
# The toolbox_tools list contains Python callables (functions/methods) designed for LLM tool-use
# integration. While this example uses Google's genai client, these callables can be adapted for
# various function-calling or agent frameworks. For easier integration with supported frameworks
# (https://github.com/googleapis/mcp-toolbox-python-sdk/tree/main/packages), use the
# provided wrapper packages, which handle framework-specific boilerplate.
toolbox_tools = await toolbox_client.load_toolset("my-toolset")
genai_client = genai.Client(
vertexai=True, project="project-id", location="us-central1"
)
genai_tools = [
Tool(
function_declarations=[
FunctionDeclaration.from_callable_with_api_option(callable=tool)
]
)
for tool in toolbox_tools
]
history = []
for query in queries:
user_prompt_content = Content(
role="user",
parts=[Part.from_text(text=query)],
)
history.append(user_prompt_content)
response = genai_client.models.generate_content(
model="gemini-2.0-flash-001",
contents=history,
config=GenerateContentConfig(
system_instruction=prompt,
tools=genai_tools,
),
)
history.append(response.candidates[0].content)
function_response_parts = []
for function_call in response.function_calls:
fn_name = function_call.name
# The tools are sorted alphabetically
if fn_name == "search-hotels-by-name":
function_result = await toolbox_tools[3](**function_call.args)
elif fn_name == "search-hotels-by-location":
function_result = await toolbox_tools[2](**function_call.args)
elif fn_name == "book-hotel":
function_result = await toolbox_tools[0](**function_call.args)
elif fn_name == "update-hotel":
function_result = await toolbox_tools[4](**function_call.args)
elif fn_name == "cancel-hotel":
function_result = await toolbox_tools[1](**function_call.args)
else:
raise ValueError("Function name not present.")
function_response = {"result": function_result}
function_response_part = Part.from_function_response(
name=function_call.name,
response=function_response,
)
function_response_parts.append(function_response_part)
if function_response_parts:
tool_response_content = Content(role="tool", parts=function_response_parts)
history.append(tool_response_content)
response2 = genai_client.models.generate_content(
model="gemini-2.0-flash-001",
contents=history,
config=GenerateContentConfig(
tools=genai_tools,
),
)
final_model_response_content = response2.candidates[0].content
history.append(final_model_response_content)
print(response2.text)
asyncio.run(run_application())
{{< /tab >}}
{{< /tabpane >}}

View File

@@ -522,7 +522,6 @@ import (
"context"
"encoding/json"
"log"
"fmt
"github.com/googleapis/mcp-toolbox-sdk-go/core"
openai "github.com/openai/openai-go"
@@ -652,7 +651,7 @@ func main() {
params.Messages = append(params.Messages, openai.AssistantMessage(query))
fmt.println("\n", completion.Choices[0].Message.Content)
println("\n", completion.Choices[0].Message.Content)
}

View File

@@ -64,26 +64,384 @@ npm install @google/genai
{{< tabpane persist=header >}}
{{< tab header="LangChain" lang="js" >}}
{{< include "quickstart/js/langchain/quickstart.js" >}}
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
import { ToolboxClient } from "@toolbox-sdk/core";
import { tool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { MemorySaver } from "@langchain/langgraph";
// Replace it with your API key
process.env.GOOGLE_API_KEY = 'your-api-key';
const prompt = `
You're a helpful hotel assistant. You handle hotel searching, booking, and
cancellations. When the user searches for a hotel, mention its name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
`;
const queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
];
async function runApplication() {
const model = new ChatGoogleGenerativeAI({
model: "gemini-2.0-flash",
});
const client = new ToolboxClient("http://127.0.0.1:5000");
const toolboxTools = await client.loadToolset("my-toolset");
// Define the basics of the tool: name, description, schema and core logic
const getTool = (toolboxTool) => tool(toolboxTool, {
name: toolboxTool.getName(),
description: toolboxTool.getDescription(),
schema: toolboxTool.getParamSchema()
});
const tools = toolboxTools.map(getTool);
const agent = createReactAgent({
llm: model,
tools: tools,
checkpointer: new MemorySaver(),
systemPrompt: prompt,
});
const langGraphConfig = {
configurable: {
thread_id: "test-thread",
},
};
for (const query of queries) {
const agentOutput = await agent.invoke(
{
messages: [
{
role: "user",
content: query,
},
],
verbose: true,
},
langGraphConfig
);
const response = agentOutput.messages[agentOutput.messages.length - 1].content;
console.log(response);
}
}
runApplication()
.catch(console.error)
.finally(() => console.log("\nApplication finished."));
{{< /tab >}}
{{< tab header="GenkitJS" lang="js" >}}
{{< include "quickstart/js/genkit/quickstart.js" >}}
import { ToolboxClient } from "@toolbox-sdk/core";
import { genkit } from "genkit";
import { googleAI } from '@genkit-ai/googleai';
// Replace it with your API key
process.env.GOOGLE_API_KEY = 'your-api-key';
const systemPrompt = `
You're a helpful hotel assistant. You handle hotel searching, booking, and
cancellations. When the user searches for a hotel, mention its name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
`;
const queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
];
async function run() {
const toolboxClient = new ToolboxClient("http://127.0.0.1:5000");
const ai = genkit({
plugins: [
googleAI({
apiKey: process.env.GEMINI_API_KEY || process.env.GOOGLE_API_KEY
})
],
model: googleAI.model('gemini-2.0-flash'),
});
const toolboxTools = await toolboxClient.loadToolset("my-toolset");
const toolMap = Object.fromEntries(
toolboxTools.map((tool) => {
const definedTool = ai.defineTool(
{
name: tool.getName(),
description: tool.getDescription(),
inputSchema: tool.getParamSchema(),
},
tool
);
return [tool.getName(), definedTool];
})
);
const tools = Object.values(toolMap);
let conversationHistory = [{ role: "system", content: [{ text: systemPrompt }] }];
for (const query of queries) {
conversationHistory.push({ role: "user", content: [{ text: query }] });
const response = await ai.generate({
messages: conversationHistory,
tools: tools,
});
conversationHistory.push(response.message);
const toolRequests = response.toolRequests;
if (toolRequests?.length > 0) {
// Execute tools concurrently and collect their responses.
const toolResponses = await Promise.all(
toolRequests.map(async (call) => {
try {
const toolOutput = await toolMap[call.name].invoke(call.input);
return { role: "tool", content: [{ toolResponse: { name: call.name, output: toolOutput } }] };
} catch (e) {
console.error(`Error executing tool ${call.name}:`, e);
return { role: "tool", content: [{ toolResponse: { name: call.name, output: { error: e.message } } }] };
}
})
);
conversationHistory.push(...toolResponses);
// Call the AI again with the tool results.
response = await ai.generate({ messages: conversationHistory, tools });
conversationHistory.push(response.message);
}
console.log(response.text);
}
}
run();
{{< /tab >}}
{{< tab header="LlamaIndex" lang="js" >}}
{{< include "quickstart/js/llamaindex/quickstart.js" >}}
import { gemini, GEMINI_MODEL } from "@llamaindex/google";
import { agent } from "@llamaindex/workflow";
import { createMemory, staticBlock, tool } from "llamaindex";
import { ToolboxClient } from "@toolbox-sdk/core";
const TOOLBOX_URL = "http://127.0.0.1:5000"; // Update if needed
process.env.GOOGLE_API_KEY = 'your-api-key'; // Replace it with your API key
const prompt = `
You're a helpful hotel assistant. You handle hotel searching, booking and cancellations.
When the user searches for a hotel, mention its name, id, location and price tier.
Always mention hotel ids while performing any searches — this is very important for operations.
For any bookings or cancellations, please provide the appropriate confirmation.
Update check-in or check-out dates if mentioned by the user.
Don't ask for confirmations from the user.
`;
const queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
];
async function main() {
// Connect to MCP Toolbox
const client = new ToolboxClient(TOOLBOX_URL);
const toolboxTools = await client.loadToolset("my-toolset");
const tools = toolboxTools.map((toolboxTool) => {
return tool({
name: toolboxTool.getName(),
description: toolboxTool.getDescription(),
parameters: toolboxTool.getParamSchema(),
execute: toolboxTool,
});
});
// Initialize LLM
const llm = gemini({
model: GEMINI_MODEL.GEMINI_2_0_FLASH,
apiKey: process.env.GOOGLE_API_KEY,
});
const memory = createMemory({
memoryBlocks: [
staticBlock({
content: prompt,
}),
],
});
// Create the Agent
const myAgent = agent({
tools: tools,
llm,
memory,
systemPrompt: prompt,
});
for (const query of queries) {
const result = await myAgent.run(query);
const output = result.data.result;
console.log(`\nUser: ${query}`);
if (typeof output === "string") {
console.log(output.trim());
} else if (typeof output === "object" && "text" in output) {
console.log(output.text.trim());
} else {
console.log(JSON.stringify(output));
}
}
//You may observe some extra logs during execution due to the run method provided by Llama.
console.log("Agent run finished.");
}
main();
{{< /tab >}}
{{< tab header="GoogleGenAI" lang="js" >}}
import { GoogleGenAI } from "@google/genai";
import { ToolboxClient } from "@toolbox-sdk/core";
{{< include "quickstart/js/genAI/quickstart.js" >}}
const TOOLBOX_URL = "http://127.0.0.1:5000"; // Update if needed
const GOOGLE_API_KEY = 'enter your api here'; // Replace it with your API key
const prompt = `
You're a helpful hotel assistant. You handle hotel searching, booking, and
cancellations. When the user searches for a hotel, you MUST use the available tools to find information. Mention its name, id,
location and price tier. Always mention hotel id while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
`;
const queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
];
function mapZodTypeToOpenAPIType(zodTypeName) {
console.log(zodTypeName)
const typeMap = {
'ZodString': 'string',
'ZodNumber': 'number',
'ZodBoolean': 'boolean',
'ZodArray': 'array',
'ZodObject': 'object',
};
return typeMap[zodTypeName] || 'string';
}
async function runApplication() {
const toolboxClient = new ToolboxClient(TOOLBOX_URL);
const toolboxTools = await toolboxClient.loadToolset("my-toolset");
const geminiTools = [{
functionDeclarations: toolboxTools.map(tool => {
const schema = tool.getParamSchema();
const properties = {};
const required = [];
for (const [key, param] of Object.entries(schema.shape)) {
properties[key] = {
type: mapZodTypeToOpenAPIType(param.constructor.name),
description: param.description || '',
};
required.push(key)
}
return {
name: tool.getName(),
description: tool.getDescription(),
parameters: { type: 'object', properties, required },
};
})
}];
const genAI = new GoogleGenAI({ apiKey: GOOGLE_API_KEY });
const chat = genAI.chats.create({
model: "gemini-2.5-flash",
config: {
systemInstruction: prompt,
tools: geminiTools,
}
});
for (const query of queries) {
let currentResult = await chat.sendMessage({ message: query });
let finalResponseGiven = false
while (!finalResponseGiven) {
const response = currentResult;
const functionCalls = response.functionCalls || [];
if (functionCalls.length === 0) {
console.log(response.text)
finalResponseGiven = true;
} else {
const toolResponses = [];
for (const call of functionCalls) {
const toolName = call.name
const toolToExecute = toolboxTools.find(t => t.getName() === toolName);
if (toolToExecute) {
try {
const functionResult = await toolToExecute(call.args);
toolResponses.push({
functionResponse: { name: call.name, response: { result: functionResult } }
});
} catch (e) {
console.error(`Error executing tool '${toolName}':`, e);
toolResponses.push({
functionResponse: { name: call.name, response: { error: e.message } }
});
}
}
}
currentResult = await chat.sendMessage({ message: toolResponses });
}
}
}
}
runApplication()
.catch(console.error)
.finally(() => console.log("\nApplication finished."));
{{< /tab >}}
{{< /tabpane >}}

View File

@@ -105,7 +105,7 @@ In this section, we will download Toolbox, configure our tools in a
<!-- {x-release-please-start-version} -->
```bash
export OS="linux/amd64" # one of linux/amd64, darwin/arm64, darwin/amd64, or windows/amd64
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/$OS/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/$OS/toolbox
```
<!-- {x-release-please-end} -->

View File

@@ -1,119 +0,0 @@
import { GoogleGenAI } from "@google/genai";
import { ToolboxClient } from "@toolbox-sdk/core";
const TOOLBOX_URL = "http://127.0.0.1:5000"; // Update if needed
const GOOGLE_API_KEY = 'enter your api here'; // Replace it with your API key
const prompt = `
You're a helpful hotel assistant. You handle hotel searching, booking, and
cancellations. When the user searches for a hotel, you MUST use the available tools to find information. Mention its name, id,
location and price tier. Always mention hotel id while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
`;
const queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
];
function mapZodTypeToOpenAPIType(zodTypeName) {
console.log(zodTypeName)
const typeMap = {
'ZodString': 'string',
'ZodNumber': 'number',
'ZodBoolean': 'boolean',
'ZodArray': 'array',
'ZodObject': 'object',
};
return typeMap[zodTypeName] || 'string';
}
async function main() {
const toolboxClient = new ToolboxClient(TOOLBOX_URL);
const toolboxTools = await toolboxClient.loadToolset("my-toolset");
const geminiTools = [{
functionDeclarations: toolboxTools.map(tool => {
const schema = tool.getParamSchema();
const properties = {};
const required = [];
for (const [key, param] of Object.entries(schema.shape)) {
properties[key] = {
type: mapZodTypeToOpenAPIType(param.constructor.name),
description: param.description || '',
};
required.push(key)
}
return {
name: tool.getName(),
description: tool.getDescription(),
parameters: { type: 'object', properties, required },
};
})
}];
const genAI = new GoogleGenAI({ apiKey: GOOGLE_API_KEY });
const chat = genAI.chats.create({
model: "gemini-2.5-flash",
config: {
systemInstruction: prompt,
tools: geminiTools,
}
});
for (const query of queries) {
let currentResult = await chat.sendMessage({ message: query });
let finalResponseGiven = false
while (!finalResponseGiven) {
const response = currentResult;
const functionCalls = response.functionCalls || [];
if (functionCalls.length === 0) {
console.log(response.text)
finalResponseGiven = true;
} else {
const toolResponses = [];
for (const call of functionCalls) {
const toolName = call.name
const toolToExecute = toolboxTools.find(t => t.getName() === toolName);
if (toolToExecute) {
try {
const functionResult = await toolToExecute(call.args);
toolResponses.push({
functionResponse: { name: call.name, response: { result: functionResult } }
});
} catch (e) {
console.error(`Error executing tool '${toolName}':`, e);
toolResponses.push({
functionResponse: { name: call.name, response: { error: e.message } }
});
}
}
}
currentResult = await chat.sendMessage({ message: toolResponses });
}
}
}
}
main();

View File

@@ -1,89 +0,0 @@
import { ToolboxClient } from "@toolbox-sdk/core";
import { genkit } from "genkit";
import { googleAI } from '@genkit-ai/googleai';
// Replace it with your API key
process.env.GOOGLE_API_KEY = 'your-api-key';
const systemPrompt = `
You're a helpful hotel assistant. You handle hotel searching, booking, and
cancellations. When the user searches for a hotel, mention its name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
`;
const queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
];
async function main() {
const toolboxClient = new ToolboxClient("http://127.0.0.1:5000");
const ai = genkit({
plugins: [
googleAI({
apiKey: process.env.GEMINI_API_KEY || process.env.GOOGLE_API_KEY
})
],
model: googleAI.model('gemini-2.0-flash'),
});
const toolboxTools = await toolboxClient.loadToolset("my-toolset");
const toolMap = Object.fromEntries(
toolboxTools.map((tool) => {
const definedTool = ai.defineTool(
{
name: tool.getName(),
description: tool.getDescription(),
inputSchema: tool.getParamSchema(),
},
tool
);
return [tool.getName(), definedTool];
})
);
const tools = Object.values(toolMap);
let conversationHistory = [{ role: "system", content: [{ text: systemPrompt }] }];
for (const query of queries) {
conversationHistory.push({ role: "user", content: [{ text: query }] });
const response = await ai.generate({
messages: conversationHistory,
tools: tools,
});
conversationHistory.push(response.message);
const toolRequests = response.toolRequests;
if (toolRequests?.length > 0) {
// Execute tools concurrently and collect their responses.
const toolResponses = await Promise.all(
toolRequests.map(async (call) => {
try {
const toolOutput = await toolMap[call.name].invoke(call.input);
return { role: "tool", content: [{ toolResponse: { name: call.name, output: toolOutput } }] };
} catch (e) {
console.error(`Error executing tool ${call.name}:`, e);
return { role: "tool", content: [{ toolResponse: { name: call.name, output: { error: e.message } } }] };
}
})
);
conversationHistory.push(...toolResponses);
// Call the AI again with the tool results.
response = await ai.generate({ messages: conversationHistory, tools });
conversationHistory.push(response.message);
}
console.log(response.text);
}
}
main();

View File

@@ -1,74 +0,0 @@
import { ChatGoogleGenerativeAI } from "@langchain/google-genai";
import { ToolboxClient } from "@toolbox-sdk/core";
import { tool } from "@langchain/core/tools";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { MemorySaver } from "@langchain/langgraph";
// Replace it with your API key
process.env.GOOGLE_API_KEY = 'your-api-key';
const prompt = `
You're a helpful hotel assistant. You handle hotel searching, booking, and
cancellations. When the user searches for a hotel, mention its name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
`;
const queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
];
async function main() {
const model = new ChatGoogleGenerativeAI({
model: "gemini-2.0-flash",
});
const client = new ToolboxClient("http://127.0.0.1:5000");
const toolboxTools = await client.loadToolset("my-toolset");
// Define the basics of the tool: name, description, schema and core logic
const getTool = (toolboxTool) => tool(toolboxTool, {
name: toolboxTool.getName(),
description: toolboxTool.getDescription(),
schema: toolboxTool.getParamSchema()
});
const tools = toolboxTools.map(getTool);
const agent = createReactAgent({
llm: model,
tools: tools,
checkpointer: new MemorySaver(),
systemPrompt: prompt,
});
const langGraphConfig = {
configurable: {
thread_id: "test-thread",
},
};
for (const query of queries) {
const agentOutput = await agent.invoke(
{
messages: [
{
role: "user",
content: query,
},
],
verbose: true,
},
langGraphConfig
);
const response = agentOutput.messages[agentOutput.messages.length - 1].content;
console.log(response);
}
}
main();

View File

@@ -1,79 +0,0 @@
import { gemini, GEMINI_MODEL } from "@llamaindex/google";
import { agent } from "@llamaindex/workflow";
import { createMemory, staticBlock, tool } from "llamaindex";
import { ToolboxClient } from "@toolbox-sdk/core";
const TOOLBOX_URL = "http://127.0.0.1:5000"; // Update if needed
process.env.GOOGLE_API_KEY = 'your-api-key'; // Replace it with your API key
const prompt = `
You're a helpful hotel assistant. You handle hotel searching, booking and cancellations.
When the user searches for a hotel, mention its name, id, location and price tier.
Always mention hotel ids while performing any searches — this is very important for operations.
For any bookings or cancellations, please provide the appropriate confirmation.
Update check-in or check-out dates if mentioned by the user.
Don't ask for confirmations from the user.
`;
const queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
];
async function main() {
// Connect to MCP Toolbox
const client = new ToolboxClient(TOOLBOX_URL);
const toolboxTools = await client.loadToolset("my-toolset");
const tools = toolboxTools.map((toolboxTool) => {
return tool({
name: toolboxTool.getName(),
description: toolboxTool.getDescription(),
parameters: toolboxTool.getParamSchema(),
execute: toolboxTool,
});
});
// Initialize LLM
const llm = gemini({
model: GEMINI_MODEL.GEMINI_2_0_FLASH,
apiKey: process.env.GOOGLE_API_KEY,
});
const memory = createMemory({
memoryBlocks: [
staticBlock({
content: prompt,
}),
],
});
// Create the Agent
const myAgent = agent({
tools: tools,
llm,
memory,
systemPrompt: prompt,
});
for (const query of queries) {
const result = await myAgent.run(query);
const output = result.data.result;
console.log(`\nUser: ${query}`);
if (typeof output === "string") {
console.log(output.trim());
} else if (typeof output === "object" && "text" in output) {
console.log(output.text.trim());
} else {
console.log(JSON.stringify(output));
}
}
//You may observe some extra logs during execution due to the run method provided by Llama.
console.log("Agent run finished.");
}
main();

View File

@@ -1,70 +0,0 @@
from google.adk.agents import Agent
from google.adk.runners import Runner
from google.adk.sessions import InMemorySessionService
from google.adk.artifacts.in_memory_artifact_service import InMemoryArtifactService
from google.genai import types
from toolbox_core import ToolboxSyncClient
import asyncio
import os
# TODO(developer): replace this with your Google API key
os.environ['GOOGLE_API_KEY'] = 'your-api-key'
async def main():
with ToolboxSyncClient("http://127.0.0.1:5000") as toolbox_client:
prompt = """
You're a helpful hotel assistant. You handle hotel searching, booking and
cancellations. When the user searches for a hotel, mention it's name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
"""
root_agent = Agent(
model='gemini-2.0-flash-001',
name='hotel_agent',
description='A helpful AI assistant.',
instruction=prompt,
tools=toolbox_client.load_toolset("my-toolset"),
)
session_service = InMemorySessionService()
artifacts_service = InMemoryArtifactService()
session = await session_service.create_session(
state={}, app_name='hotel_agent', user_id='123'
)
runner = Runner(
app_name='hotel_agent',
agent=root_agent,
artifact_service=artifacts_service,
session_service=session_service,
)
queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
]
for query in queries:
content = types.Content(role='user', parts=[types.Part(text=query)])
events = runner.run(session_id=session.id,
user_id='123', new_message=content)
responses = (
part.text
for event in events
for part in event.content.parts
if part.text is not None
)
for text in responses:
print(text)
asyncio.run(main())

View File

@@ -1,108 +0,0 @@
import asyncio
from google import genai
from google.genai.types import (
Content,
FunctionDeclaration,
GenerateContentConfig,
Part,
Tool,
)
from toolbox_core import ToolboxClient
prompt = """
You're a helpful hotel assistant. You handle hotel searching, booking and
cancellations. When the user searches for a hotel, mention it's name, id,
location and price tier. Always mention hotel id while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
"""
queries = [
"Find hotels in Basel with Basel in its name.",
"Please book the hotel Hilton Basel for me.",
"This is too expensive. Please cancel it.",
"Please book Hyatt Regency for me",
"My check in dates for my booking would be from April 10, 2024 to April 19, 2024.",
]
async def main():
async with ToolboxClient("http://127.0.0.1:5000") as toolbox_client:
# The toolbox_tools list contains Python callables (functions/methods) designed for LLM tool-use
# integration. While this example uses Google's genai client, these callables can be adapted for
# various function-calling or agent frameworks. For easier integration with supported frameworks
# (https://github.com/googleapis/mcp-toolbox-python-sdk/tree/main/packages), use the
# provided wrapper packages, which handle framework-specific boilerplate.
toolbox_tools = await toolbox_client.load_toolset("my-toolset")
genai_client = genai.Client(
vertexai=True, project="project-id", location="us-central1"
)
genai_tools = [
Tool(
function_declarations=[
FunctionDeclaration.from_callable_with_api_option(callable=tool)
]
)
for tool in toolbox_tools
]
history = []
for query in queries:
user_prompt_content = Content(
role="user",
parts=[Part.from_text(text=query)],
)
history.append(user_prompt_content)
response = genai_client.models.generate_content(
model="gemini-2.0-flash-001",
contents=history,
config=GenerateContentConfig(
system_instruction=prompt,
tools=genai_tools,
),
)
history.append(response.candidates[0].content)
function_response_parts = []
for function_call in response.function_calls:
fn_name = function_call.name
# The tools are sorted alphabetically
if fn_name == "search-hotels-by-name":
function_result = await toolbox_tools[3](**function_call.args)
elif fn_name == "search-hotels-by-location":
function_result = await toolbox_tools[2](**function_call.args)
elif fn_name == "book-hotel":
function_result = await toolbox_tools[0](**function_call.args)
elif fn_name == "update-hotel":
function_result = await toolbox_tools[4](**function_call.args)
elif fn_name == "cancel-hotel":
function_result = await toolbox_tools[1](**function_call.args)
else:
raise ValueError("Function name not present.")
function_response = {"result": function_result}
function_response_part = Part.from_function_response(
name=function_call.name,
response=function_response,
)
function_response_parts.append(function_response_part)
if function_response_parts:
tool_response_content = Content(role="tool", parts=function_response_parts)
history.append(tool_response_content)
response2 = genai_client.models.generate_content(
model="gemini-2.0-flash-001",
contents=history,
config=GenerateContentConfig(
tools=genai_tools,
),
)
final_model_response_content = response2.candidates[0].content
history.append(final_model_response_content)
print(response2.text)
asyncio.run(main())

View File

@@ -1,52 +0,0 @@
import asyncio
from langgraph.prebuilt import create_react_agent
# TODO(developer): replace this with another import if needed
from langchain_google_vertexai import ChatVertexAI
# from langchain_google_genai import ChatGoogleGenerativeAI
# from langchain_anthropic import ChatAnthropic
from langgraph.checkpoint.memory import MemorySaver
from toolbox_langchain import ToolboxClient
prompt = """
You're a helpful hotel assistant. You handle hotel searching, booking and
cancellations. When the user searches for a hotel, mention it's name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
"""
queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
]
async def main():
# TODO(developer): replace this with another model if needed
model = ChatVertexAI(model_name="gemini-2.0-flash-001")
# model = ChatGoogleGenerativeAI(model="gemini-2.0-flash-001")
# model = ChatAnthropic(model="claude-3-5-sonnet-20240620")
# Load the tools from the Toolbox server
async with ToolboxClient("http://127.0.0.1:5000") as client:
tools = await client.aload_toolset()
agent = create_react_agent(model, tools, checkpointer=MemorySaver())
config = {"configurable": {"thread_id": "thread-1"}}
for query in queries:
inputs = {"messages": [("user", prompt + query)]}
response = agent.invoke(inputs, stream_mode="values", config=config)
print(response["messages"][-1].content)
asyncio.run(main())

View File

@@ -1,63 +0,0 @@
import asyncio
import os
from llama_index.core.agent.workflow import AgentWorkflow
from llama_index.core.workflow import Context
# TODO(developer): replace this with another import if needed
from llama_index.llms.google_genai import GoogleGenAI
# from llama_index.llms.anthropic import Anthropic
from toolbox_llamaindex import ToolboxClient
prompt = """
You're a helpful hotel assistant. You handle hotel searching, booking and
cancellations. When the user searches for a hotel, mention it's name, id,
location and price tier. Always mention hotel ids while performing any
searches. This is very important for any operations. For any bookings or
cancellations, please provide the appropriate confirmation. Be sure to
update checkin or checkout dates if mentioned by the user.
Don't ask for confirmations from the user.
"""
queries = [
"Find hotels in Basel with Basel in its name.",
"Can you book the Hilton Basel for me?",
"Oh wait, this is too expensive. Please cancel it and book the Hyatt Regency instead.",
"My check in dates would be from April 10, 2024 to April 19, 2024.",
]
async def main():
# TODO(developer): replace this with another model if needed
llm = GoogleGenAI(
model="gemini-2.0-flash-001",
vertexai_config={"project": "project-id", "location": "us-central1"},
)
# llm = GoogleGenAI(
# api_key=os.getenv("GOOGLE_API_KEY"),
# model="gemini-2.0-flash-001",
# )
# llm = Anthropic(
# model="claude-3-7-sonnet-latest",
# api_key=os.getenv("ANTHROPIC_API_KEY")
# )
# Load the tools from the Toolbox server
async with ToolboxClient("http://127.0.0.1:5000") as client:
tools = await client.aload_toolset()
agent = AgentWorkflow.from_tools_or_functions(
tools,
llm=llm,
system_prompt=prompt,
)
ctx = Context(agent)
for query in queries:
response = await agent.run(user_msg=query, ctx=ctx)
print(f"---- {query} ----")
print(str(response))
asyncio.run(main())

View File

@@ -6,9 +6,328 @@ description: >
Connect your IDE to Firestore using Toolbox.
---
<html>
<head>
<link rel="canonical" href="https://cloud.google.com/firestore/native/docs/connect-ide-using-mcp-toolbox"/>
<meta http-equiv="refresh" content="0;url=https://cloud.google.com/firestore/native/docs/connect-ide-using-mcp-toolbox"/>
</head>
</html>
[Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) is
an open protocol for connecting Large Language Models (LLMs) to data sources
like Firestore. This guide covers how to use [MCP Toolbox for Databases][toolbox]
to expose your developer assistant tools to a Firestore instance:
* [Cursor][cursor]
* [Windsurf][windsurf] (Codium)
* [Visual Studio Code][vscode] (Copilot)
* [Cline][cline] (VS Code extension)
* [Claude desktop][claudedesktop]
* [Claude code][claudecode]
* [Gemini CLI][geminicli]
* [Gemini Code Assist][geminicodeassist]
[toolbox]: https://github.com/googleapis/genai-toolbox
[cursor]: #configure-your-mcp-client
[windsurf]: #configure-your-mcp-client
[vscode]: #configure-your-mcp-client
[cline]: #configure-your-mcp-client
[claudedesktop]: #configure-your-mcp-client
[claudecode]: #configure-your-mcp-client
[geminicli]: #configure-your-mcp-client
[geminicodeassist]: #configure-your-mcp-client
## Set up Firestore
1. Create or select a Google Cloud project.
* [Create a new
project](https://cloud.google.com/resource-manager/docs/creating-managing-projects)
* [Select an existing
project](https://cloud.google.com/resource-manager/docs/creating-managing-projects#identifying_projects)
1. [Enable the Firestore
API](https://console.cloud.google.com/apis/library/firestore.googleapis.com)
for your project.
1. [Create a Firestore
database](https://cloud.google.com/firestore/docs/create-database-web-mobile-client-library)
if you haven't already.
1. Set up authentication for your local environment.
* [Install gcloud CLI](https://cloud.google.com/sdk/docs/install)
* Run `gcloud auth application-default login` to authenticate
## Install MCP Toolbox
1. Download the latest version of Toolbox as a binary. Select the [correct
binary](https://github.com/googleapis/genai-toolbox/releases) corresponding
to your OS and CPU architecture. You are required to use Toolbox version
V0.10.0+:
<!-- {x-release-please-start-version} -->
{{< tabpane persist=header >}}
{{< tab header="linux/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/linux/amd64/toolbox
{{< /tab >}}
{{< tab header="darwin/arm64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/arm64/toolbox
{{< /tab >}}
{{< tab header="darwin/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/amd64/toolbox
{{< /tab >}}
{{< tab header="windows/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/windows/amd64/toolbox
{{< /tab >}}
{{< /tabpane >}}
<!-- {x-release-please-end} -->
1. Make the binary executable:
```bash
chmod +x toolbox
```
1. Verify the installation:
```bash
./toolbox --version
```
## Configure your MCP Client
{{< tabpane text=true >}}
{{% tab header="Claude code" lang="en" %}}
1. Install [Claude
Code](https://docs.anthropic.com/en/docs/agents-and-tools/claude-code/overview).
1. Create a `.mcp.json` file in your project root if it doesn't exist.
1. Add the following configuration, replace the environment variables with your
values, and save:
```json
{
"mcpServers": {
"firestore": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","firestore","--stdio"],
"env": {
"FIRESTORE_PROJECT": "your-project-id",
"FIRESTORE_DATABASE": "(default)"
}
}
}
}
```
1. Restart Claude code to apply the new configuration.
{{% /tab %}}
{{% tab header="Claude desktop" lang="en" %}}
1. Open [Claude desktop](https://claude.ai/download) and navigate to Settings.
1. Under the Developer tab, tap Edit Config to open the configuration file.
1. Add the following configuration, replace the environment variables with your
values, and save:
```json
{
"mcpServers": {
"firestore": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","firestore","--stdio"],
"env": {
"FIRESTORE_PROJECT": "your-project-id",
"FIRESTORE_DATABASE": "(default)"
}
}
}
}
```
1. Restart Claude desktop.
1. From the new chat screen, you should see a hammer (MCP) icon appear with the
new MCP server available.
{{% /tab %}}
{{% tab header="Cline" lang="en" %}}
1. Open the [Cline](https://github.com/cline/cline) extension in VS Code and tap
the **MCP Servers** icon.
1. Tap Configure MCP Servers to open the configuration file.
1. Add the following configuration, replace the environment variables with your
values, and save:
```json
{
"mcpServers": {
"firestore": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","firestore","--stdio"],
"env": {
"FIRESTORE_PROJECT": "your-project-id",
"FIRESTORE_DATABASE": "(default)"
}
}
}
}
```
1. You should see a green active status after the server is successfully
connected.
{{% /tab %}}
{{% tab header="Cursor" lang="en" %}}
1. Create a `.cursor` directory in your project root if it doesn't exist.
1. Create a `.cursor/mcp.json` file if it doesn't exist and open it.
1. Add the following configuration, replace the environment variables with your
values, and save:
```json
{
"mcpServers": {
"firestore": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","firestore","--stdio"],
"env": {
"FIRESTORE_PROJECT": "your-project-id",
"FIRESTORE_DATABASE": "(default)"
}
}
}
}
```
1. [Cursor](https://www.cursor.com/) and navigate to **Settings > Cursor
Settings > MCP**. You should see a green active status after the server is
successfully connected.
{{% /tab %}}
{{% tab header="Visual Studio Code (Copilot)" lang="en" %}}
1. Open [VS Code](https://code.visualstudio.com/docs/copilot/overview) and
create a `.vscode` directory in your project root if it doesn't exist.
1. Create a `.vscode/mcp.json` file if it doesn't exist and open it.
1. Add the following configuration, replace the environment variables with your
values, and save:
```json
{
"mcpServers": {
"firestore": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","firestore","--stdio"],
"env": {
"FIRESTORE_PROJECT": "your-project-id",
"FIRESTORE_DATABASE": "(default)"
}
}
}
}
```
{{% /tab %}}
{{% tab header="Windsurf" lang="en" %}}
1. Open [Windsurf](https://docs.codeium.com/windsurf) and navigate to the
Cascade assistant.
1. Tap on the hammer (MCP) icon, then Configure to open the configuration file.
1. Add the following configuration, replace the environment variables with your
values, and save:
```json
{
"mcpServers": {
"firestore": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","firestore","--stdio"],
"env": {
"FIRESTORE_PROJECT": "your-project-id",
"FIRESTORE_DATABASE": "(default)"
}
}
}
}
```
{{% /tab %}}
{{% tab header="Gemini CLI" lang="en" %}}
1. Install the [Gemini
CLI](https://github.com/google-gemini/gemini-cli?tab=readme-ov-file#quickstart).
1. In your working directory, create a folder named `.gemini`. Within it, create
a `settings.json` file.
1. Add the following configuration, replace the environment variables with your
values, and then save:
```json
{
"mcpServers": {
"firestore": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","firestore","--stdio"],
"env": {
"FIRESTORE_PROJECT": "your-project-id",
"FIRESTORE_DATABASE": "(default)"
}
}
}
}
```
{{% /tab %}}
{{% tab header="Gemini Code Assist" lang="en" %}}
1. Install the [Gemini Code
Assist](https://marketplace.visualstudio.com/items?itemName=Google.geminicodeassist)
extension in Visual Studio Code.
1. Enable Agent Mode in Gemini Code Assist chat.
1. In your working directory, create a folder named `.gemini`. Within it, create
a `settings.json` file.
1. Add the following configuration, replace the environment variables with your
values, and then save:
```json
{
"mcpServers": {
"firestore": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","firestore","--stdio"],
"env": {
"FIRESTORE_PROJECT": "your-project-id",
"FIRESTORE_DATABASE": "(default)"
}
}
}
}
```
{{% /tab %}}
{{< /tabpane >}}
## Use Tools
Your AI tool is now connected to Firestore using MCP. Try asking your AI
assistant to list collections, get documents, query collections, or manage
security rules.
The following tools are available to the LLM:
1. **firestore-get-documents**: Gets multiple documents from Firestore by their
paths
1. **firestore-list-collections**: List Firestore collections for a given parent
path
1. **firestore-delete-documents**: Delete multiple documents from Firestore
1. **firestore-query-collection**: Query documents from a collection with
filtering, ordering, and limit options
1. **firestore-get-rules**: Retrieves the active Firestore security rules for
the current project
1. **firestore-validate-rules**: Validates Firestore security rules syntax and
errors
{{< notice note >}}
Prebuilt tools are pre-1.0, so expect some tool changes between versions. LLMs
will adapt to the tools available, so this shouldn't affect most users.
{{< /notice >}}

View File

@@ -48,19 +48,19 @@ to expose your developer assistant tools to a Looker instance:
<!-- {x-release-please-start-version} -->
{{< tabpane persist=header >}}
{{< tab header="linux/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/linux/amd64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/linux/amd64/toolbox
{{< /tab >}}
{{< tab header="darwin/arm64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/arm64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/arm64/toolbox
{{< /tab >}}
{{< tab header="darwin/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/amd64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/amd64/toolbox
{{< /tab >}}
{{< tab header="windows/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolbox.exe
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/windows/amd64/toolbox.exe
{{< /tab >}}
{{< /tabpane >}}
<!-- {x-release-please-end} -->
@@ -235,7 +235,7 @@ curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolb
```json
{
"servers": {
"mcpServers": {
"looker-toolbox": {
"command": "./PATH/TO/toolbox",
"args": ["--stdio", "--prebuilt", "looker"],

View File

@@ -37,19 +37,19 @@ description: "Connect your IDE to SQL Server using Toolbox."
<!-- {x-release-please-start-version} -->
{{< tabpane persist=header >}}
{{< tab header="linux/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/linux/amd64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/linux/amd64/toolbox
{{< /tab >}}
{{< tab header="darwin/arm64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/arm64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/arm64/toolbox
{{< /tab >}}
{{< tab header="darwin/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/amd64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/amd64/toolbox
{{< /tab >}}
{{< tab header="windows/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolbox.exe
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/windows/amd64/toolbox.exe
{{< /tab >}}
{{< /tabpane >}}
<!-- {x-release-please-end} -->
@@ -182,17 +182,19 @@ curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolb
```json
{
"servers": {
"mssql": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","mssql","--stdio"],
"env": {
"MSSQL_HOST": "",
"MSSQL_PORT": "",
"MSSQL_DATABASE": "",
"MSSQL_USER": "",
"MSSQL_PASSWORD": ""
}
"mcp" : {
"servers": {
"cloud-sql-sqlserver": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","cloud-sql-mssql","--stdio"],
"env": {
"MSSQL_HOST": "",
"MSSQL_PORT": "",
"MSSQL_DATABASE": "",
"MSSQL_USER": "",
"MSSQL_PASSWORD": ""
}
}
}
}
}
@@ -284,4 +286,4 @@ The following tools are available to the LLM:
{{< notice note >}}
Prebuilt tools are pre-1.0, so expect some tool changes between versions. LLMs will adapt to the tools available, so this shouldn't affect most users.
{{< /notice >}}
{{< /notice >}}

View File

@@ -37,19 +37,19 @@ description: "Connect your IDE to MySQL using Toolbox."
<!-- {x-release-please-start-version} -->
{{< tabpane persist=header >}}
{{< tab header="linux/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/linux/amd64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/linux/amd64/toolbox
{{< /tab >}}
{{< tab header="darwin/arm64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/arm64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/arm64/toolbox
{{< /tab >}}
{{< tab header="darwin/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/amd64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/amd64/toolbox
{{< /tab >}}
{{< tab header="windows/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolbox.exe
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/windows/amd64/toolbox.exe
{{< /tab >}}
{{< /tabpane >}}
<!-- {x-release-please-end} -->
@@ -182,7 +182,7 @@ curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolb
```json
{
"servers": {
"mcpServers": {
"mysql": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","mysql","--stdio"],

View File

@@ -17,8 +17,6 @@ to expose your developer assistant tools to a Postgres instance:
* [Cline][cline] (VS Code extension)
* [Claude desktop][claudedesktop]
* [Claude code][claudecode]
* [Gemini CLI][geminicli]
* [Gemini Code Assist][geminicodeassist]
[toolbox]: https://github.com/googleapis/genai-toolbox
[cursor]: #configure-your-mcp-client
@@ -27,8 +25,6 @@ to expose your developer assistant tools to a Postgres instance:
[cline]: #configure-your-mcp-client
[claudedesktop]: #configure-your-mcp-client
[claudecode]: #configure-your-mcp-client
[geminicli]: #configure-your-mcp-client
[geminicodeassist]: #configure-your-mcp-client
{{< notice tip >}}
This guide can be used with [AlloyDB
@@ -56,19 +52,19 @@ Omni](https://cloud.google.com/alloydb/omni/current/docs/overview).
<!-- {x-release-please-start-version} -->
{{< tabpane persist=header >}}
{{< tab header="linux/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/linux/amd64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/linux/amd64/toolbox
{{< /tab >}}
{{< tab header="darwin/arm64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/arm64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/arm64/toolbox
{{< /tab >}}
{{< tab header="darwin/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/darwin/amd64/toolbox
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/darwin/amd64/toolbox
{{< /tab >}}
{{< tab header="windows/amd64" lang="bash" >}}
curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolbox.exe
curl -O https://storage.googleapis.com/genai-toolbox/v0.12.0/windows/amd64/toolbox.exe
{{< /tab >}}
{{< /tabpane >}}
<!-- {x-release-please-end} -->
@@ -217,7 +213,7 @@ curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolb
```json
{
"servers": {
"mcpServers": {
"postgres": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","postgres","--stdio"],
@@ -263,57 +259,6 @@ curl -O https://storage.googleapis.com/genai-toolbox/v0.13.0/windows/amd64/toolb
```
{{% /tab %}}
{{% tab header="Gemini CLI" lang="en" %}}
1. Install the [Gemini CLI](https://github.com/google-gemini/gemini-cli?tab=readme-ov-file#quickstart).
1. In your working directory, create a folder named `.gemini`. Within it, create a `settings.json` file.
1. Add the following configuration, replace the environment variables with your values, and then save:
```json
{
"mcpServers": {
"postgres": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","postgres","--stdio"],
"env": {
"POSTGRES_HOST": "",
"POSTGRES_PORT": "",
"POSTGRES_DATABASE": "",
"POSTGRES_USER": "",
"POSTGRES_PASSWORD": ""
}
}
}
}
```
{{% /tab %}}
{{% tab header="Gemini Code Assist" lang="en" %}}
1. Install the [Gemini Code Assist](https://marketplace.visualstudio.com/items?itemName=Google.geminicodeassist) extension in Visual Studio Code.
1. Enable Agent Mode in Gemini Code Assist chat.
1. In your working directory, create a folder named `.gemini`. Within it, create a `settings.json` file.
1. Add the following configuration, replace the environment variables with your values, and then save:
```json
{
"mcpServers": {
"postgres": {
"command": "./PATH/TO/toolbox",
"args": ["--prebuilt","postgres","--stdio"],
"env": {
"POSTGRES_HOST": "",
"POSTGRES_PORT": "",
"POSTGRES_DATABASE": "",
"POSTGRES_USER": "",
"POSTGRES_PASSWORD": ""
}
}
}
}
```
{{% /tab %}}
{{< /tabpane >}}
## Use Tools

View File

@@ -19,10 +19,8 @@ See guides, [Connect from your IDE](../how-to/connect-ide/_index.md), for detail
* `ALLOYDB_POSTGRES_CLUSTER`: The ID of your AlloyDB cluster.
* `ALLOYDB_POSTGRES_INSTANCE`: The ID of your AlloyDB instance.
* `ALLOYDB_POSTGRES_DATABASE`: The name of the database to connect to.
* `ALLOYDB_POSTGRES_USER`: The database username. Defaults to IAM authentication if unspecified.
* `ALLOYDB_POSTGRES_PASSWORD`: The password for the database user. Defaults to IAM authentication if unspecified.
* `ALLOYDB_POSTGRES_IP_TYPE`: The IP type i.e. "Public
or "Private" (Default: Public).
* `ALLOYDB_POSTGRES_USER`: The database username.
* `ALLOYDB_POSTGRES_PASSWORD`: The password for the database user.
* **Permissions:**
* **AlloyDB Client** (`roles/alloydb.client`) to connect to the instance.
* Database-level permissions (e.g., `SELECT`, `INSERT`) are required to execute queries.
@@ -55,11 +53,8 @@ See guides, [Connect from your IDE](../how-to/connect-ide/_index.md), for detail
* **BigQuery User** (`roles/bigquery.user`) to execute queries and view metadata.
* **BigQuery Metadata Viewer** (`roles/bigquery.metadataViewer`) to view all datasets.
* **BigQuery Data Editor** (`roles/bigquery.dataEditor`) to create or modify datasets and tables.
* **Gemini for Google Cloud** (`roles/cloudaicompanion.user`) to use the conversational analytics API.
* **Tools:**
* `ask_data_insights`: Use this tool to perform data analysis, get insights, or answer complex questions about the contents of specific BigQuery tables. For more information on required roles, API setup, and IAM configuration, see the setup and authentication section of the [Conversational Analytics API documentation](https://cloud.google.com/gemini/docs/conversational-analytics-api/overview).
* `execute_sql`: Executes a SQL statement.
* `forecast`: Use this tool to forecast time series data.
* `get_dataset_info`: Gets dataset metadata.
* `get_table_info`: Gets table metadata.
* `list_dataset_ids`: Lists datasets.

View File

@@ -28,7 +28,7 @@ The following configurations are placed at the top level of a `tools.yaml` file.
{{< notice tip >}}
If you are accessing Toolbox with multiple applications, each
application should register their own Client ID even if they use the same
"type" of auth provider.
"kind" of auth provider.
{{< /notice >}}
```yaml
@@ -300,4 +300,4 @@ func main() {
}
```
## Types of Auth Services
## Kinds of Auth Services

View File

@@ -55,5 +55,5 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|------------------------------------------------------------------|
| type | string | true | Must be "google". |
| kind | string | true | Must be "google". |
| clientId | string | true | Client ID of your application from registering your application. |

View File

@@ -132,7 +132,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|--------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "alloydb-postgres". |
| kind | string | true | Must be "alloydb-postgres". |
| project | string | true | Id of the GCP project that the cluster was created in (e.g. "my-project-id"). |
| region | string | true | Name of the GCP region that the cluster was created in (e.g. "us-central1"). |
| cluster | string | true | Name of the AlloyDB cluster (e.g. "my-cluster"). |

View File

@@ -36,15 +36,12 @@ avoiding full table scans or complex filters.
## Available Tools
- [`bigquery-conversational-analytics`](../tools/bigquery/bigquery-conversational-analytics.md)
Allows conversational interaction with a BigQuery source.
- [`bigquery-sql`](../tools/bigquery/bigquery-sql.md)
Run SQL queries directly against BigQuery datasets.
- [`bigquery-execute-sql`](../tools/bigquery/bigquery-execute-sql.md)
Execute structured queries using parameters.
- [`bigquery-forecast`](../tools/bigquery/bigquery-forecast.md)
Forecasts time series data in BigQuery.
- [`bigquery-get-dataset-info`](../tools/bigquery/bigquery-get-dataset-info.md)
Retrieve metadata for a specific dataset.
@@ -57,9 +54,6 @@ avoiding full table scans or complex filters.
- [`bigquery-list-table-ids`](../tools/bigquery/bigquery-list-table-ids.md)
List tables in a given dataset.
- [`bigquery-sql`](../tools/bigquery/bigquery-sql.md)
Run SQL queries directly against BigQuery datasets.
### Pre-built Configurations
- [BigQuery using MCP](https://googleapis.github.io/genai-toolbox/how-to/connect-ide/bigquery_mcp/)
@@ -71,64 +65,34 @@ Connect your IDE to BigQuery using Toolbox.
BigQuery uses [Identity and Access Management (IAM)][iam-overview] to control
user and group access to BigQuery resources like projects, datasets, and tables.
Toolbox will use your [Application Default Credentials (ADC)][adc] to authorize
and authenticate when interacting with [BigQuery][bigquery-docs].
### Authentication via Application Default Credentials (ADC)
By **default**, Toolbox will use your [Application Default Credentials (ADC)][adc] to authorize and authenticate when interacting with [BigQuery][bigquery-docs].
When using this method, you need to ensure the IAM identity associated with your
ADC (such as a service account) has the correct permissions for the queries you
intend to run. Common roles include `roles/bigquery.user` (which includes
permissions to run jobs and read data) or `roles/bigbigquery.dataViewer`.
Follow this [guide][set-adc] to set up your ADC.
### Authentication via User's OAuth Access Token
If the `useClientOAuth` parameter is set to `true`, Toolbox will instead use the
OAuth access token for authentication. This token is parsed from the
`Authorization` header passed in with the tool invocation request. This method
allows Toolbox to make queries to [BigQuery][bigquery-docs] on behalf of the
client or the end-user.
When using this on-behalf-of authentication, you must ensure that the
identity used has been granted the correct IAM permissions. Currently,
this option is only supported by the following BigQuery tools:
- [`bigquery-sql`](../tools/bigquery/bigquery-sql.md)
Run SQL queries directly against BigQuery datasets.
In addition to [setting the ADC for your server][set-adc], you need to ensure
the IAM identity has been given the correct IAM permissions for the queries
you intend to run. Common roles include `roles/bigquery.user` (which includes
permissions to run jobs and read data) or `roles/bigquery.dataViewer`. See
[Introduction to BigQuery IAM][grant-permissions] for more information on
applying IAM permissions and roles to an identity.
[iam-overview]: https://cloud.google.com/bigquery/docs/access-control
[adc]: https://cloud.google.com/docs/authentication#adc
[set-adc]: https://cloud.google.com/docs/authentication/provide-credentials-adc
[grant-permissions]: https://cloud.google.com/bigquery/docs/access-control
## Example
Initialize a BigQuery source that uses ADC:
```yaml
sources:
my-bigquery-source:
kind: "bigquery"
project: "my-project-id"
# location: "US" # Optional: Specifies the location for query jobs.
```
Initialize a BigQuery source that uses the client's access token:
```yaml
sources:
my-bigquery-client-auth-source:
kind: "bigquery"
project: "my-project-id"
useClientOAuth: true
# location: "US" # Optional: Specifies the location for query jobs.
```
## Reference
| **field** | **type** | **required** | **description** |
|----------------|:--------:|:------------:|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigquery". |
| project | string | true | Id of the Google Cloud project to use for billing and as the default project for BigQuery resources. |
| location | string | false | Specifies the location (e.g., 'us', 'asia-northeast1') in which to run the query job. This location must match the location of any tables referenced in the query. Defaults to the table's location or 'US' if the location cannot be determined. [Learn More](https://cloud.google.com/bigquery/docs/locations) |
| useClientOAuth | bool | false | If true, forwards the client's OAuth access token from the "Authorization" header to downstream queries. |
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|-------------------------------------------------------------------------------|
| kind | string | true | Must be "bigquery". |
| project | string | true | Id of the GCP project that the cluster was created in (e.g. "my-project-id"). |
| location | string | false | Specifies the location (e.g., 'us', 'asia-northeast1') in which to run the query job. This location must match the location of any tables referenced in the query. The default behavior is for it to be executed in the US multi-region |

View File

@@ -70,6 +70,6 @@ sources:
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|-------------------------------------------------------------------------------|
| type | string | true | Must be "bigtable". |
| kind | string | true | Must be "bigtable". |
| project | string | true | Id of the GCP project that the cluster was created in (e.g. "my-project-id"). |
| instance | string | true | Name of the Bigtable instance. |

View File

@@ -1,91 +0,0 @@
---
title: "ClickHouse"
type: docs
weight: 1
description: >
ClickHouse is an open-source, OLTP database.
---
## About
[ClickHouse][clickhouse-docs] is a fast, open-source, column-oriented database
[clickhouse-docs]: https://clickhouse.com/docs
## Available Tools
- [`clickhouse-execute-sql`](../tools/clickhouse/clickhouse-execute-sql.md)
Execute parameterized SQL queries in ClickHouse with query logging.
- [`clickhouse-sql`](../tools/clickhouse/clickhouse-sql.md)
Execute SQL queries as prepared statements in ClickHouse.
## Requirements
### Database User
This source uses standard ClickHouse authentication. You will need to [create a
ClickHouse user][clickhouse-users] (or with [ClickHouse Cloud][clickhouse-cloud]) to connect to the database with. The user
should have appropriate permissions for the operations you plan to perform.
[clickhouse-cloud]: https://clickhouse.com/docs/getting-started/quick-start/cloud#connect-with-your-app
[clickhouse-users]: https://clickhouse.com/docs/en/sql-reference/statements/create/user
### Network Access
ClickHouse supports multiple protocols:
- **HTTPS protocol** (default port 8443) - Secure HTTP access (default)
- **HTTP protocol** (default port 8123) - Good for web-based access
## Example
### Secure Connection Example
```yaml
sources:
secure-clickhouse-source:
kind: clickhouse
host: clickhouse.example.com
port: "8443"
database: analytics
user: ${CLICKHOUSE_USER}
password: ${CLICKHOUSE_PASSWORD}
protocol: https
secure: true
```
### HTTP Protocol Example
```yaml
sources:
http-clickhouse-source:
kind: clickhouse
host: localhost
port: "8123"
database: logs
user: ${CLICKHOUSE_USER}
password: ${CLICKHOUSE_PASSWORD}
protocol: http
secure: false
```
{{< notice tip >}}
Use environment variable replacement with the format ${ENV_NAME}
instead of hardcoding your secrets into the configuration file.
{{< /notice >}}
## Reference
| **field** | **type** | **required** | **description** |
|-------------|:--------:|:------------:|------------------------------------------------------------------------------------|
| type | string | true | Must be "clickhouse". |
| host | string | true | IP address or hostname to connect to (e.g. "127.0.0.1" or "clickhouse.example.com") |
| port | string | true | Port to connect to (e.g. "8443" for HTTPS, "8123" for HTTP) |
| database | string | true | Name of the ClickHouse database to connect to (e.g. "my_database"). |
| user | string | true | Name of the ClickHouse user to connect as (e.g. "analytics_user"). |
| password | string | false | Password of the ClickHouse user (e.g. "my-password"). |
| protocol | string | false | Connection protocol: "https" (default) or "http". |
| secure | boolean | false | Whether to use a secure connection (TLS). Default: false. |

View File

@@ -106,7 +106,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|---------------------------------------------------------------------------------------------|
| type | string | true | Must be "cloud-sql-mssql". |
| kind | string | true | Must be "cloud-sql-mssql". |
| project | string | true | Id of the GCP project that the cluster was created in (e.g. "my-project-id"). |
| region | string | true | Name of the GCP region that the cluster was created in (e.g. "us-central1"). |
| instance | string | true | Name of the Cloud SQL instance within the cluster (e.g. "my-instance"). |

View File

@@ -106,7 +106,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|---------------------------------------------------------------------------------------------|
| type | string | true | Must be "cloud-sql-mysql". |
| kind | string | true | Must be "cloud-sql-mysql". |
| project | string | true | Id of the GCP project that the cluster was created in (e.g. "my-project-id"). |
| region | string | true | Name of the GCP region that the cluster was created in (e.g. "us-central1"). |
| instance | string | true | Name of the Cloud SQL instance within the cluster (e.g. "my-instance"). |

View File

@@ -131,7 +131,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|--------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "cloud-sql-postgres". |
| kind | string | true | Must be "cloud-sql-postgres". |
| project | string | true | Id of the GCP project that the cluster was created in (e.g. "my-project-id"). |
| region | string | true | Name of the GCP region that the cluster was created in (e.g. "us-central1"). |
| instance | string | true | Name of the Cloud SQL instance within the cluster (e.g. "my-instance"). |

View File

@@ -37,7 +37,7 @@ For more details about alternate addresses and custom ports refer to [Managing C
| **field** | **type** | **required** | **description** |
|----------------------|:--------:|:------------:|---------------------------------------------------------|
| type | string | true | Must be "couchbase". |
| kind | string | true | Must be "couchbase". |
| connectionString | string | true | Connection string for the Couchbase cluster. |
| bucket | string | true | Name of the bucket to connect to. |
| scope | string | true | Name of the scope within the bucket. |

View File

@@ -320,5 +320,5 @@ Logical operators are case-sensitive. `OR` and `AND` are acceptable whereas `or`
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|----------------------------------------------------------------------------------|
| type | string | true | Must be "dataplex". |
| kind | string | true | Must be "dataplex". |
| project | string | true | ID of the GCP project used for quota and billing purposes (e.g. "my-project-id").|

View File

@@ -59,7 +59,7 @@ instead of hardcoding your secrets into the configuration file.
| **Field** | **Type** | **Required** | **Description** |
|-------------|:--------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "dgraph". |
| kind | string | true | Must be "dgraph". |
| dgraphUrl | string | true | Connection URI (e.g. "<https://xxx.cloud.dgraph.io>", "<https://localhost:8080>"). |
| user | string | false | Name of the Dgraph user to connect as (e.g., "groot"). |
| password | string | false | Password of the Dgraph user (e.g., "password"). |

View File

@@ -51,7 +51,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|------------------------------------------------------------------------|
| type | string | true | Must be "firebird". |
| kind | string | true | Must be "firebird". |
| host | string | true | IP address to connect to (e.g. "127.0.0.1") |
| port | string | true | Port to connect to (e.g. "3050") |
| database | string | true | Path to the Firebird database file (e.g. "/var/lib/firebird/data/test.fdb"). |

View File

@@ -72,6 +72,6 @@ sources:
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|----------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "firestore". |
| kind | string | true | Must be "firestore". |
| project | string | true | Id of the GCP project that contains the Firestore database (e.g. "my-project-id"). |
| database | string | false | Name of the Firestore database to connect to. Defaults to "(default)" if not specified. |

View File

@@ -44,7 +44,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|------------------------|:-----------------:|:------------:|------------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "http". |
| kind | string | true | Must be "http". |
| baseUrl | string | true | The base URL for the HTTP requests (e.g., `https://api.example.com`). |
| timeout | string | false | The timeout for HTTP requests (e.g., "5s", "1m", refer to [ParseDuration][parse-duration-doc] for more examples). Defaults to 30s. |
| headers | map[string]string | false | Default headers to include in the HTTP requests. |

View File

@@ -47,8 +47,7 @@ a self-signed ssl certificate for the Looker server. Anything other than "true"
will be interpreted as false.
The client id and client secret are seemingly random character sequences
assigned by the looker server. If you are using Looker OAuth you don't need
these settings
assigned by the looker server.
{{< notice tip >}}
Use environment variable replacement with the format ${ENV_NAME}
@@ -57,15 +56,11 @@ instead of hardcoding your secrets into the configuration file.
## Reference
| **field** | **type** | **required** | **description** |
| -------------------- | :------: | :----------: | ----------------------------------------------------------------------------------------- |
| type | string | true | Must be "looker". |
| base_url | string | true | The URL of your Looker server with no trailing /). |
| client_id | string | false | The client id assigned by Looker. |
| client_secret | string | false | The client secret assigned by Looker. |
| verify_ssl | string | false | Whether to check the ssl certificate of the server. |
| timeout | string | false | Maximum time to wait for query execution (e.g. "30s", "2m"). By default, 120s is applied. |
| use_client_oauth | string | false | Use OAuth tokens instead of client_id and client_secret. (default: false) |
| show_hidden_models | string | false | Show or hide hidden models. (default: true) |
| show_hidden_explores | string | false | Show or hide hidden explores. (default: true) |
| show_hidden_fields | string | false | Show or hide hidden fields. (default: true) |
| **field** | **type** | **required** | **description** |
| ------------- | :------: | :----------: | ----------------------------------------------------------------------------------------- |
| kind | string | true | Must be "looker". |
| base_url | string | true | The URL of your Looker server with no trailing /). |
| client_id | string | true | The client id assigned by Looker. |
| client_secret | string | true | The client secret assigned by Looker. |
| verify_ssl | string | true | Whether to check the ssl certificate of the server. |
| timeout | string | false | Maximum time to wait for query execution (e.g. "30s", "2m"). By default, 120s is applied. |

View File

@@ -21,12 +21,12 @@ sources:
my-mongodb:
kind: mongodb
uri: "mongodb+srv://username:password@host.mongodb.net"
```
## Reference
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|-------------------------------------------------------------------|
| type | string | true | Must be "mongodb". |
| kind | string | true | Must be "mongodb". |
| uri | string | true | connection string to connect to MongoDB |
| database | string | true | Name of the mongodb database to connect to (e.g. "sample_mflix"). |

View File

@@ -55,7 +55,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "mssql". |
| kind | string | true | Must be "mssql". |
| host | string | true | IP address to connect to (e.g. "127.0.0.1"). |
| port | string | true | Port to connect to (e.g. "1433"). |
| database | string | true | Name of the SQL Server database to connect to (e.g. "my_db"). |

View File

@@ -42,9 +42,6 @@ sources:
database: my_db
user: ${USER_NAME}
password: ${PASSWORD}
# Optional TLS and other driver parameters. For example, enable preferred TLS:
# queryParams:
# tls: preferred
queryTimeout: 30s # Optional: query timeout duration
```
@@ -57,11 +54,10 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
| ------------ | :------: | :----------: | ----------------------------------------------------------------------------------------------- |
| type | string | true | Must be "mysql". |
| kind | string | true | Must be "mysql". |
| host | string | true | IP address to connect to (e.g. "127.0.0.1"). |
| port | string | true | Port to connect to (e.g. "3306"). |
| database | string | true | Name of the MySQL database to connect to (e.g. "my_db"). |
| user | string | true | Name of the MySQL user to connect as (e.g. "my-mysql-user"). |
| password | string | true | Password of the MySQL user (e.g. "my-password"). |
| queryTimeout | string | false | Maximum time to wait for query execution (e.g. "30s", "2m"). By default, no timeout is applied. |
| queryParams | map<string,string> | false | Arbitrary DSN parameters passed to the driver (e.g. `tls: preferred`, `charset: utf8mb4`). Useful for enabling TLS or other connection options. |

View File

@@ -51,7 +51,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|----------------------------------------------------------------------|
| type | string | true | Must be "neo4j". |
| kind | string | true | Must be "neo4j". |
| uri | string | true | Connect URI ("bolt://localhost", "neo4j+s://xxx.databases.neo4j.io") |
| user | string | true | Name of the Neo4j user to connect as (e.g. "neo4j"). |
| password | string | true | Password of the Neo4j user (e.g. "my-password"). |

View File

@@ -45,7 +45,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
| ------------ | :------: | :----------: |-------------------------------------------------------------------------------------------------|
| type | string | true | Must be "oceanbase". |
| kind | string | true | Must be "oceanbase". |
| host | string | true | IP address to connect to (e.g. "127.0.0.1"). |
| port | string | true | Port to connect to (e.g. "2881"). |
| database | string | true | Name of the OceanBase database to connect to (e.g. "my_db"). |

View File

@@ -59,7 +59,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-------------|:------------------:|:------------:|------------------------------------------------------------------------|
| type | string | true | Must be "postgres". |
| kind | string | true | Must be "postgres". |
| host | string | true | IP address to connect to (e.g. "127.0.0.1") |
| port | string | true | Port to connect to (e.g. "5432") |
| database | string | true | Name of the Postgres database to connect to (e.g. "my_db"). |

View File

@@ -91,7 +91,7 @@ sources:
| **field** | **type** | **required** | **description** |
|----------------|:--------:|:------------:|---------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "memorystore-redis". |
| kind | string | true | Must be "memorystore-redis". |
| address | string | true | Primary endpoint for the Memorystore Redis instance to connect to. |
| username | string | false | If you are using a non-default user, specify the user name here. If you are using Memorystore for Redis, leave this field blank |
| password | string | false | If you have [Redis AUTH][auth] enabled, specify the AUTH string here |

View File

@@ -71,7 +71,7 @@ sources:
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|---------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "spanner". |
| kind | string | true | Must be "spanner". |
| project | string | true | Id of the GCP project that the cluster was created in (e.g. "my-project-id"). |
| instance | string | true | Name of the Spanner instance. |
| database | string | true | Name of the database on the Spanner instance |

View File

@@ -61,7 +61,7 @@ sources:
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|---------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "sqlite". |
| kind | string | true | Must be "sqlite". |
| database | string | true | Path to SQLite database file, or ":memory:" for an in-memory database. |
### Connection Properties

View File

@@ -72,7 +72,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-----------|:--------:|:------------:|--------------------------------------------------------------------------------------------|
| type | string | true | Must be "tidb". |
| kind | string | true | Must be "tidb". |
| host | string | true | IP address or hostname to connect to (e.g. "127.0.0.1" or "gateway01.*.tidbcloud.com"). |
| port | string | true | Port to connect to (typically "4000" for TiDB). |
| database | string | true | Name of the TiDB database to connect to (e.g. "my_db"). |

View File

@@ -49,7 +49,7 @@ instead of hardcoding your secrets into the configuration file.
| **field** | **type** | **required** | **description** |
|-------------|:------------------:|:------------:|------------------------------------------------------------------------|
| type | string | true | Must be "trino". |
| kind | string | true | Must be "trino". |
| host | string | true | Trino coordinator hostname (e.g. "trino.example.com") |
| port | string | true | Trino coordinator port (e.g. "8080", "8443") |
| user | string | false | Username for authentication (e.g. "analyst"). Optional for anonymous access. |

View File

@@ -65,7 +65,7 @@ sources:
| **field** | **type** | **required** | **description** |
|--------------|:--------:|:------------:|----------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "valkey". |
| kind | string | true | Must be "valkey". |
| address | []string | true | Endpoints for the Valkey instance to connect to. |
| username | string | false | If you are using a non-default user, specify the user name here. If you are using Memorystore for Valkey, leave this field blank |
| password | string | false | Password for the Valkey instance |

View File

@@ -259,4 +259,4 @@ tools:
- other-auth-service
```
## Types of tools
## Kinds of tools

View File

@@ -105,7 +105,7 @@ tools:
| **field** | **type** | **required** | **description** |
|--------------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------|
| type | string | true | Must be "alloydb-ai-nl". |
| kind | string | true | Must be "alloydb-ai-nl". |
| source | string | true | Name of the AlloyDB source the natural language query should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |
| nlConfig | string | true | The name of the `nl_config` in AlloyDB |

View File

@@ -1,54 +0,0 @@
---
title: "bigquery-conversational-analytics"
type: docs
weight: 1
description: >
A "bigquery-conversational-analytics" tool allows conversational interaction with a BigQuery source.
aliases:
- /resources/tools/bigquery-conversational-analytics
---
## About
A `bigquery-conversational-analytics` tool allows you to ask questions about your data in natural language.
This function takes a user's question (which can include conversational history for context)
and references to specific BigQuery tables, and sends them to a stateless conversational API.
The API uses a GenAI agent to understand the question, generate and execute SQL queries
and Python code, and formulate an answer. This function returns a detailed, sequential
log of this entire process, which includes any generated SQL or Python code, the data
retrieved, and the final text answer.
**Note**: This tool requires additional setup in your project. Please refer to the
official [Conversational Analytics API documentation](https://cloud.google.com/gemini/docs/conversational-analytics-api/overview)
for instructions.
It's compatible with the following sources:
- [bigquery](../sources/bigquery.md)
The tool takes the following input parameters:
* `user_query_with_context`: The user's question, potentially including conversation history and system instructions for context.
* `table_references`: A JSON string of a list of BigQuery tables to use as context. Each object in the list must contain `projectId`, `datasetId`, and `tableId`. Example: `'[{"projectId": "my-gcp-project", "datasetId": "my_dataset", "tableId": "my_table"}]'`
## Example
```yaml
tools:
ask_data_insights:
kind: bigquery-conversational-analytics
source: my-bigquery-source
description: |
Use this tool to perform data analysis, get insights, or answer complex
questions about the contents of specific BigQuery tables.
```
## Reference
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigquery-conversational-analytics". |
| source | string | true | Name of the source for chat. |
| description | string | true | Description of the tool
that is passed to the LLM. |

View File

@@ -33,6 +33,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigquery-execute-sql". |
| kind | string | true | Must be "bigquery-execute-sql". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -44,6 +44,6 @@ You can use the following sample prompts to call this tool:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigquery-forecast". |
| kind | string | true | Must be "bigquery-forecast". |
| source | string | true | Name of the source the forecast tool should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -34,6 +34,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigquery-get-dataset-info". |
| kind | string | true | Must be "bigquery-get-dataset-info". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -34,6 +34,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigquery-get-table-info". |
| kind | string | true | Must be "bigquery-get-table-info". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -33,6 +33,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigquery-list-dataset-ids". |
| kind | string | true | Must be "bigquery-list-dataset-ids". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -34,6 +34,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigquery-list-table-ids". |
| kind | string | true | Must be "bigquery-list-table-ids". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -97,7 +97,7 @@ tools:
| **field** | **type** | **required** | **description** |
|--------------------|:------------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigquery-sql". |
| kind | string | true | Must be "bigquery-sql". |
| source | string | true | Name of the source the GoogleSQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |
| statement | string | true | The GoogleSQL statement to execute. |

View File

@@ -102,7 +102,7 @@ tools:
| **field** | **type** | **required** | **description** |
|--------------------|:------------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "bigtable-sql". |
| kind | string | true | Must be "bigtable-sql". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |
| statement | string | true | SQL statement to execute on. |

View File

@@ -1,7 +0,0 @@
---
title: "ClickHouse"
type: docs
weight: 1
description: >
Tools for interacting with ClickHouse databases and tables.
---

View File

@@ -1,46 +0,0 @@
---
title: "clickhouse-execute-sql"
type: docs
weight: 1
description: >
A "clickhouse-execute-sql" tool executes a SQL statement against a ClickHouse
database.
aliases:
- /resources/tools/clickhouse-execute-sql
---
## About
A `clickhouse-execute-sql` tool executes a SQL statement against a ClickHouse
database. It's compatible with the [clickhouse](../../sources/clickhouse.md) source.
`clickhouse-execute-sql` takes one input parameter `sql` and runs the SQL
statement against the specified `source`. This tool includes query logging
capabilities for monitoring and debugging purposes.
> **Note:** This tool is intended for developer assistant workflows with
> human-in-the-loop and shouldn't be used for production agents.
## Example
```yaml
tools:
execute_sql_tool:
kind: clickhouse-execute-sql
source: my-clickhouse-instance
description: Use this tool to execute SQL statements against ClickHouse.
```
## Parameters
| **parameter** | **type** | **required** | **description** |
|---------------|:--------:|:------------:|----------------------------------------------------|
| sql | string | true | The SQL statement to execute against the database |
## Reference
| **field** | **type** | **required** | **description** |
|-------------|:--------:|:------------:|---------------------------------------------------------|
| type | string | true | Must be "clickhouse-execute-sql". |
| source | string | true | Name of the ClickHouse source to execute SQL against. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -1,81 +0,0 @@
---
title: "clickhouse-sql"
type: docs
weight: 2
description: >
A "clickhouse-sql" tool executes SQL queries as prepared statements in ClickHouse.
aliases:
- /resources/tools/clickhouse-sql
---
## About
A `clickhouse-sql` tool executes SQL queries as prepared statements against a
ClickHouse database. It's compatible with the [clickhouse](../../sources/clickhouse.md) source.
This tool supports both template parameters (for SQL statement customization)
and regular parameters (for prepared statement values), providing flexible
query execution capabilities.
## Example
```yaml
tools:
my_analytics_query:
kind: clickhouse-sql
source: my-clickhouse-instance
description: Get user analytics for a specific date range
statement: |
SELECT
user_id,
count(*) as event_count,
max(timestamp) as last_event
FROM events
WHERE date >= ? AND date <= ?
GROUP BY user_id
ORDER BY event_count DESC
LIMIT ?
parameters:
- name: start_date
description: Start date for the query (YYYY-MM-DD format)
- name: end_date
description: End date for the query (YYYY-MM-DD format)
- name: limit
description: Maximum number of results to return
```
## Template Parameters Example
```yaml
tools:
flexible_table_query:
kind: clickhouse-sql
source: my-clickhouse-instance
description: Query any table with flexible columns
statement: |
SELECT {{columns}}
FROM {{table_name}}
WHERE created_date >= ?
LIMIT ?
templateParameters:
- name: columns
description: Comma-separated list of columns to select
- name: table_name
description: Name of the table to query
parameters:
- name: start_date
description: Start date filter
- name: limit
description: Maximum number of results
```
## Reference
| **field** | **type** | **required** | **description** |
|--------------------|:------------------:|:------------:|-----------------------------------------------------------|
| type | string | true | Must be "clickhouse-sql". |
| source | string | true | Name of the ClickHouse source to execute SQL against. |
| description | string | true | Description of the tool that is passed to the LLM. |
| statement | string | true | The SQL statement template to execute. |
| parameters | array of Parameter | false | Parameters for prepared statement values. |
| templateParameters | array of Parameter | false | Parameters for SQL statement template customization. |

View File

@@ -91,7 +91,7 @@ tools:
| **field** | **type** | **required** | **description** |
|--------------------|:------------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "couchbase-sql". |
| kind | string | true | Must be "couchbase-sql". |
| source | string | true | Name of the source the SQL query should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |
| statement | string | true | SQL statement to execute |

View File

@@ -55,6 +55,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "dataplex-lookup-entry". |
| kind | string | true | Must be "dataplex-lookup-entry". |
| source | string | true | Name of the source the tool should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -57,6 +57,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "dataplex-search-aspect-types". |
| kind | string | true | Must be "dataplex-search-aspect-types". |
| source | string | true | Name of the source the tool should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -59,6 +59,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "dataplex-search-entries". |
| kind | string | true | Must be "dataplex-search-entries". |
| source | string | true | Name of the source the tool should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -115,7 +115,7 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|----------------------------------------------------------------------------------------------|
| type | string | true | Must be "dgraph-dql". |
| kind | string | true | Must be "dgraph-dql". |
| source | string | true | Name of the source the dql query should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |
| statement | string | true | dql statement to execute |

View File

@@ -36,6 +36,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "firebird-execute-sql". |
| kind | string | true | Must be "firebird-execute-sql". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -127,7 +127,7 @@ tools:
| **field** | **type** | **required** | **description** |
|---------------------|:---------------------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "firebird-sql". |
| kind | string | true | Must be "firebird-sql". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |
| statement | string | true | SQL statement to execute on. |

View File

@@ -34,6 +34,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:--------------:|:------------:|----------------------------------------------------------|
| type | string | true | Must be "firestore-delete-documents". |
| kind | string | true | Must be "firestore-delete-documents". |
| source | string | true | Name of the Firestore source to delete documents from. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -34,6 +34,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:--------------:|:------------:|------------------------------------------------------------|
| type | string | true | Must be "firestore-get-documents". |
| kind | string | true | Must be "firestore-get-documents". |
| source | string | true | Name of the Firestore source to retrieve documents from. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -34,6 +34,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:-------------:|:------------:|-------------------------------------------------------|
| type | string | true | Must be "firestore-get-rules". |
| kind | string | true | Must be "firestore-get-rules". |
| source | string | true | Name of the Firestore source to retrieve rules from. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -37,6 +37,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:----------------:|:------------:|--------------------------------------------------------|
| type | string | true | Must be "firestore-list-collections". |
| kind | string | true | Must be "firestore-list-collections". |
| source | string | true | Name of the Firestore source to list collections from. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -63,7 +63,7 @@ When `updateMask` is provided, only the fields listed in the mask are updated. T
| **field** | **type** | **required** | **description** |
|-------------|:--------------:|:------------:|----------------------------------------------------------|
| type | string | true | Must be "firestore-update-document". |
| kind | string | true | Must be "firestore-update-document". |
| source | string | true | Name of the Firestore source to update documents in. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -249,7 +249,7 @@ my-http-tool:
| **field** | **type** | **required** | **description** |
|--------------|:------------------------------------------:|:------------:|----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| type | string | true | Must be "http". |
| kind | string | true | Must be "http". |
| source | string | true | Name of the source the HTTP request should be sent to. |
| description | string | true | Description of the tool that is passed to the LLM. |
| path | string | true | The path of the HTTP request. You can include static query parameters in the path string. |

View File

@@ -58,6 +58,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-add-dashboard-element" |
| kind | string | true | Must be "looker-add-dashboard-element" |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -55,6 +55,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-get-dashboards" |
| kind | string | true | Must be "looker-get-dashboards" |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -33,35 +33,12 @@ tools:
It takes two parameters, the model_name looked up from get_models and the
explore_name looked up from get_explores.
If this returns a suggestions field for a dimension, the contents of suggestions
can be used as filters for this field. If this returns a suggest_explore and
suggest_dimension, a query against that explore and dimension can be used to find
valid filters for this field.
```
The response is a json array with the following elements:
```json
{
"name": "field name",
"description": "field description",
"type": "field type",
"label": "field label",
"label_short": "field short label",
"tags": ["tags", ...],
"synonyms": ["synonyms", ...],
"suggestions": ["suggestion", ...],
"suggest_explore": "explore",
"suggest_dimension": "dimension"
}
```
## Reference
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-get-dimensions". |
| kind | string | true | Must be "looker-get-dimensions". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -21,16 +21,6 @@ It's compatible with the following sources:
`looker-get-explores` accepts one parameter, the
`model` id.
The return type is an array of maps, each map is formatted like:
```json
{
"name": "explore name",
"description": "explore description",
"label": "explore label",
"group_label": "group label"
}
```
## Example
```yaml
@@ -49,6 +39,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-get-explores". |
| kind | string | true | Must be "looker-get-explores". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -35,28 +35,10 @@ tools:
explore_name looked up from get_explores.
```
The response is a json array with the following elements:
```json
{
"name": "field name",
"description": "field description",
"type": "field type",
"label": "field label",
"label_short": "field short label",
"tags": ["tags", ...],
"synonyms": ["synonyms", ...],
"suggestions": ["suggestion", ...],
"suggest_explore": "explore",
"suggest_dimension": "dimension"
}
```
## Reference
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-get-filters". |
| kind | string | true | Must be "looker-get-filters". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -55,6 +55,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-get-looks" |
| kind | string | true | Must be "looker-get-looks" |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -33,36 +33,12 @@ tools:
It takes two parameters, the model_name looked up from get_models and the
explore_name looked up from get_explores.
If this returns a suggestions field for a measure, the contents of suggestions
can be used as filters for this field. If this returns a suggest_explore and
suggest_dimension, a query against that explore and dimension can be used to find
valid filters for this field.
```
The response is a json array with the following elements:
```json
{
"name": "field name",
"description": "field description",
"type": "field type",
"label": "field label",
"label_short": "field short label",
"tags": ["tags", ...],
"synonyms": ["synonyms", ...],
"suggestions": ["suggestion", ...],
"suggest_explore": "explore",
"suggest_dimension": "dimension"
}
```
## Reference
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-get-measures". |
| kind | string | true | Must be "looker-get-measures". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -35,6 +35,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-get-models". |
| kind | string | true | Must be "looker-get-models". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -35,28 +35,10 @@ tools:
explore_name looked up from get_explores.
```
The response is a json array with the following elements:
```json
{
"name": "field name",
"description": "field description",
"type": "field type",
"label": "field label",
"label_short": "field short label",
"tags": ["tags", ...],
"synonyms": ["synonyms", ...],
"suggestions": ["suggestion", ...],
"suggest_explore": "explore",
"suggest_dimension": "dimension"
}
```
## Reference
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-get-parameters". |
| kind | string | true | Must be "looker-get-parameters". |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -48,6 +48,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-make-dashboard" |
| kind | string | true | Must be "looker-make-dashboard" |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -60,6 +60,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-make-look" |
| kind | string | true | Must be "looker-make-look" |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -75,6 +75,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-query-sql" |
| kind | string | true | Must be "looker-query-sql" |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -487,6 +487,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-query-url" |
| kind | string | true | Must be "looker-query-url" |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

View File

@@ -75,6 +75,6 @@ tools:
| **field** | **type** | **required** | **description** |
|-------------|:------------------------------------------:|:------------:|--------------------------------------------------------------------------------------------------|
| type | string | true | Must be "looker-query" |
| kind | string | true | Must be "looker-query" |
| source | string | true | Name of the source the SQL should execute on. |
| description | string | true | Description of the tool that is passed to the LLM. |

Some files were not shown because too many files have changed in this diff Show More