`
tools:
wait_for_tool:
kind: wait-for
description: "Tool puts chat to sleep for given timeout example 3m,10s,
5m etc. For tasks such as cluster creation no need to wait. It takes
longer time such as 8m for instance creation. Use timeout value as
default if nothing is provided"
timeout: 10s
`
Output:
`
prernakakkar@prernakakkar:~/senseai/genai-toolbox$ curl -X POST -H
"Content-Type: application/json" -d '{"duration": "5m"}'
http://127.0.0.1:5000/api/tool/wa
it_for_tool/invoke
{"result":"[\"Wait for 5m0s completed successfully.\"]"}
`
Added an option for user to indicate if the parameter is required.
Example:
```
parameters:
- name: foo
type: string
description: foo
required: false
```
If the `required` field is not provided, it will be defaulted to `true`.
If a `default` value is provided, `required = false` regardless if the
field is indicated.
```
parameters:
- name: foo
type: string
description: foo
default: hello world
```
Fixes#736
- Spanner: convert array to typed before querying, as Spanner does not
accept non-typed array []any
- BigQuery: fix https://github.com/googleapis/genai-toolbox/issues/793
- Bigtable: add the required `ElemType` for array-type params
- Redis/Valkey: change indexing to append to avoid extra spaces
Add integration tests for array parameters, skipped for the sources not
supporting arrays:
- SQLite
- Cloud SQL MSSQL
- Cloud SQL MySQL
- MSSQL
- MySQL
Optional projectID parameter enables dynamic, cross-project resource
access in BigQuery tools.
This allows a single tool configuration to target different projects at
runtime, rather than being fixed to the project in its source
configuration.
---------
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>
When go-yaml decode into CommonParameter with Default being an any type,
int will be converted into []uint64.
It will fail the Parse() when the value is being used since it does not
belong to either of the int types.
Unmarshal `default` value into each field's type directly.
Fixes#771
Copy fix from #757.
The Invoke function had two bugs:
A panic would occur when scanning a row containing a NULL value in a
TEXT or VARCHAR column. The code did not check for nil before attempting
a type assertion on the scanned value.
The *sql.Rows result was not being closed on all code paths, leading to
connection leaks that could exhaust the database connection pool.
This change corrects both issues. A guard clause now checks for nil
values before processing, and rows.Close() is deferred to guarantee the
connection is released.
The Invoke function had two bugs:
1. A panic would occur when scanning a row containing a NULL value in a
TEXT or VARCHAR column. The code did not check for nil before attempting
a type assertion on the scanned value.
2. The *sql.Rows result was not being closed on all code paths, leading
to connection leaks that could exhaust the database connection pool.
This change corrects both issues. A guard clause now checks for nil
values before processing, and rows.Close() is deferred to guarantee the
connection is released.
Co-authored-by: Yuan <45984206+Yuan325@users.noreply.github.com>
Add a `default` field to parameters, that enables users to specify a
default value.
e.g.
```
parameters:
- name: name
type: string
default: "some-default-value"
description: The name of the hotel.
```
if this parameter is invoked without specifying `name`, the parameter
would default to "some-default-value"
For parameter manifest, there will be an additional `Required` field.
The default `Required` field is true. If a `default` value is presented,
`Required: false`. Array parameter's item's `Required` field will
inherit the array's `Required` field.
Fixes#475
Add templateParameters to support non-filter parameters and DDL
statements.
Added a new argument `ignoreInsert` at integration test. Bigtable only
allow `SELECT` statement. This is used to filter insert statement for
bigtable.
Part of #535
Add `templateParameters` to support non-filter parameters and DDL
statements.
Added a new argument `ignoreDdl` at integration test. Admin client is
needed to execute ddl statement in spanner. Toolbox does not use admin
client.
Part of #535
Add new tool field, templateParameters, to support non-filter parameters
and DDL statements
Fix#535 for postgressql tool.
---------
Co-authored-by: Yuan <45984206+Yuan325@users.noreply.github.com>
This PR refactors the tool configuration and loading mechanism to use a
dynamic registration pattern. Each tool package now registers itself
with a central registry, and the server configuration code uses this
registry to decode and initialize tools.
Key changes:
- Introduced tools.Register and tools.DecodeToolConfig for dynamic tool
handling.
- Removed direct imports of specific tool packages from
internal/server/config.go.
- Updated individual tool packages to include init() functions for
self-registration.
- Modified ToolKind constants to be local kind constants within each
tool package.
- Adjusted test files to reflect the changes in tool kind identifiers.
This change simplifies adding new tools and decouples the server
configuration from specific tool implementations.
---------
Co-authored-by: Yuan Teoh <yuanteoh@google.com>
Co-authored-by: Yuan <45984206+Yuan325@users.noreply.github.com>
@Yuan325 please review and merge this if all looks ok.
In existing code, for the character field with null values it will panic
with error:
"panic: interface conversion: interface {} is nil, not []uint8"
gosimple had been deprecated in favor of staticcheck:
https://github.com/golangci/golangci-lint/issues/357
Other requirements are all migrated.
`std-error-handling` exclusions is included because without that, it
will ask to check all error returns from (`Close()`, or `os.Setenv`s, or
`fmt.Fprint`s...
This tool can be used across spanner sources.
`spanner-execute-sql` config is as below:
```
tools:
spanner_execute_sql_tool:
kind: "spanner-execute-sql"
source: my-spanner-source
description: Use this tool to execute sql.
```
The `spanner-execute-sql` tool takes one parameter. Example request as
follow:
```
curl -X POST -H "Content-Type: application/json" -d '{"sql": "SELECT 1"}' http://127.0.0.1:5000/api/tool/spanner_execute_sql_tool/invoke
```
---------
Co-authored-by: Yuan <45984206+Yuan325@users.noreply.github.com>
This tool can be used across mysql sources.
`mysql-execute-sql` config is as below:
```
tools:
mysql_execute_sql_tool:
kind: "mysql-execute-sql"
source: my-mysql-source
description: Use this tool to execute sql.
```
The `mysql-execute-sql` tool takes one parameter. Example request as
follow:
```
curl -X POST -H "Content-Type: application/json" -d '{"sql": "SELECT 1"}' http://127.0.0.1:5000/api/tool/mysql_execute_sql_tool/invoke
```
Allowing user to add `readOnly` field in spanner tools.
The existing tool doesn't work for reading schema tables since schema
tables can only be accessed through read-only transaction.
This PR also resolve#435 for Spanner tool.
---------
Co-authored-by: Yuan <45984206+Yuan325@users.noreply.github.com>
This tool can be used across all postgres sources.
`postgres-execute-sql` config is as below:
```
tools:
postgres_execute_sql_tool:
kind: "postgres-execute-sql"
source: my-alloydb-source // or any other sources that is compatible with this tool
description: Use this tool to execute sql.
```
The `postgres-execute-sql` tool takes one parameter. Example request as
follow:
```
curl -X POST -H "Content-Type: application/json" -d '{"sql": "SELECT 1"}' http://127.0.0.1:5000/api/tool/postgres_execute_sql_tool/invoke
```
Update http tools `Invoke` method.
* use `json.Unmarshal` for response body that are either list or json
map. This will allow us to return lists as is (e.g. `[{map}]` instead of
having to nest it in an additional list (e.g. `[]any{ [{map}] }`)
* for response body that are strings or fail to unmarshal, return it as
is.
Environment variable replacement is needed so that users don't have to
hardcode their secrets in configuring `tools.yaml`.
Both formats `$ENV_NAME` and `${ENV_NAME}` are standard ways to declare
an environment variable.
However, some database statement placeholders that are already using the
`$ENV_NAME` format.
Therefore, we only support env var declaration using `${ENV_NAME}` to
disambiguate it from other usages.
Fixes issue: https://github.com/googleapis/genai-toolbox/issues/431
A `BigQuery` source can be added as the following example:
```yaml
sources:
my-bigquery-source:
kind: bigquery
project: bigframes-dev
location: us # This field is optional
```
A `BigQuery` tool can be added as below:
```yaml
tools:
search-hotels-by-name:
kind: bigquery-sql
source: my-bigquery-source
description: Search for hotels based on name.
parameters:
- name: name
type: string
description: The name of the hotel.
```
---------
Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>
# Add Bigtable support
A `bigtable` source can be added as the following example
```
sources:
test-bigtable-source:
kind: "bigtable"
project: "sample-project"
instance: "sample-instance"
```
A `bigtable` tool can be added as below
```
tools:
get-test-tool-data:
kind: bigtable-sql
source: test-bigtable-source
description: Some description
statement: SELECT * FROM `test-table` WHERE address['state'] = @state;
parameters:
- name: state
type: string
description: Filter by state
```
---------
Co-authored-by: Yuan <45984206+Yuan325@users.noreply.github.com>
Co-authored-by: Kurtis Van Gent <31518063+kurtisvg@users.noreply.github.com>
Co-authored-by: Wenxin Du <117315983+duwenxin99@users.noreply.github.com>
