According to the json schema spec:There are two numeric types in JSON
Schema: integer and number So 'float' is not with mcpcurl and mcphost
Fixes#984, #797
---------
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
mysql driver return []uint8 types for "JSON", hence we will need to cast
it.
Toolbox will unmarshal JSON data retrieved from database during
invocation. If directly convert results into string, it will be
marshaled again when returning results to the user (causing double
marshaling).
Fixes#840
Example:
```
alloydb-operations-get:
kind: wait-for-operation
source: alloydb-api-source
method: GET
path: /v1/projects/{{.projectId}}/locations/{{.locationId}}/operations/{{.operationId}}
description: "Makes API call to check whether operation is done or not. This tool is run first then wait for tool. if its still in create phase trigger it after 3 minutes. Print a message saying still not done. We will notify once its done."
pathParams:
- name: projectId
type: string
description: The dynamic path parameter
- name: locationId
type: string
description: The dynamic path parameter
default: us-central1
- name: operationId
type: string
description: Operation status check for previous task
```
This pull request introduces a new tool for executing arbitrary Cypher
queries against a Neo4j database (`neo4j-execute-cypher`) and implements
robust query classification functionality to distinguish between read
and write operations. The changes include updates to documentation, the
addition of a query classifier, and comprehensive test coverage for the
classifier.
### Addition of `neo4j-execute-cypher` tool:
- **Documentation**: Added a new markdown file `neo4j-execute-cypher.md`
that explains the tool's functionality, usage, and configuration
options, including the ability to enforce read-only mode for security.
- **Import statement**: Registered the new tool in the `cmd/root.go`
file to make it available in the toolbox.
### Query classification functionality:
- **Query classifier implementation**: Added `QueryClassifier` in
`classifier.go`, which classifies Cypher queries into read or write
operations based on keywords, procedures, and subquery analysis. It
supports handling edge cases like nested subqueries, multi-word
keywords, and invalid syntax.
- **Test coverage**: Created extensive tests in `classifier_test.go` to
validate the classifier's behavior across various query types, including
abuse cases, subqueries, and procedure calls. Tests ensure the
classifier is robust and does not panic on malformed queries.
---------
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
Previously code snippets were added to the README on how to use the new
Toolbox Go Core SDK.
Recently we have released a `tbgenkit` client-side package to make
integration with Genkit Go easier.
This PR updates the code snippet to use the newer package
---------
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
The checkout actions uses ref as `github.sha` by default. For forked
repos, this refers to the last commit on the main branch
([ref](https://docs.github.com/en/actions/reference/events-that-trigger-workflows#fork)).
This means that the docs preview pipeline when run on forked PRs does
not allow us to preview changes made in the PR.
`github.event.pull_request.head.sha` allows to to checkout the latest
commit on the forked PR.
### What this PR does:
This Pull Request resolves a critical configuration error in the
`cloud-sql-mssql.yaml` prebuilt tool definition, which was preventing
the `execute_sql` tool from correctly initializing and connecting to a
Cloud SQL for SQL Server instance.
### Problem:
Previously, the `source` field in
`internal/prebuiltconfigs/tools/cloud-sql-mssql.yaml` was incorrectly
configured as `cloud-sql-mssql-source`. This led to the `genai-toolbox`
server failing to find the corresponding data source, resulting in
errors like:
### Description
Enhance the [JavaScript
Quickstart](https://googleapis.github.io/genai-toolbox/getting-started/local_quickstart_js/)
by adding a new tab dedicated to integrating the MCP Toolbox with
LlamaIndex. This provides users with a direct, runnable example of how
to utilize Toolbox's capabilities within a LlamaIndex-powered LLM agent
for hotel search and booking operations.
The changes include:
- Addition of a new `LlamaIndex` tab in `docs/quickstarts/js-local.md`.
- Corresponding `hotelAgent.js` code snippet for LlamaIndex integration.
### Related Issue
This PR addresses and resolves#930.
---------
Signed-off-by: Anushka Saxena <anushka.saxena-it-2k19-05@iips.edu.in>
Co-authored-by: Twisha Bansal <58483338+twishabansal@users.noreply.github.com>
**Package Renaming**: The `neo4j` package has been renamed to
`neo4jcypher` to better reflect its functionality. This change affects
the tool's implementation
(`internal/tools/neo4j/neo4jcypher/neo4jcypher.go`) and its associated
tests (`internal/tools/neo4j/neo4jcypher/neo4jcypher_test.go`).
support both generic and typed map. Config example:
```
parameters:
- name: user_scores
type: map
description: A map of user IDs to their scores. All scores must be integers.
valueType: integer # This enforces the value type for all entries. Leave it blank for generic map
```
Represented as `Object` with `additionalProperties` in manifests.
Added a util function to convert json.Number (string type) to int/float
types to address the problem where int/float values are converted to
strings for the generic map.
- Added a dry run step to identify the query type (e.g., SELECT, DML),
which allows the tool to correctly handle the query's output.
- The recommended high-level client, cloud.google.com/go/bigquery, does
not expose the statement type from a dry run. To circumvent this
limitation, the low-level BigQuery REST API client
(google.golang.org/api/bigquery/v2) was added to gain access to these
necessary details.
fixes: #915
---------
Co-authored-by: Yuan Teoh <45984206+Yuan325@users.noreply.github.com>
Firestore is a NoSQL document database built for automatic scaling, high
performance, and ease of application development. It's a fully managed,
serverless database that supports mobile, web, and server development.
This change adds Firestore as a source in toolbox
This PR consist of two fixes:
1. Added `default` to table_names parameter since the default value is
an empty string.
2. Update the sql statement for reusing parameter within the statement.
Fixes partial #877
Update `tool.Invoke()` to return type `any` instead of `[]any`.
Toolbox return a map with the `results` key, and the SDK reads the
string from the key. So this won't break existing SDK implementation.
Fixes#870
