15101b1edb
This PR introduces a new configuration field valueFromParam to the tool definitions. This feature allows a parameter to automatically inherit its value from another sibling parameter, mainly to streamline the configuration of vector insertion tools. Parameters utilizing valueFromParam are excluded from the Tool and MCP manifests. This means the LLM does not see these parameters and is not required to generate them. The value is resolved internally by the Toolbox during execution.
3.2 KiB
title, type, weight, description
| title | type | weight | description |
|---|---|---|---|
| EmbeddingModels | docs | 2 | EmbeddingModels represent services that transform text into vector embeddings for semantic search. |
EmbeddingModels represent services that generate vector representations of text data. In the MCP Toolbox, these models enable Semantic Queries, allowing Tools to automatically convert human-readable text into numerical vectors before using them in a query.
This is primarily used in two scenarios:
-
Vector Ingestion: Converting a text parameter into a vector string during an
INSERToperation. -
Semantic Search: Converting a natural language query into a vector to perform similarity searches.
Hidden Parameter Duplication (valueFromParam)
When building tools for vector ingestion, you often need the same input string twice:
- To store the original text in a TEXT column.
- To generate the vector embedding for a VECTOR column.
Requesting an Agent (LLM) to output the exact same string twice is inefficient
and error-prone. The valueFromParam field solves this by allowing a parameter
to inherit its value from another parameter in the same tool.
Key Behaviors
- Hidden from Manifest: Parameters with valueFromParam set are excluded from the tool definition sent to the Agent. The Agent does not know this parameter exists.
- Auto-Filled: When the tool is executed, the Toolbox automatically copies the value from the referenced parameter before processing embeddings.
Example
The following configuration defines an embedding model and applies it to specific tool parameters.
{{< notice tip >}} Use environment variable replacement with the format ${ENV_NAME} instead of hardcoding your API keys into the configuration file. {{< /notice >}}
Step 1 - Define an Embedding Model
Define an embedding model in the embeddingModels section:
embeddingModels:
gemini-model: # Name of the embedding model
kind: gemini
model: gemini-embedding-001
apiKey: ${GOOGLE_API_KEY}
dimension: 768
Step 2 - Embed Tool Parameters
Use the defined embedding model, embed your query parameters using the
embeddedBy field. Only string-typed parameters can be embedded:
tools:
# Vector ingestion tool
insert_embedding:
kind: postgres-sql
source: my-pg-instance
statement: |
INSERT INTO documents (content, embedding)
VALUES ($1, $2);
parameters:
- name: content
type: string
description: The raw text content to be stored in the database.
- name: vector_string
type: string
# This parameter is hidden from the LLM.
# It automatically copies the value from 'content' and embeds it.
valueFromParam: content
embeddedBy: gemini-model
# Semantic search tool
search_embedding:
kind: postgres-sql
source: my-pg-instance
statement: |
SELECT id, content, embedding <-> $1 AS distance
FROM documents
ORDER BY distance LIMIT 1
parameters:
- name: semantic_search_string
type: string
description: The search query that will be converted to a vector.
embeddedBy: gemini-model # refers to the name of a defined embedding model