kdeps-tools-embedding
v1.0.0Run one embedding operation: index, search, upsert or delete in the local SQLite embedding database, vectorize or embed_query through an embedding backend, or rerank documents with Cohere. Call it through the embedding component. Requires: operation. Optional: text, collection, dbPath, limit, inputs, model, backend, baseURL, rerankQuery, rerankDocuments, rerankTopN.
set tools / shelf tools
LLM context: ~408 tokens when loaded (prompt or tool definition)
Where it runs
Part of the tools set, used in workflow and agent mode. What the model is told about each built-in tool: its description, usage notes and parameters. kdeps runs the tool itself.
- the agent loop builds the request
- the tool definitions are sent to the modeltools/embedding
- the model calls a tool
- kdeps runs it
- the result goes back to the model
Loaded by: kdeps (agent loop), /update, /settings, kdeps run, kdeps install, kdeps list, kdeps uninstall, kdeps update
In the code: kdeps (agent loop)agent.RegisterBuiltinToolsagent.definedAs
Install
A kdeps asset: installed with the first-run profile that includes its set, or the first time a command needs it, and updated without a new release.
Pin a version with kdeps install tools/embedding@<version>.
Contents
Run one embedding operation: index, search, upsert or delete in the local SQLite embedding database, vectorize or embed_query through an embedding backend, or rerank documents with Cohere. Call it through the embedding component. Requires: operation. Optional: text, collection, dbPath, limit, inputs, model, backend, baseURL, rerankQuery, rerankDocuments, rerankTopN.
| Parameter | Type | Description |
|---|---|---|
| backend | string | Embedding backend for vectorize/embed_query: openai, ollama, google. |
| baseURL | string | Custom base URL for an OpenAI-compatible backend. |
| collection | string | Collection (namespace) inside the local embedding database. |
| dbPath | string | Path to the SQLite embedding database. Default comes from the embedding defaults. |
| inputs | array | Texts to embed for vectorize and embed_query. |
| limit | number | Maximum number of search results. |
| model | string | Embedding model for vectorize and embed_query, e.g. text-embedding-3-small. |
| operation * | string | index, search, upsert, delete, vectorize, embed_query or rerank. |
| rerankDocuments | array | Candidate documents to rerank (operation rerank). |
| rerankQuery | string | Query the candidate documents are ranked against (operation rerank). |
| rerankTopN | number | Number of top reranked results to return; 0 returns all. |
| text | string | Text to index, search for, upsert or delete. |
version: 1.0.0
description: 'Run one embedding operation: index, search, upsert or delete in the local SQLite embedding database, vectorize or embed_query through an embedding backend, or rerank documents with Cohere. Call it through the embedding component. Requires: operation. Optional: text, collection, dbPath, limit, inputs, model, backend, baseURL, rerankQuery, rerankDocuments, rerankTopN.'
parameters:
backend:
type: string
description: 'Embedding backend for vectorize/embed_query: openai, ollama, google.'
baseURL:
type: string
description: Custom base URL for an OpenAI-compatible backend.
collection:
type: string
description: Collection (namespace) inside the local embedding database.
dbPath:
type: string
description: Path to the SQLite embedding database. Default comes from the embedding defaults.
inputs:
type: array
description: Texts to embed for vectorize and embed_query.
limit:
type: number
description: Maximum number of search results.
model:
type: string
description: Embedding model for vectorize and embed_query, e.g. text-embedding-3-small.
operation:
type: string
description: 'index, search, upsert, delete, vectorize, embed_query or rerank.'
required: true
rerankDocuments:
type: array
description: Candidate documents to rerank (operation rerank).
rerankQuery:
type: string
description: Query the candidate documents are ranked against (operation rerank).
rerankTopN:
type: number
description: Number of top reranked results to return; 0 returns all.
text:
type: string
description: Text to index, search for, upsert or delete.
Versions
| Version | Published | Status |
|---|---|---|
| 1.0.0 | 10/21/2026 | active |
Details
- Author
- kdeps
- License
- Apache-2.0
- Latest Version
- 1.0.0
- Published
- 10/21/2026