Embedding Tools¶
Configuration File: embedding_tools.json
Tool Type: Local
Tools Count: 5
This page contains all tools defined in the embedding_tools.json configuration file.
Available Tools¶
embedding_database_add (Type: EmbeddingDatabase)¶
Append documents to an existing per-collection datastore (<name>.db + <name>.faiss). Uses the sam…
embedding_database_add tool specification
Tool Information:
Name:
embedding_database_addType:
EmbeddingDatabaseDescription: Append documents to an existing per-collection datastore (<name>.db + <name>.faiss). Uses the same L2-normalized cosine setup. Enforces model/dimension consistency with the collection.
Parameters:
action(string) (optional) No descriptiondatabase_name(string) (required) Existing collection/database namedocuments(array) (required) List of new document texts to embed and addmetadata(array) (optional) Optional metadata per document (must match length of documents if provided)provider(string) (optional) Embedding backend override. If omitted, falls back to collection/env.model(string) (optional) Embedding model/deployment id override. If omitted, uses collection model or env default.
Example Usage:
query = {
"name": "embedding_database_add",
"arguments": {
"database_name": "example_value",
"documents": ["item1", "item2"]
}
}
result = tu.run(query)
embedding_database_create (Type: EmbeddingDatabase)¶
Create a per-collection datastore: <name>.db (SQLite) + <name>.faiss (FAISS). Embeds documents us…
embedding_database_create tool specification
Tool Information:
Name:
embedding_database_createType:
EmbeddingDatabaseDescription: Create a per-collection datastore: <name>.db (SQLite) + <name>.faiss (FAISS). Embeds documents using the chosen provider (openai/azure/huggingface/local). Vectors are L2-normalized; FAISS index uses IndexFlatIP (cosine).
Parameters:
action(string) (optional) No descriptiondatabase_name(string) (required) Collection/database name (produces <name>.db and <name>.faiss)documents(array) (required) List of document texts to embed and storemetadata(array) (optional) Optional metadata for each document (must match length of documents if provided)provider(string) (optional) Embedding backend. Defaults: EMBED_PROVIDER, else by available creds (azure>openai>huggingface>local).model(string) (optional) Embedding model/deployment id. Defaults: EMBED_MODEL, else provider-specific sensible default.description(string) (optional) Optional human-readable description for the collection
Example Usage:
query = {
"name": "embedding_database_create",
"arguments": {
"database_name": "example_value",
"documents": ["item1", "item2"]
}
}
result = tu.run(query)
embedding_database_search (Type: EmbeddingDatabase)¶
Semantic search over a per-collection datastore using FAISS (cosine via L2-normalized vectors). S…
embedding_database_search tool specification
Tool Information:
Name:
embedding_database_searchType:
EmbeddingDatabaseDescription: Semantic search over a per-collection datastore using FAISS (cosine via L2-normalized vectors). Supports optional metadata filtering.
Parameters:
action(string) (optional) No descriptiondatabase_name(string) (required) Collection/database name to searchquery(string) (required) Query text to embed and search withtop_k(integer) (optional) Number of most similar documents to returnfilters(object) (optional) Optional metadata filters (‘$gte’, ‘$lte’, ‘$in’, ‘$contains’, exact match)provider(string) (optional) Embedding backend for the query vector. Defaults to collection/env.model(string) (optional) Embedding model/deployment id for the query vector. Defaults to collection/env.
Example Usage:
query = {
"name": "embedding_database_search",
"arguments": {
"database_name": "example_value",
"query": "example_value"
}
}
result = tu.run(query)
embedding_sync_download (Type: EmbeddingSync)¶
Download a per-collection datastore from Hugging Face Hub into ./data/embeddings as <name>.db and…
embedding_sync_download tool specification
Tool Information:
Name:
embedding_sync_downloadType:
EmbeddingSyncDescription: Download a per-collection datastore from Hugging Face Hub into ./data/embeddings as <name>.db and <name>.faiss.
Parameters:
action(string) (optional) No descriptionrepository(string) (required) HF dataset repo to download from (e.g., ‘user/repo’)local_name(string) (optional) Local collection name to save as (defaults to repo basename)overwrite(boolean) (optional) Whether to overwrite existing local files
Example Usage:
query = {
"name": "embedding_sync_download",
"arguments": {
"repository": "example_value"
}
}
result = tu.run(query)
embedding_sync_upload (Type: EmbeddingSync)¶
Upload a per-collection datastore to Hugging Face Hub: <name>.db and <name>.faiss, plus metadata …
embedding_sync_upload tool specification
Tool Information:
Name:
embedding_sync_uploadType:
EmbeddingSyncDescription: Upload a per-collection datastore to Hugging Face Hub: <name>.db and <name>.faiss, plus metadata files.
Parameters:
action(string) (optional) No descriptiondatabase_name(string) (required) Collection/database name to upload (expects <name>.db and <name>.faiss under data_dir)repository(string) (required) HF dataset repo (e.g., ‘user/repo’)description(string) (optional) Optional dataset description in the HF READMEprivate(boolean) (optional) Create/use a private HF repocommit_message(string) (optional) Commit message for the upload
Example Usage:
query = {
"name": "embedding_sync_upload",
"arguments": {
"database_name": "example_value",
"repository": "example_value"
}
}
result = tu.run(query)