Terminal
Terminal/Skill
Lets your agent search, query and manage Weaviate vector database collections, including imports from PDF, CSV and JSON files.
By Weaviate
Works with
npx skills add weaviate/agent-skills --skill weaviateThis skill provides comprehensive access to Weaviate vector databases including search operations, natural language queries, schema inspection, data exploration, filtered fetching, collection creation, and data imports.
If the user does not have an instance yet, direct them to the cloud console to register and create a free sandbox. Create a Weaviate instance via Weaviate Cloud.
Required:
WEAVIATE_URL - Your Weaviate Cloud cluster URLWEAVIATE_API_KEY - Your Weaviate API keyExternal Provider Keys (auto-detected): Set only the keys your collections use, refer to Environment Requirements for more information.
text2vec_weaviate is used).Weaviate Cloud free-tier clusters have limits that can change; if a script's error contradicts this section, trust the error.
429 USAGE_LIMIT_EXCEEDED ("collections count limit of 1 reached"). Run list_collections.py first. If a collection exists, import into it instead of creating another, and ask the user before using the only slot.example_data.py uses that slot; a PDF import is refused. example_data.py creates one collection whose name depends on --domain (AI_Arxiv for the default academic; Income_Tax_Returns, Product_Catalog, Hair_Medical or IT_Support_Tickets for the others). Do not run it unless the user agrees to spend the slot. import.py on a PDF creates its collection automatically, and free-tier clusters refuse that create with 422 CONFIG_NOT_ALLOWED; if the user asks for a PDF import, tell them it is refused on a free-tier cluster and let them decide. No script here deletes a collection.hfresh vector index is accepted. A create that asks for another type (for example hnsw) is refused with 422 CONFIG_NOT_ALLOWED. The scripts pin weaviate-client 4.23.1, which leaves the index type to the server; older clients request hnsw and are refused. If a 422 says hnsw is not allowed on 4.23.1 or newer, tell the user rather than retrying.Start by listing collections if you don't know what's available:
uv run scripts/list_collections.py
Ask the user if they want to create example data if nothing is available and the user requests it. Otherwise continue.
uv run scripts/example_data.py
Get collection details to understand the schema:
uv run scripts/get_collection.py --name "COLLECTION_NAME"
Explore collection data to see values and statistics:
uv run scripts/explore_collection.py "COLLECTION_NAME"
Create a collection if importing a new CSV, JSON, or JSONL file — the collection must exist before importing:
uv run scripts/create_collection.py CollectionName \
--properties '[{"name": "title", "data_type": "text"}, {"name": "body", "data_type": "text"}]'
Do not specify a vectorizer unless the user explicitly requests one.
Import data into an existing collection:
uv run scripts/import.py "data.csv" --collection "CollectionName"
For PDF imports, the collection is created automatically — skip step 5.
Choose the right search type:
ask.pyquery_search.pyhybrid_search.py (default)semantic_search.pykeyword_search.pyAll scripts support:
--json flag)Common errors:
WEAVIATE_URL not set → Set the environment variableCollection not found → Use list_collections.py to see available collectionsAuthentication error → Check API keys for both Weaviate and vectorizer providers