| description |
|---|
Upsert embedded data and perform similarity search upon query using Pinecone, a leading fully managed hosted vector database. |
- Register an account for Pinecone
- Click Create index
- Fill in required fields:
- Index Name, name of the index to be created. (e.g. "flowise-test")
- Dimensions, size of the vectors to be inserted in the index. (e.g. 1536)
- Click Create Index
- Get/Create your API Key
- Add a new Pinecone node to canvas and fill in the parameters:
- Pinecone Index
- Pinecone namespace (optional)
Pinecone Node
- Create new Pinecone credential -> Fill in API Key
- Add additional nodes to canvas and start the upsert process
- Document can be connected with any node under Document Loader category {% hint style="info" %} Document loaders and text splitters for LlamaIndex are not yet available, but using one of the ones available under LangChain will still allow querying with LlamaIndex as normal. {% endhint %}
- Embeddings can be connected with any node under Embeddings category
- Verify on Pinecone dashboard that data has been successfully upserted:
