+2
Document Processor
Automatically process uploaded files by extracting content
Marketing
85.8K uses
Artificial Intelligence
Pinecone
Complete Pinecone integration: vector operations, search, index management, AI embeddings, and document reranking.
15 actions
Pinecone
Pinecone
Integration details
- Triggers
- 0
- Actions
- 15
- Category
- Artificial Intelligence
- Website
- pinecone.io
Actions
Steps a workflow can run in Pinecone.
| Action | What it does |
|---|---|
| Upsert Vectors | Upsert vectors into a namespace. If a new value is upserted for an existing vector ID, it will overwrite the previous value. Important: Vector dimensions must match your index configuration (e.g., 1024, 1536, etc.). |
| Fetch Vectors | Look up and return vectors by ID from a single namespace. The returned vectors include the vector data and/or metadata. |
| Update Vector | Update a vector in a namespace. If a value is included, it will overwrite the previous value. If set_metadata is included, the values of the fields specified in it will be added or overwrite the previous value. |
| Delete Vectors | Delete vectors by id from a single namespace. |
| List Vector IDs | List the IDs of vectors in a single namespace of a serverless index. An optional prefix can be passed to limit the results to IDs with a common prefix. Note: Only supported for serverless indexes. |
| Query Vectors | Search a namespace using a query vector. Retrieves the ids of the most similar items in a namespace, along with their similarity scores. |
| Search Records | Search a namespace with a query text, query vector, or record ID and return the most similar records. Text search requires indexes with integrated embedding models. |
| List Indexes | List all indexes in a project. |
| Create Index | Create a Pinecone index. This is where you specify the measure of similarity, the dimension of vectors to be stored in the index, which cloud provider you would like to deploy with, and more. |
| Describe Index | Get a description of an index. |
| Delete Index | Delete an existing index. |
| Get Index Stats | Return statistics about the contents of an index, including the vector count per namespace, the number of dimensions, and the index fullness. Serverless indexes scale automatically as needed, so index fullness is relevant only for pod-based indexes. |
| Generate Embeddings | Generate vector embeddings for input data using Pinecone's hosted embedding models. Note: Requires access to Pinecone's inference API which may not be available on all plans. |
| Rerank Documents | Rerank results according to their relevance to a query using Pinecone's reranking models. Note: Requires access to Pinecone's inference API which may not be available on all plans. |
| List Models | List the embedding and reranking models hosted by Pinecone. Note: This requires access to Pinecone's inference API which may not be available on all plans. You can use these models for embedding generation and reranking. |
Templates with Pinecone
Ready-made workflows that already use Pinecone.
More in Artificial Intelligence
Other apps in this category you can connect to your workflows.
Connect Every Tool