Pinecone (Canopy) Integration

This integration allows a developer using Canopy to choose from the best LLMs on OctoAI.


Pinecone provides storage and retrieval infrastructure needed for building AI applications. Pinecone’s Canopy is an open-source framework built on top of Pinecone’s vector database to build production-ready chat assistants at any scale.

Using OctoAI’s LLMs and Pinecone

As a fully open source solution, Canopy+OctoAI is one of the fastest ways and more affordable ways to get started on your RAG journey. Canopy uses Pinecone vector database for storage and retrieval, which is free to use for up to 100k vectors (that’s about 30k pages of text). OctoAI offers industry leading pricing at $0.05 / 1M token for its gte-large embedding model, and offers $10 of free credit upon sign up.

To get a Canopy server running with OctoAI’s modles, you do not need custom ConvolverNode, simply update the Canopy YAML configureations as follows:

max_prompt_tokens: 2048
llm: &llm
type: OctoAILLM
model_name: mistral-7b-instruct
type: OctoAIRecordEncoder
model_name: thenlper/gte-large
batch_size: 2048

Learn with our demo apps

Get started today by following along with one of our demo apps:

Learn more about our partnership: