This is a more involved example using dexter
to build a basic chatbot using RAG. It indexes 100 transcript chunks from the Huberman Lab Podcast into a hybrid Pinecone datastore using OpenAI ada-002 embeddings for the dense vectors and a HuggingFace SPLADE model for the sparse embeddings.
OPENAI_API_KEY
PINECONE_API_KEY
PINECONE_BASE_URL
- Note: Pinecone's free starter indexes don't seem to support namespaces or hybrid search, so unfortunately you'll need to upgrade to a paid plan to run this example. See Pinecone's hybrid docs for details on setting up a hybrid index, and make sure it is using the
dotproduct
metric.
- Note: Pinecone's free starter indexes don't seem to support namespaces or hybrid search, so unfortunately you'll need to upgrade to a paid plan to run this example. See Pinecone's hybrid docs for details on setting up a hybrid index, and make sure it is using the
SPLADE_SERVICE_URL
tsx examples/chatbot/ingest.ts
tsx examples/chatbot/cli.ts
MIT © Dexa