redis-vl-python
redis-vl-python copied to clipboard
redis
Redis Vector Library (RedisVL) interfaces with Redis' vector database for realtime semantic search, RAG, and recommendation systems.
Add a more clear validation on AzureOpenAITextVectorizer config for azure_deployment, so it won't make people confused since it doesn't state that azure_deployment is a required field.
The third cell in this section contains unwanted output: https://docs.redisvl.com/en/latest/user_guide/04_vectorizers.html#azure-openai
Proposal to introduce multimodal embeddings and a reference implementation using VoyageAI multimodal embeddings api
Is there an interface planned for multimodal embeddings? We'd love to contribute one that accepts interleaved text and images, similar to how Anthropic does [content blocks](https://docs.anthropic.com/en/docs/build-with-claude/vision#example-multiple-images-with-a-system-prompt).
When an index is defined with multiple prefixes such as: `IndexDefinition(prefix=["AA","BB","CC"], index_type=IndexType.HASH)` and we call `.from_existing(..)` the returned index is: "index": { "name": "index:test", "prefix": "AA", "key_separator": ":", "storage_type": "hash"...
Right now in order to deserialize an embedding field, you need to call: ``` qry.return_field("embedding", decode_field=False) qry.return_fields("title","year") ``` which is less ideally from a UX perspective. This feature was added...
