Daniel Chalef
Daniel Chalef
Thanks for reporting. While we investigate, would you like to use Zep filter boolean logic here rather than an `in` operation? I recognize this may not be helpful if the...
Hey @raghavendracs unfortunately I've not had time to investigate. We use Postgres' JSONPath flavor. If the `in` syntax is not supported by Postgres, it won't work with Zep: https://www.postgresql.org/docs/current/functions-json.html#FUNCTIONS-SQLJSON-PATH
Zep embeds all chat conversations so that they may be recalled via semantic search. Are you using Azure's OpenAI embedding service or Zep's local embedding service? More about Zep's embedding...
We've merged a fix for this in #346 and released in `v0.26.0`
Search scores are cosine distance normalized to (0,1). As such, you may be able to accomplish this by combining results from separate searches over the different Collections, ordering by score,...
Great. Hopefully the Go was straightforward. I've left some thoughts on the PR. Thanks for contributing!
This is on the roadmap, alongside the Titan Foundational LLMs. I can't say as yet when we'll get to it though!
Amazon Bedrock and other inference providers are now supported via a proxy such as LiteLLM.
Thanks, all. We'd love to support LangGraph. LG checkpoints contain both chat history and the graph's state. Would you expect Zep to maintain state for the entire graph? How should...
@elvenking I expect LangChain to continue rapidly evolving and enhancing the LangGraph framework and cloud service in the coming year, with changes to APIs and the Checkpoint format inevitable. I...