Mem0 Integration: Add mem0 as memory provider for RAG #914
Conversation
|
Hi @Dev-Khant! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
|
Hey, reviewers need your help! So we are integrating Mem0 as memory provider but are facing issue on what should be the best way to do it, as currently there's only support for |
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks! |
|
I also started testing out the feature by starting a local server from this doc: https://llama-stack.readthedocs.io/en/latest/distributions/index.html. But the issue is whenever I make changes to my local it's not reflecting in the running server. How can I fix this? |
|
Hi @ashwinb, I was able to run our provider when I completely run the current But now the issue while inferencing the mem0 tool is not getting called and the default tool is called for insertion and querying. So can you please help me guide on what changes do I need to make in order to pass and call I'm following these docs:
Thanks! |
|
Hey @ashwinb Can you please go through the above comments and help me out? Thanks! |
| @@ -110,3 +113,5 @@ tool_groups: | |||
| provider_id: rag-runtime | |||
| - toolgroup_id: builtin::code_interpreter | |||
There was a problem hiding this comment.
Sorry for the late response. The problem is that we don't support multiple providers for
client.tool_runtime.rag_tool.insert:
To support this, we might need to add provider_id as an argument, similar to client.vector_dbs.register for example.
However, I also think it might be time to rework this API client.tool_runtime.rag_tool.insert. Will need some time to think through this.
What does this PR do?
Integrate Mem0 as a memory provider for RAG.
Test Plan
Please describe:
Sources
Mem0: https://mem0.ai/
Docs: https://docs.mem0.ai/overview
Before submitting
Pull Request section?