New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

FastAPI RAG app example with vector embeddings #1118

Merged

mkandler merged 10 commits into main from fastapi-embedding-example

Aug 12, 2024

Contributor

mkandler commented Aug 6, 2024

No description provided.

jlewitt1 and others added 7 commits

August 6, 2024 17:46


          add fast api embedding example

41ed111


          Restructure and spruce up multi-hop example to store vector embedding…

be1e811

…s and find matches to a text input


          Fill in description of FastAPI Rag app, include generation step with …

07316bb

…vLLM


          Expanding example markdown for FastAPI Rag app

7bc9e8d


          Expanding example markdown for FastAPI Rag app

bf03c4f


          Filling in example content and improving debuggability of RAG

af2e34a


          Rename rag example, add graphic

d977947

mkandler marked this pull request as ready for review

August 9, 2024 21:55


          Rename example/fastapi-embeddings-rag

cc0c4ba

mkandler changed the title ~~[WIP] Fastapi embedding example~~ FastAPI RAG app example with vector embeddings

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Outdated Show resolved Hide resolved

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Outdated Show resolved Hide resolved

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Outdated Show resolved Hide resolved

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Outdated Show resolved Hide resolved

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Show resolved Hide resolved

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Show resolved Hide resolved

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Outdated Show resolved Hide resolved

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Show resolved Hide resolved

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Show resolved Hide resolved

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Outdated Show resolved Hide resolved


          Cleanup rag embedding app instructions

1c5a306

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py

+                  module_name = "llama_model"
+                  # First check for an instance of the LlamaModel stored on the cluster
+                  remote_llm = cluster.get(module_name, default=None, remote=True)

Collaborator

jlewitt1 Aug 12, 2024

is this block here to remove confusion behind get_or_to?

Contributor Author

mkandler Aug 12, 2024

yeah and I think .get_or_to isn't necessarily working as intended for modules? @dongreenberg made this point last week

jlewitt1 reviewed

View reviewed changes

examples/fastapi-embeddings-rag/app/main.py Show resolved Hide resolved


          Include note on cloud providers

ae87072

mkandler merged commit c75fa7c into main

10 of 12 checks passed

mkandler deleted the fastapi-embedding-example branch

August 12, 2024 19:31

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet