Degree Copilot

deleted deleted posted an update — Jul 04, 2024 08:05 PM EDT

The credits I received for this event have expired so the demo application is no longer live.

deleted deleted posted an update — Jun 30, 2024 03:36 AM EDT

In the FastAPI application lifespan startup, the Cosmongo instances are created using the users and chat collections in the CosmosDB for MongoDB vCore database. While the messages array goes into the class variable messages, it does not go into its agent_executor. Therefore the underlying Langchain Agent Executor will not have access to this message history. This can be seen by looking at the create_conversational_retrieval_agent function call in the init of Cosmongo. I am curious how this conversation history can be fed to the agent upon creation. I looked into this function from Langchain but it doesnt appear to accept a conversation history (although it does take memory_key param). Perhaps creating the Agent Executor with the class constructor and passing memory param is the way to go.

It is not a big deal, since I believe the Azure App Service will keep the server running. However, in case of any requirement to restart, it would be nice to have this feature.

deleted deleted posted an update — Jun 29, 2024 02:11 PM EDT

Realized I did not implement the vector search feature for degrees. Partly because the degree embeddings were not working as well as the course embeddings (more detailed descriptions of courses), so I was more focused on the latter.

To get this working, take the code in the Vector Embedding condition in the /courses route in routes.py, add it to the /degrees route, and modify the collections that are queried.

deleted deleted posted an update — Jun 26, 2024 07:49 PM EDT

Embedding endpoint is currently down so the Chat and Vector searches won't work.

deleted deleted started this project — Jun 22, 2024 11:23 PM EDT

Leave feedback in the comments!