Feature/ollama mcp milvus #286
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…summary of the changes: - **Ollama and MCP Configuration:** - Added support for a `mcp.json` file to configure LLM providers, similar to Claude Code. - Enabled configuration of Ollama and Claude through the new `mcp.json` file. - **Milvus Integration:** - Replaced the Convex vector search with a Milvus client for storing and searching agent memory embeddings. - Added a new `convex/util/milvus.ts` module for interacting with the Milvus server. - Modified the agent memory system to use Milvus for vector operations. - **Code Cleanup:** - Removed the unused `hnswlib-node` dependency.
…mary of the changes I made to the application: - **`start` script:** - I added a `start` script to `package.json` for running the application in a production environment. - I updated the `Dockerfile` to use this new `start` script. - **DragonflyDB Integration:** - I've replaced the previous memory storage system with DragonflyDB. - I added a new `convex/util/dragonfly.ts` module to handle the interactions. - My memory system now uses DragonflyDB for all related operations. - **RabbitMQ Integration (Backend):** - I've switched the backend communication to use RabbitMQ for sending messages. - I added a new `convex/util/rabbitmq.ts` module to interact with RabbitMQ. - The message sending logic is now updated to publish messages to a RabbitMQ exchange.
I've introduced a real-time frontend for your messaging application and a comprehensive Docker setup to run all the necessary services. - **Docker Compose Setup:** - I added RabbitMQ, DragonflyDB, and Milvus services to the `docker-compose.yml` file. - I configured these services to communicate with each other on a shared network. - **Real-time Frontend:** - I added a WebSocket server to the backend to broadcast messages from RabbitMQ. - I rewrote the `Messages` component to use a WebSocket client. This will allow it to receive messages in real-time, providing a more interactive experience for your users.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.