Adk Rag FAQs

Question 1

What types of documents can Adk Rag ingest?

Accepted Answer

Currently, Adk Rag primarily processes `.md` and `.pdf` files. It extracts text, splits it into chunks, generates embeddings, and stores them in the Qdrant vector database for retrieval.

Question 2

What are the main features of Adk Rag?

Accepted Answer

Key features include semantic search powered by Qdrant, Google ADK integration, MCP server utilization for Qdrant interaction, context augmentation of LLM responses, and comprehensive monitoring and logging.

Question 3

What is Adk Rag?

Accepted Answer

Adk Rag is a Retrieval-Augmented Generation (RAG) system that combines Google's Agent Development Kit (ADK) with Qdrant vector database (via MCP server) for efficient knowledge retrieval. It enhances LLM responses with relevant context.

Question 4

What is Qdrant MCP server?

Accepted Answer

Qdrant MCP (Model Context Protocol) server facilitates interaction with the Qdrant vector database. Adk Rag uses it for storing and retrieving relevant context to improve LLM performance.

Question 5

How do I install and configure Adk Rag?

Accepted Answer

Installation involves cloning the repository, creating a virtual environment, installing dependencies using `uv pip install -r requirements.txt`, and configuring environment variables in a `.env` file within the `docker` directory.  Then, build and start services using Docker Compose.

Adk Rag

Adk Rag

主要功能

使用案例

主要功能

使用案例