Add RAG module into AgentScope

[DavdGao]

AgentScope Version

1.0.4

Description

• Basic functionalities
  • Finish the RAG module abstraction
  • Provide basic implementations
    • A Qdrant based store class QdrantStore
    • A simple knowledge class SimpleKnowledge
    • A text reader class TextReader and a basic PDF reader class PDFReader
  • Support DashScope multimodal embedding API by DashScopeMultiModalEmbedding
  • Support batch embedding with batch size larger than 10 in DashScopeTextEmbedding
• Examples
  • Add a RAG example to demonstrate 1) basic usage, 2) agentic RAG, 3) integration with ReActAgent, and 4) multimodal RAG
• Docs
  • Add RAG section in the tutorial (both Chinese and English)
• Unittests
  • Add unittests for the store class
  • Add unittests for the knowledge class
  • Add unittests for the reader classes
  • Add unittests for the DashScope multimodal embedding class DashScopeMultiModalEmbedding

Checklist

Please check the following items before code is ready to be reviewed.

• Code has been formatted with pre-commit run --all-files command
• All tests are passing
• Docstrings are in Google style
• Related documentation has been updated (e.g. links, examples, etc.)
• Code is ready for review

[Copilot]

Pull Request Overview

Adds a comprehensive Retrieval-Augmented Generation (RAG) module to AgentScope that supports both multimodal data and traditional text-based RAG functionality. The module provides document readers, vector database stores, knowledge bases, and integrates with embedding models to enable document-based question answering capabilities.

Key changes:

• New RAG module with document readers (TextReader, PDFReader) for data chunking
• Vector database store abstractions with Qdrant implementation for document storage
• Knowledge base system supporting multimodal embeddings
• Integration of RAG capabilities into ReActAgent through knowledge parameter

Reviewed Changes

Copilot reviewed 24 out of 25 changed files in this pull request and generated 8 comments.

Show a summary per file

File	Description
src/agentscope/rag/	Core RAG module with document, reader, store, and knowledge base implementations
src/agentscope/embedding/	Updated embedding models to support dimensions and multimodal data
src/agentscope/agent/_react_agent.py	Added knowledge parameter to ReActAgent for RAG integration
tests/tracer_test.py	Updated test to reflect embedding model constructor changes
examples/functionality/rag/	Example usage scripts demonstrating basic and agentic RAG workflows

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

Pull Request Overview

Copilot reviewed 46 out of 47 changed files in this pull request and generated 10 comments.

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

Pull Request Overview

Copilot reviewed 47 out of 48 changed files in this pull request and generated 5 comments.

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}

[Copilot]

Pull Request Overview

Copilot reviewed 46 out of 47 changed files in this pull request and generated 6 comments.

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}