# Clone the repository
git clone <repository-url>
cd documentation

# Create virtual environment
python3.12 -m venv .venv
source .venv/bin/activate

# Install dependencies
pip install -r requirements.txt

# Pull the embedding model
ollama pull bge-m3

# Fetch documentation
python -m src.main fetch gemini
python -m src.main fetch fastmcp

# Index for search (requires Ollama running)
python -m src.rag.index gemini
python -m src.rag.index fastmcp

# Search Gemini docs
python -m src.main search "function calling"

# Search FastMCP docs
python -m src.main search "how to create a tool" -c fastmcp

# More results
python -m src.main search "rate limits" -n 10

# Replace /path/to/documentation with your actual absolute path
claude mcp add docs-search --scope user --transport stdio -- \
  /path/to/documentation/.venv/bin/python \
  /path/to/documentation/src/mcp_server.py

{
  "mcpServers": {
    "docs-search": {
      "command": "/path/to/documentation/.venv/bin/python",
      "args": ["/path/to/documentation/src/mcp_server.py"]
    }
  }
}

# Check server is registered
claude mcp list

# In Claude Code, check connection status
/mcp

documentation/
├── src/
│   ├── main.py                 # CLI entry point
│   ├── mcp_server.py           # MCP server for Claude Code
│   ├── core/
│   │   ├── fetcher.py          # HTTP/markdown fetching
│   │   └── parser.py           # Navigation parsing
│   ├── modules/
│   │   ├── base.py             # Abstract base class
│   │   ├── gemini/             # Gemini documentation module
│   │   └── fastmcp/            # FastMCP documentation module
│   └── rag/
│       ├── chunker.py          # Markdown-aware chunking
│       ├── embedder.py         # Ollama bge-m3 embeddings
│       ├── sqlite_store.py     # SQLite + sqlite-vec vector store
│       ├── search.py           # Hybrid search with RRF
│       ├── query_expander.py   # Multi-query expansion (LLM)
│       ├── reranker.py         # Cross-encoder reranking
│       └── index.py            # Indexing CLI
├── output/                     # Fetched documentation
│   ├── gemini/
│   └── fastmcp/
├── data/
│   └── docs.db                 # SQLite vector database
├── requirements.txt
└── README.md

# src/modules/example/config.py
BASE_URL = "https://docs.example.com"
SITEMAP_URL = "https://docs.example.com/sitemap.xml"
MARKDOWN_SUFFIX = ".md"  # or ".md.txt" for Google sites

# src/modules/example/module.py
from src.modules.base import BaseModule

class ExampleModule(BaseModule):
    @property
    def name(self) -> str:
        return "example"

    def get_doc_urls(self) -> list[NavLink]:
        # Parse sitemap or navigation
        ...

    def fetch_page(self, url: str) -> str:
        # Fetch markdown content
        ...

from src.modules.example.module import ExampleModule

# In fetch_command():
elif args.module == "example":
    module = ExampleModule()
    module.run(output_dir)

python -m src.main fetch example
python -m src.rag.index example

# Run tests
python -m pytest

# Check MCP server
claude mcp list

# Test search functionality
python -m src.rag.search

# Make sure Ollama is running
ollama serve

# Pull the embedding model
ollama pull bge-m3

# Check if collection is indexed
python -m src.rag.index --status gemini

# Re-index if needed
python -m src.rag.index --clear gemini

# Check server status
claude mcp list

# Reinstall
claude mcp remove docs-search
fastmcp install claude-code src/mcp_server.py --name docs-search