flowchart TB
    subgraph Input
        A[PDF File] --> B{Text Extraction}
    end

    subgraph TextExtraction["Text Extraction"]
        B -->|Success| C[Raw Text]
        B -->|Empty/Minimal| D{OCR Configured?}
        D -->|Yes| E[Vision LLM OCR]
        D -->|No| C
        E --> C
    end

    subgraph Indexing
        C --> F[LLM Summarization]
        F -->|Per Page| G[Page Summaries]
        G --> H[(Cached Index)]
    end

    subgraph Search["Agentic Search"]
        I[User Query] --> J{Has Query?}
        J -->|No| K[Return Full Index]
        J -->|Yes| L[LLM Reasoning]
        H --> L
        L --> M[Ranked Results]
    end

    subgraph LLMProvider["LLM Provider"]
        N{MCP Sampling?}
        N -->|Supported| O[MCP Client LLM]
        N -->|Not Supported| P[Fallback LLM API]
    end

    F -.-> N
    L -.-> N

{
  "mcpServers": {
    "pageindex": {
      "command": "uv",
      "args": ["run", "--directory", "/path/to/pageindex-light-mcp", "server.py"],
      "env": {
        "PAGEINDEX_LLM_BASE_URL": "https://api.openai.com/v1",
        "PAGEINDEX_LLM_API_KEY": "sk-xxx",
        "PAGEINDEX_LLM_MODEL": "gpt-4o-mini",
        "PAGEINDEX_OCR_BASE_URL": "https://api.openai.com/v1",
        "PAGEINDEX_OCR_API_KEY": "sk-xxx",
        "PAGEINDEX_OCR_MODEL": "gpt-4o-mini"
      }
    }
  }
}

# LLM Config — Used when MCP client doesn't support Sampling
PAGEINDEX_LLM_BASE_URL=https://api.openai.com/v1
PAGEINDEX_LLM_API_KEY=sk-xxx
PAGEINDEX_LLM_MODEL=gpt-4o-mini

# OCR Config — Used when PDF text extraction returns empty/minimal content
PAGEINDEX_OCR_BASE_URL=https://api.openai.com/v1
PAGEINDEX_OCR_API_KEY=sk-xxx
PAGEINDEX_OCR_MODEL=gpt-4o-mini  # Any vision-capable model