npx -y @smithery/cli install @DeepSpringAI/parquet_mcp_server --client claude

git clone ...
cd parquet_mcp_server

uv venv
.venv\Scripts\activate  # On Windows
source .venv/bin/activate  # On macOS/Linux

uv pip install -e .

EMBEDDING_URL=http://sample-url.com/api/embed  # URL for the embedding service
OLLAMA_URL=http://sample-url.com/  # URL for Ollama server
EMBEDDING_MODEL=sample-model  # Model to use for generating embeddings
SEARCHAPI_API_KEY=your_searchapi_api_key
FIRECRAWL_API_KEY=your_firecrawl_api_key
VOYAGE_API_KEY=your_voyage_api_key
AZURE_OPENAI_ENDPOINT=http://sample-url.com/azure_openai
AZURE_OPENAI_API_KEY=your_azure_openai_api_key

{
  "mcpServers": {
    "parquet-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/home/${USER}/workspace/parquet_mcp_server/src/parquet_mcp_server",
        "run",
        "main.py"
      ]
    }
  }
}

"Please perform a web search for 'macbook' and 'laptop' and scrape the results from page 1"

"Please extract relevant information from the previous searches for 'macbook'"

python src/tests/run_tests.py

# Test Web Search
python src/tests/test_search_web.py

# Test Extract Info from Search
python src/tests/test_extract_info_from_search.py

from parquet_mcp_server.client import (
    perform_search_and_scrape,  # New web search function
    find_similar_chunks  # New extract info function
)

# Perform a web search
perform_search_and_scrape(["macbook", "laptop"], page_number=1)

# Extract information from the search results
find_similar_chunks(["macbook"])

-- Create the function for vector similarity search
CREATE OR REPLACE FUNCTION match_web_search(
  query_embedding vector(1024),  -- Adjusted vector size
  match_threshold float,
  match_count int  -- User-defined limit for number of results
)
RETURNS TABLE (
  id bigint,
  metadata jsonb,
  text TEXT,  -- Added text column to the result
  date TIMESTAMP,  -- Using the date column instead of created_at
  similarity float
)
LANGUAGE plpgsql
AS $$
BEGIN
  RETURN QUERY
  SELECT
    web_search.id,
    web_search.metadata,
    web_search.text,  -- Returning the full text of the chunk
    web_search.date,  -- Returning the date timestamp
    1 - (web_search.embedding <=> query_embedding) as similarity
  FROM web_search
  WHERE 1 - (web_search.embedding <=> query_embedding) > match_threshold
  ORDER BY web_search.date DESC,  -- Sort by date in descending order (newest first)
           web_search.embedding <=> query_embedding  -- Sort by similarity
  LIMIT match_count;  -- Limit the results to the match_count specified by the user
END;
$$;

CREATE TABLE web_search (
    id SERIAL PRIMARY KEY,
    text TEXT,
    metadata JSONB,
    embedding VECTOR(1024),

    -- This will be auto-updated
    date TIMESTAMP DEFAULT NOW()
);