SearchMind: A Python Client for Snapzion Search

A simple Python client for the Snapzion Search API.

SearchMind is a lightweight wrapper that makes it easy to fetch search results and format them for use in other applications, especially for providing real-time web context to Large Language Models (LLMs) like those from OpenAI.

Features

• Simple and intuitive API: client.search("your query").
• Built-in helper to format results into a clean string for LLM prompts.
• Uses requests.Session for efficient connection pooling.
• Proper error handling with custom SearchMindError exceptions.
• Fully type-hinted for better editor support and code quality.

Installation

pip install searchmind

Quick Start

Getting search results is straightforward.

from searchmind import SearchMindClient, SearchMindError

# 1. Initialize the client
client = SearchMindClient()

# 2. Perform a search
try:
    results = client.search("latest trends in renewable energy")
    
    # The result is a list of dictionaries
    for item in results:
        print(f"[{item['position']}] {item['title']}")
        print(f"   Link: {item['link']}\n")

except SearchMindError as e:
    print(f"An error occurred: {e}")

Usage with LLMs (e.g., OpenAI API)

The primary goal of this library is to act as a web search tool for LLMs. The format_for_llm utility creates a perfectly formatted context string.

from searchmind import SearchMindClient, format_for_llm, APIError
# from openai import OpenAI # Hypothetical usage

# 1. Initialize the SearchMind client
search_client = SearchMindClient()

# 2. Define your query
user_query = "What are the main AI trends for 2025 according to recent articles?"

# 3. Get search results
try:
    print(f"Searching for: '{user_query}'...")
    search_results = search_client.search(user_query)

    # 4. Format the results into a single string for the LLM
    search_context = format_for_llm(search_results)

    print("\n--- Formatted Context for LLM ---\n")
    print(search_context)
    
    # 5. Use the context in a prompt to an LLM
    # client = OpenAI(api_key="your-openai-key")
    #
    # response = client.chat.completions.create(
    #   model="gpt-4o",
    #   messages=[
    #     {"role": "system", "content": "You are a helpful assistant. Answer the user's question based *only* on the provided search context. Cite your sources using the [number] and URL."},
    #     {"role": "user", "content": f"Question: {user_query}\n\nSearch Context:\n---\n{search_context}\n---"}
    #   ]
    # )
    #
    # print("\n--- LLM Response ---\n")
    # print(response.choices[0].message.content)

except APIError as e:
    print(f"An error occurred while searching: {e}")

Contributing

Contributions are welcome! Please open an issue or submit a pull request on our GitHub repository.

License

This project is licensed under the MIT License.