llm-search

Querying local documents, powered by LLM

GitHub Stars

624

User Rating

Not Rated

Favorites

0

Views

60

Forks

67

Issues

6

Installation
Difficulty
Intermediate
Estimated Time
10-20 minutes
Requirements
Python 3.7 or higher
pip latest version

Installation

Installation

Prerequisites

Please specify required software and versions:
Python: 3.7 or higher
pip: Latest version

Installation Steps

1. Clone Repository

bash
git clone https://github.com/snexus/llm-search.git
cd llm-search

2. Install Dependencies

bash
pip install -r requirements.txt

3. Start Server

bash
python -m llm_search.server

Troubleshooting

Common Issues

Issue: Server won't start Solution: Check Python version and reinstall dependencies. Issue: Documents are not parsed correctly Solution: Verify that the document format is supported.

Configuration

Configuration

Basic Configuration

Create YAML Configuration File

Create a config.yaml file with the following settings:
yaml
llm:
  model: "openai"
  api_key: "your-api-key"
documents:
  folder: "path/to/documents"

Environment Variables

Set the following environment variables as needed:
bash
export API_KEY="your-api-key"

Advanced Configuration

Security Settings

Store API keys in environment variables or secure configuration files
Set appropriate file access permissions

Performance Tuning

Configure timeout values
Limit concurrent executions

Configuration Example

yaml
llm:
  model: "huggingface"
  api_key: "your-api-key"
documents:
  folder: "./data"

Examples

Examples

Basic Usage

Using in Jupyter Notebook

python
from llm_search import LLMSearch

search = LLMSearch(api_key="your-api-key")
results = search.query("specific question")
print(results)

Advanced Examples

Automation Script

bash
#!/bin/bash

Batch processing example

for file in *.txt; do llm-search process "$file" done

Use Cases

Searching an enterprise knowledge base to quickly retrieve relevant information
Parsing academic papers to answer questions on specific topics
Building a custom chatbot to provide context-based answers to user inquiries
Extracting specific procedures from PDF manuals to present to users

Additional Resources