Tagging
Tag and classify CSV data rows using large language models with parallel processing capabilities across multiple providers.
关于
This MCP server offers a powerful solution for rapidly classifying and tagging CSV data. It harnesses the `polar_llama` library to execute parallel LLM inference, making it incredibly efficient for batch classification tasks. Users can define custom taxonomies, from simple lists of categories to complex multi-dimensional structures, and leverage various LLM providers like Claude, OpenAI, Gemini, and Groq. The tool provides structured, type-safe outputs, complete with optional detailed reasoning, reflection, and confidence scores for each tag, ensuring transparency and reliability in data classification.
主要功能
- Parallel Processing: Tag hundreds or thousands of CSV rows concurrently
- Detailed Reasoning & Confidence Scores: Include confidence levels and explanations for tags
- Multiple LLM Providers: Support for Claude, OpenAI, Gemini, Groq, and Bedrock
- Flexible Taxonomy: Define custom tag lists or complex multi-field taxonomies
- Structured Output: Uses Pydantic models for consistent, type-safe results
- 0 GitHub stars
使用案例
- Batch classification of large CSV datasets for topic modeling or sentiment analysis
- Categorizing support tickets based on department, priority, and issue type
- Adding custom tags to product descriptions or customer feedback for improved searchability and analysis
Sponsored