moritztng/fltr
Like grep but for natural language questions. Based on Mistral 7B or Mixtral 8x7B.
This tool helps you quickly filter large text files, like email archives or customer feedback, based on natural language questions. You input a text file and a question, and it outputs only the lines that match your query. It's ideal for anyone who needs to quickly sift through large amounts of text to find specific information without manually reading everything.
387 stars. No commits in the last 6 months.
Use this if you need to extract specific text snippets from a large document or dataset by asking a question, rather than using keyword searches.
Not ideal if you need to process text on devices with very limited memory or if you require extremely high processing speeds on standard consumer hardware.
Stars
387
Forks
8
Language
Rust
License
MIT
Category
Last pushed
Mar 13, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/moritztng/fltr"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
ludwig-ai/ludwig
Low-code framework for building custom LLMs, neural networks, and other AI models
withcatai/node-llama-cpp
Run AI models locally on your machine with node.js bindings for llama.cpp. Enforce a JSON schema...
mudler/LocalAI
:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and...
zhudotexe/kani
kani (カニ) is a highly hackable microframework for tool-calling language models. (NLP-OSS @ EMNLP 2023)
SciSharp/LLamaSharp
A C#/.NET library to run LLM (🦙LLaMA/LLaVA) on your local device efficiently.