geeks-of-data/knowledge-gpt
Extract knowledge from all information sources using gpt and other language models. Index and make Q&A session with information sources.
This tool helps you quickly get answers to your questions by drawing information from various sources like websites, PDFs, PowerPoint files, and even YouTube videos. You provide your documents or links and ask a question, and it gives you a concise answer. This is ideal for researchers, analysts, or anyone who needs to synthesize information from multiple resources without manually sifting through each one.
291 stars. No commits in the last 6 months.
Use this if you need to rapidly extract specific answers from a collection of diverse documents, web pages, or video transcripts without extensive manual review.
Not ideal if you require a human-level understanding for nuanced interpretation or if the accuracy of the answer is critical without independent verification.
Stars
291
Forks
54
Language
Python
License
MIT
Category
Last pushed
Apr 25, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/geeks-of-data/knowledge-gpt"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
rasbt/LLMs-from-scratch
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
facebookresearch/LayerSkip
Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024
FareedKhan-dev/train-llm-from-scratch
A straightforward method for training your LLM, from downloading data to generating text.
kmeng01/rome
Locating and editing factual associations in GPT (NeurIPS 2022)
datawhalechina/llms-from-scratch-cn
仅需Python基础，从0构建大语言模型；从0逐步构建GLM4\Llama3\RWKV6， 深入理解大模型原理