ProTaska-GPT
parsee-datasets
| ProTaska-GPT | parsee-datasets | |
|---|---|---|
| 1 | 2 | |
| 2 | 61 | |
| - | - | |
| 7.2 | 6.4 | |
| 9 months ago | 4 days ago | |
| Jupyter Notebook | Jupyter Notebook | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
ProTaska-GPT
parsee-datasets
-
FinRAG Datasets and Study
To test this, we created 3 different datasets, all based on the same selection of 1,156 randomly selected annual reports for the year 2023 of publicly listed US companies.
The resulting (fully labeled) datasets contain a combined total of 10,404 rows, 37,536,847 tokens and 1,156 images and can be found on Github and Huggingface: https://github.com/parsee-ai/parsee-datasets/tree/main/datas...
For our study, we are evaluating 8 state-of-the-art (M)LLMs on a subset of 100 reports with some interesting results.
-
Parsee.ai – a framework to easily extract complex structured data with LLMs
Yes, another LLM framework. This one is specialized on extracting structured data from various document types (mainly PDFs, images and HTML files).
Comes with a new (separate) PDF extraction library that is focused on the extraction of numeric tables (tables with numbers, so especially for the financial domain): https://github.com/parsee-ai/parsee-pdf-reader
Helps to easily set up a dataset to evaluate the performance of various LLMs on data extraction tasks, e.g. extracting revenue figures from financial reports: https://github.com/parsee-ai/parsee-datasets/tree/main/datas...
What are some alternatives?
TLDR-the-TnC - TLDR the T&C uses an LLM to understand the contents of Terms and Conditions documents and provides a user-friendly chatbot interface for users to ask questions and receive answers.
tiger - Open Source LLM toolkit to build trustworthy LLM applications. TigerArmor (AI safety), TigerRAG (embedding, RAG), TigerTune (fine-tuning)
voxelgpt - AI assistant that can query visual datasets, search the FiftyOne docs, and answer general computer vision questions
LangChain-SynData-RAG-Eval - LangChain, Llama2-Chat, and zero- and few-shot prompting are used to generate synthetic datasets for IR and RAG system evaluation
LlamaIndex-course - Learn to build and deploy AI apps.
llm-chatbot-rag - A local LLM chatbot with RAG for PDF input files
Human-pose-estimation - A quick tutorial on multi-pose estimation with OpenCV, Tensorflow and MoveNet lightning.
instinct.cpp - instinct.cpp provides ready to use alternatives to OpenAI Assistant API and built-in utilities for developing AI Agent applications (RAG, Chatbot, Code interpreter) powered by language models. Call it langchain.cpp if you like.
langchain-course - Learn to build and deploy AI apps.
langchain-tutorials - Overview and tutorial of the LangChain Library
cinemattr-db - Backend of cinemattr.ca
Roy - Roy: A lightweight, model-agnostic framework for crafting advanced multi-agent systems using large language models.