icaropires / pdf2dataset
Converts a whole subdirectory with a big (or small) volume of PDF documents to a dataset (pandas DataFrame) with error tracking and choice of features
☆19Updated 4 years ago
Related projects: ⓘ
- 📃 A contracts clause summarization system using LLM and vector database☆11Updated 6 months ago
- Python toolbox to load, parse and process Official Journals of the European Union (EU).☆13Updated 4 months ago
- GPT-3.5-trubo + Harvard's Case Access Project☆14Updated last year
- A Python package to get useful information from documents using TopicRank Algorithm.☆16Updated last year
- This is a tutorial I made on how to deploy a HuggingFace/LangChain pipeline on the newly released Falcon 7B LLM by TII☆10Updated last year
- LangChain Baby AGI integrated as a Web App using Databutton☆15Updated last year
- A simple web application for searching Word2Vec embeddings derived from approximately 2,000 law reports published by the The Incorporated…☆25Updated last year
- Named entity recognition for the legal domain☆40Updated 3 years ago
- A framework for converting natural language text inputs to corresponding Pandas, MongoDB, Kusto and Neo4j (Cypher) queries.☆66Updated 4 months ago
- A web app built with Streamlit that summarizes input text☆13Updated 3 years ago
- This repository serves as a collection of scrapers procuring and structuring various legal datasets☆15Updated last year
- ☆22Updated 3 years ago
- Chat Complex PDF with Tables Using IBM WatsonX, Langchain and LlamaParser.☆10Updated 5 months ago
- Create a local dashboard to visualize and filter your GitHub feed☆29Updated 2 years ago
- A simple tool that serves as a knowledge graph explorer utilizing the GPT 3.5 turbo model to help users explore information in an organiz…☆56Updated 2 weeks ago
- A python package that provides a custom streamlit connection to query data from weaviate, the AI native vector database☆49Updated last month
- Web application that allows you to interact with biomedical knowledge graphs and query biomedical questions.☆29Updated last year
- End to End MLOps☆10Updated 3 years ago
- A chatbot made using the Chatterbot library in Python and locally hosted using Streamlit. Dataset used were collected during ConvAI2 comp…☆13Updated 3 years ago
- This is an application that automates the process of text analysis with a user-friendly GUI. 📱 It has been implemented using Python and …☆34Updated 2 years ago
- Opennyai : An efficient NLP Pipeline for Indian Legal documents☆65Updated 4 months ago
- AI + Legal APIs: A Tool-Based Retrieval Augmented Generation Workbench for Legal AI UX Research.☆36Updated 4 months ago
- Code for DELSumm, an unsupervised summarization algorithm for legal case judgements.☆23Updated last year
- A simple search engine to search medium stories built with streamlit and elasticsearch.☆40Updated 2 years ago
- A Python pipeline tool and plugin ecosystem for processing technical documents. Process papers from arXiv, SemanticScholar, PDF, with GRO…☆41Updated last month
- Upload an image of a document and extract text, names, facts and figures☆21Updated last month
- Pipeline to extract candidates information from PDF resumes (CVs) using OCR and ChatGPT (GPT-3.5 & GPT-4)☆40Updated last year
- ☆16Updated last year
- Utils to train and evaluate sentence transformers models (using Spanish datasets)☆9Updated 3 months ago
- streamlit dashboard to analyse data☆10Updated last year