4 results found Sort:

dissorial
doc-chatbot dissorial
134
796
unknown
12
Document chatbot — multiple files, topics, chat windows and chat history. Powered by GPT.
chat gpt-3 gpt-4 nextjs openai chatbot reactjs mongoose pinecone langchain openai-api typescript tailwindcss vectorization pdf-processing document-embedding
Created 2023-05-06
73 commits to master branch, last one about a year ago
allenai
papermage allenai
48
634
apache-2.0
9
library supporting NLP and CV research on scientific papers
python multimodal pdf-processing computer-vision machine-learning scientific-papers natural-language-processing
Created 2023-01-14
270 commits to main branch, last one 2 months ago
ahmedkhemiri95
PDFs-TextExtract ahmedkhemiri95
65
127
apache-2.0
7
Multiple and Large PDF Documents Text Extraction.
pdf pdfs parser pypdf2 python pdfminer data-science extract-text pdf-document pdf-processing text-analytics pdfs-textextract
Created 2020-05-07
41 commits to master branch, last one 4 months ago
aws-samples
document-processing-pipeline-for-regulated-industries aws-samples
13
59
apache-2.0
7
A boilerplate solution for processing image and PDF documents for regulated industries, with lineage and pipeline operations metadata services.
aws cdk aws-cdk amazon-s3 amazon-sns amazon-sqs aws-lambda data-lineage data-analytics pdf-processing amazon-dynamodb amazon-textract data-governance image-processing machine-learning amazon-comprehend amazon-web-services processing-pipelines image-processing-python amazon-elasticsearch-service
Created 2021-03-16
23 commits to main branch, last one 2 years ago