Data Parsing tools

LLMSherpa

LLM Sherpa provides strategic APIs to accelerate large language model (LLM) use cases. (It's free)

• https://github.com/nlmatics/llmsherpa

DeepSearch

Deep Search leverages state-of-the-art AI methods to continuously collect, convert, enrich, and link large document collections. You can use it for both public and proprietary PDF documents. (Its NOT free, but there is a free plan)

• https://ds4sd.github.io

LlamaParse

LlamaParse is an API created by LlamaIndex to efficiently parse and represent files for efficient retrieval and context augmentation using LlamaIndex frameworks. (Its NOT free, but there is a free plan with 1000 pages / day)

• https://github.com/run-llama/llama_parse

Llama Hub

Our integrations include utilities such as Data Loaders, Agent Tools, Llama Packs, and Llama Datasets. We make it extremely easy to connect large language models to a large variety of knowledge & data sources. Use these utilities with a framework of your choice such as LlamaIndex, LangChain, and more.

• https://llamahub.ai

LangChain Documents Loader & Splitter

LangChain has a number of built-in document transformers that make it easy to split, combine, filter, and otherwise manipulate documents.

• https://python.langchain.com/docs/modules/data_connection/document_transformers/
• https://python.langchain.com/docs/modules/data_connection/document_loaders/