LlamaIndex

An open-source Python framework for AI agents and document-based answers that connects your data to language models, including models served through Ollama.

LlamaIndex is a Python framework for developers building AI agents and applications that answer questions using their own data. It provides the connections and retrieval tools needed to give a language model relevant context from documents and other sources.

Data connections: Bring PDFs, documents, APIs and SQL data into an application through data connectors.
Indexes and retrieval: Organize material in indexes or graphs, then retrieve relevant context for model-generated answers.
Custom retrieval behavior: Adapt connectors, retrievers, query engines and reranking components to the needs of your application.
Model and app integration: Use models served through Ollama or connect the framework with application tools such as LangChain and Flask.
Document parsing integration: Use the separate LlamaParse service with the framework for complex document parsing, structured extraction and document agent workflows.

The framework is open source under the MIT license. Ollama support lets developers connect it to locally served models; data handling depends on the model and services the application uses.

LlamaParse is a separate platform that requires an account. It runs in LlamaIndex's cloud or in a customer's VPC, so its OCR and extraction capabilities aren't part of a standalone local framework deployment.