{"data":{"slug":"run-llama-llama-index","name":"llama_index","tagline":"Document processing platform for AI","github_url":"https://github.com/run-llama/llama_index","owner":"run-llama","repo":"llama_index","owner_avatar_url":"https://avatars.githubusercontent.com/u/130722866?v=4","primary_language":"Python","stars":52207,"forks":8167,"topics":["agents","application","data","fine-tuning","framework","llamaindex","llm","multi-agents","rag","vector-database"],"archived":false,"github_pushed_at":"2026-09-18T04:10:58+00:00","maintenance_label":"Very active","stars_delta_30d":765,"url":"https://www.graphcanon.com/tools/run-llama-llama-index","markdown_url":"https://www.graphcanon.com/tools/run-llama-llama-index.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/run-llama-llama-index","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=run-llama-llama-index","description":"LlamaIndex is the document processing platform for AI","homepage_url":"https://developers.llamaindex.ai","license":"MIT","open_issues":802,"watchers":287,"ai_summary":"LlamaIndex is an open-source framework for building AI-powered document processing applications, including RAG and agent applications.","readme_excerpt":"# 🗂️ LlamaIndex (OSS Framework) 🦙\n\n\n\n\n\n\n\n\n> [!NOTE]\n> The current focus of LlamaIndex is to build the best AI-powered engine for document parsing and extraction. **[LlamaParse](https://cloud.llamaindex.ai?utm_medium=li_github&utm_source=github&utm_campaign=2026--)** is our enterprise platform for agentic OCR, parsing, extraction, indexing and more. [LiteParse](https://github.com/run-llama/liteparse) represents our efforts to build the best free, fast, cheap text parser in the market. [ParseBench](https://www.parsebench.ai/) and [ExtractBench](https://www.extractbench.ai/) represent our commitment towards open benchmarking for parsing and extraction.\n>\n> The company itself has undergone an evolution since when this OSS framework first launched 3 years ago in 2023. Since the early days, the framework has consisted of a broad set of orchestration tools enabling developers to build various RAG and agent applications.\n>\n> While we still have the OSS framework available as an open toolkit that you're welcome to use, our primary focus has shifted towards LlamaParse, along with liteparse and our benchmarking efforts. We have a strong belief that agents are the new consumers of documents, and they fundamentally need the right tools to unlock context from the world's hardest documents accurately/cheaply at scale. Whether you're an AI startup processing documents or an enterprise looking to automate document workflows, [come talk to us](https://www.llamaindex.ai/contact).\n\nLlamaIndex OSS (by [LlamaIndex](https://llamaindex.ai?utm_medium=li_github&utm_source=github&utm_campaign=2026--)) is an open-source framework to build agentic applications. You can use LlamaParse with this framework or on its own; see [LlamaParse](#llamacloud-document-agent-platform) below for signup and product links.\n\n> ### 📚 **Documentation:**\n>\n> - [LlamaParse](https://developers.llamaindex.ai/python/cloud/llamaparse/?utm_medium=li_github&utm_source=github&utm_campaign=2026--)\n> - [LlamaIndex OSS](https://developers.llamaindex.ai/python/framework/?utm_medium=li_github&utm_source=github&utm_campaign=2026--)\n> - [LlamaAgents](https://developers.llamaindex.ai/python/llamaagents/overview/?utm_medium=li_github&utm_source=github&utm_campaign=2026--)\n\nBuilding with LlamaIndex typically involves working with LlamaIndex core and a chosen set of integrations (or plugins). There are two ways to start building with LlamaIndex in\nPython:\n\n1. **Starter**: [`llama-index`](https://pypi.org/project/llama-index/). A starter Python package that includes core LlamaIndex as well as a selection of integrations.\n\n2. **Customized**: [`llama-index-core`](https://pypi.org/project/llama-index-core/). Install core LlamaIndex and add your chosen LlamaIndex integration packages from the [integrations page](https://developers.llamaindex.ai/python/framework/community/integrations)\n   that are required for your application. There are over 300 LlamaIndex integration\n   packages that work seamlessly with core, allowing you to build with your preferred\n   LLM, embedding, and vector store providers.\n\nThe LlamaIndex Python library is namespaced such that import statements which\ninclude `core` imply that the core package is being used. In contrast, those\nstatements without `core` imply that an integration package is being used.\n\n```python\n# typical pattern\nfrom llama_index.core.xxx import ClassABC  # core submodule xxx\nfrom llama_index.xxx.yyy import (\n    SubclassABC,\n)  # integration yyy for submodule xxx\n\n# concrete example\nfrom llama_index.core.llms import LLM\nfrom llama_index.llms.openai import OpenAI\n```\n\n### LlamaParse (document agent platform)\n\n**LlamaParse** is its own platform—focused on document agents and agentic OCR. It includes **Parse** (parsing), **LlamaAgents** (deployed document agents), **Extract** (structured extraction), and **Index** (ingest and RAG). You can use it with the LlamaIndex framework or standalone.\n\n- **[Sign up for LlamaParse](https://cloud.llamaindex.ai?utm_medium","github_created_at":"2022-11-02T04:24:54+00:00","created_at":"2026-07-07T15:07:50.616901+00:00","updated_at":"2026-09-30T18:34:53.84419+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"developer-tools","name":"Developer Tools","url":"https://www.graphcanon.com/categories/developer-tools","markdown_url":"https://www.graphcanon.com/categories/developer-tools.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/developer-tools"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"agents","name":"agents"},{"slug":"application","name":"application"},{"slug":"data","name":"data"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"framework","name":"framework"},{"slug":"llamaindex","name":"llamaindex"},{"slug":"llm","name":"llm"},{"slug":"multi-agents","name":"multi-agents"}],"trust":{"provenance":{"is_fork":false,"github_id":560704231,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:26:55.628Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":0,"last_release_at":"2026-08-19T18:48:01Z","stars_delta_30d":765,"open_issues_delta_30d":187},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:26:58.073Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:26:54.555Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-09-18T08:26:54.555Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-09-18T08:26:54.555Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need a framework that focuses on document parsing and extraction, as LlamaIndex has evolved to prioritize these capabilities","If you are working on RAG and agent applications and require a broad set of orchestration tools","When you prefer to use an open-source toolkit that integrates with over 300 different packages for various LLM, embedding, and vector store providers"],"when_not_to_use":["If your project requires enterprise-level features such as agentic OCR, as LlamaIndex's primary focus has shifted towards LlamaParse, an enterprise platform","When you need a tool that is actively developed and maintained as the primary focus of the company has shifted towards LlamaParse and LiteParse, and the OSS framework is now a secondary focus"],"source":"enrich:decision_facts","observed_at":"2026-09-18T11:45:59.673Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"LlamaIndex is an open-source framework for building AI-powered document processing applications, including RAG and agent applications, with a focus on document parsing and extraction. It offers over 300 integration packs"}]}}