{"full_name":"run-llama/llama_index","owner":"run-llama","name":"llama_index","url":"https://github.com/run-llama/llama_index","description":"LlamaIndex is the document processing platform for AI","homepage":"https://developers.llamaindex.ai","topics":[],"language":"Python","license":"MIT","avatar":"https://avatars.githubusercontent.com/u/130722866?v=4","created_at":"2022-11-02T04:24:54Z","pushed_at":"2026-11-08T21:41:55Z","metrics":{"stars":52867,"forks":8540,"watchers":284,"issues":7499,"prs":10975,"releases":434,"issues_open":null,"issues_closed":null,"prs_open":null,"prs_closed":null,"prs_merged":null,"discussions":829},"growth":{"day":{"stars":13,"forks":8,"base_day":"2026-11-09"}},"history":{"dates":["2026-11-09","2026-11-10"],"stars":[52854,52867],"forks":[8532,8540],"watchers":[284,284],"issues_open":[null,null],"prs_open":[null,null]},"boards":{},"same_owner":[{"full_name":"run-llama/liteparse","name":"liteparse","boards":{}}],"issues":[{"number":19605,"title":"[Question]: Document Summary Index related issues","comments":42,"created_at":"2025-08-07T08:02:58Z"},{"number":19370,"title":"[Bug]: llama index Odata filter for azure ai search vector store is not filtering the chunks","comments":34,"created_at":"2025-07-09T07:06:05Z"},{"number":20386,"title":"[Feature Request]: Deterministic tool I/O pre/post-processing (middleware/hooks) for agents (MCP motivating case)","comments":33,"created_at":"2025-12-17T21:15:25Z"},{"number":23122,"title":"Integration proposal: memory store with verified transfer — export/import sealed memory bundles","comments":26,"created_at":"2026-09-18T14:19:36Z"},{"number":21666,"title":"[Feature Request]: Memory poisoning defense (OWASP ASI06) integration for agent memory stores","comments":25,"created_at":"2026-05-14T18:13:26Z"},{"number":21312,"title":"[Feature Request]: Trust scoring and interaction history for tool and agent reliability","comments":24,"created_at":"2026-04-05T21:39:46Z"},{"number":21601,"title":"Proposal: Agent Threat Rules detection integration for LlamaIndex","comments":21,"created_at":"2026-05-09T16:07:54Z"},{"number":17105,"title":"[Bug]: MultiModalLLMCompletionProgram (Ollama:Llava) raises AttributeError: 'GenerateResponse' object has no attribute 'items'","comments":17,"created_at":"2024-11-29T14:09:55Z"}],"discussions":[{"number":24048,"title":"Matching a human response versus authorizing an effect: ARQUIA-EVAL-001","comments":0,"category":"Show and tell","created_at":"2026-11-07T01:29:05Z"},{"number":23918,"title":"Usage graph filter by API key","comments":0,"category":"Ideas","created_at":"2026-11-03T15:36:44Z"},{"number":23878,"title":"ArtiGram: a remote MCP server for publishing and searching AI-made interactive pages","comments":0,"category":"Show and tell","created_at":"2026-11-01T20:20:05Z"},{"number":23869,"title":"Apizie Finance: Remote MCP and official-source data layer (SEC EDGAR, FRED, ECB)","comments":0,"category":"Show and tell","created_at":"2026-11-01T07:38:02Z"},{"number":23775,"title":"BotQuests MCP tools in a LlamaIndex agent","comments":0,"category":"Show and tell","created_at":"2026-10-28T20:01:00Z"},{"number":23765,"title":"Carbon Forge as an MCP tool for LlamaIndex agents: one versioned record for code and docs","comments":0,"category":"Show and tell","created_at":"2026-10-28T09:48:44Z"},{"number":23760,"title":"OpenAILike for OpenAI-compatible gateways: the two flags that matter (is_chat_model, is_function_calling_model) and the errors you get without them","comments":0,"category":"Show and tell","created_at":"2026-10-28T03:23:23Z"},{"number":23751,"title":"VynelixAI Agent Studio: An Open-Source Visual Builder for AI and Data Workflows","comments":0,"category":"Show and tell","created_at":"2026-10-27T09:47:19Z"}],"latest_release":{"name":"v0.14.25","tag":"v0.14.25","published_at":"2026-09-21T16:22:27Z","body":"# Release Notes\n\n## [2026-09-21]\n\n### llama-index-agent-agentmesh [0.3.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-agent-azure [0.4.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-argilla [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-arize-phoenix [0.8.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-honeyhive [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-langfuse [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-literalai [1.5.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-openinference [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-opik [1.4.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-promptlayer [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-uptrain [0.7.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-callbacks-wandb [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-core [0.14.25]\n\n- Remove deprecated ipex-llm and optimum-intel IPEX integrations ([#22406](https://github.com/run-llama/llama_index/pull/22406))\n- fix(core): fall back when metadata replacement target value is None ([#22773](https://github.com/run-llama/llama_index/pull/22773))\n- test(core): cover empty arguments in streamed tool calls ([#22825](https://github.com/run-llama/llama_index/pull/22825))\n- Fix: restore compact and refine streaming ([#22836](https://github.com/run-llama/llama_index/pull/22836))\n- fix(core): avoid retrying failed function tools ([#22841](https://github.com/run-llama/llama_index/pull/22841))\n- feat(core): add native async support to StructuredLLMRerank ([#22842](https://github.com/run-llama/llama_index/pull/22842))\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-embeddings-adapter [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-embeddings-alephalpha [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-embeddings-alibabacloud-aisearch [0.5.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n- chore: re-lock the 93 manifests with stuck Dependabot alerts ([#22921](https://github.com/run-llama/llama_index/pull/22921))\n\n### llama-index-embeddings-anyscale [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n\n### llama-index-embeddings-autoembeddings [0.4.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n- chore: re-lock the 93 manifests with stuck Dependabot alerts ([#22921](https://github.com/run-llama/llama_index/pull/22921))\n\n### llama-index-embeddings-azure-inference [0.6.0]\n\n- fix: resolve a ton of security alerts ([#22855](https://github.com/run-llama/llama_index/pull/22855))\n- chore: re-lock the 93 manifests with stuck Dependabot alerts ([#22921](https://github.com/run-llama/llama_index/pull/22921))\n\n###"},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-10T09:35:25Z","history_start":"2026-09-06"}