A few weeks ago, we stealth launched SEC Insights on Product Hunt and were thrilled to reach the top 5!
What is SEC Insights? It harnesses the Retrieval Augmented Generation (RAG) capabilities of LlamaIndex to provide answers about SEC 10-K & 10-Q documents. The enthusiastic reception we received on Product Hunt prompted us to open-source our project. Now, developers can use our project either as a reference or they can fork it entirely for their LLM-powered applications.
We at LlamaIndex built this to help developers move their LLM app ideas from prototype to production. We're very open to feedback, Github issues, and PRs!
Also, keep an eye on our YouTube page for a walkthrough and setup tutorial we have in the works!
https://www.youtube.com/@LlamaIndex"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Show HN: secinsights.ai \u2013 An open-source full-stack app using LlamaIndex"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/run-llama/sec-insights"}},"_tags":["story","author_secsamai","story_37407918","show_hn"],"author":"secsamai","created_at":"2023-09-06T17:07:43Z","created_at_i":1694020063,"num_comments":0,"objectID":"37407918","points":7,"story_id":37407918,"story_text":"Hi HN,
A few weeks ago, we stealth launched SEC Insights on Product Hunt and were thrilled to reach the top 5!
What is SEC Insights? It harnesses the Retrieval Augmented Generation (RAG) capabilities of LlamaIndex to provide answers about SEC 10-K & 10-Q documents. The enthusiastic reception we received on Product Hunt prompted us to open-source our project. Now, developers can use our project either as a reference or they can fork it entirely for their LLM-powered applications.
We at LlamaIndex built this to help developers move their LLM app ideas from prototype to production. We're very open to feedback, Github issues, and PRs!
Also, keep an eye on our YouTube page for a walkthrough and setup tutorial we have in the works!
https://www.youtube.com/@LlamaIndex","title":"Show HN: secinsights.ai \u2013 An open-source full-stack app using LlamaIndex","updated_at":"2024-09-20T14:57:39Z","url":"https://github.com/run-llama/sec-insights"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"pqn"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"LlamaIndex adds private data to large language models"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://techcrunch.com/2023/06/06/llamaindex-adds-private-data-to-large-language-models/"}},"_tags":["story","author_pqn","story_36215589"],"author":"pqn","created_at":"2023-06-06T16:46:17Z","created_at_i":1686069977,"num_comments":0,"objectID":"36215589","points":7,"story_id":36215589,"title":"LlamaIndex adds private data to large language models","updated_at":"2024-09-20T14:10:58Z","url":"https://techcrunch.com/2023/06/06/llamaindex-adds-private-data-to-large-language-models/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"marcklingen"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"OSS Decorator to Trace LLM Apps \u2013 Integrated with LlamaIndex, LangChain, OAI SDK"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://langfuse.com/blog/2024-04-python-decorator"}},"_tags":["story","author_marcklingen","story_40157248"],"author":"marcklingen","created_at":"2024-04-25T13:23:36Z","created_at_i":1714051416,"num_comments":0,"objectID":"40157248","points":6,"story_id":40157248,"title":"OSS Decorator to Trace LLM Apps \u2013 Integrated with LlamaIndex, LangChain, OAI SDK","updated_at":"2024-09-20T16:54:05Z","url":"https://langfuse.com/blog/2024-04-python-decorator"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"gerad"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"LlamaIndex: Data Agents"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://medium.com/llamaindex-blog/data-agents-eed797d7972f"}},"_tags":["story","author_gerad","story_37037407"],"author":"gerad","created_at":"2023-08-07T17:12:40Z","created_at_i":1691428360,"num_comments":0,"objectID":"37037407","points":6,"story_id":37037407,"title":"LlamaIndex: Data Agents","updated_at":"2024-09-20T14:48:44Z","url":"https://medium.com/llamaindex-blog/data-agents-eed797d7972f"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ashikshaffi0"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"A few weeks ago I got rejected from a role and the feedback was that I needed a deeper understanding of FAISS and LlamaIndex.
So I built triage.flow \u2014 an AI assistant that lets you explore and understand GitHub repositories through a chat interface.
It clones a repo, indexes it using FAISS + BM25 + tree-sitter parsing, and powers a full UI where you can:
- Ask natural-language questions like \u201chow does auth work?\u201d or \u201cexplain @src/components/Modal.tsx\u201d\n\n - Mention specific files/folders with @filename.ts (autocomplete supported)\n\n - See how the agent thinks in real time (Thought \u2192 Action \u2192 Observation)\n\n - View retrieved code side-by-side with the chat\nGitHub: https://github.com/ashikshafi08/triage.flow
Would love feedback or thoughts from anyone building similar tools.
(Also exploring new opportunities \u2014 open to roles around LLM infra, RAG, or applied ML.)"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Show HN: Triage.flow \u2013 Chat with Any GitHub Repo Using Faiss and LlamaIndex"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/ashikshafi08/triage.flow"}},"_tags":["story","author_ashikshaffi0","story_44186380","show_hn"],"author":"ashikshaffi0","children":[44208907],"created_at":"2025-06-04T22:48:13Z","created_at_i":1749077293,"num_comments":1,"objectID":"44186380","points":5,"story_id":44186380,"story_text":"A few weeks ago I got rejected from a role and the feedback was that I needed a deeper understanding of FAISS and LlamaIndex.
So I built triage.flow \u2014 an AI assistant that lets you explore and understand GitHub repositories through a chat interface.
It clones a repo, indexes it using FAISS + BM25 + tree-sitter parsing, and powers a full UI where you can:
- Ask natural-language questions like \u201chow does auth work?\u201d or \u201cexplain @src/components/Modal.tsx\u201d\n\n - Mention specific files/folders with @filename.ts (autocomplete supported)\n\n - See how the agent thinks in real time (Thought \u2192 Action \u2192 Observation)\n\n - View retrieved code side-by-side with the chat\nGitHub: https://github.com/ashikshafi08/triage.flow
Would love feedback or thoughts from anyone building similar tools.
(Also exploring new opportunities \u2014 open to roles around LLM infra, RAG, or applied ML.)","title":"Show HN: Triage.flow \u2013 Chat with Any GitHub Repo Using Faiss and LlamaIndex","updated_at":"2025-06-07T11:18:16Z","url":"https://github.com/ashikshafi08/triage.flow"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"SimFG"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"How GPTCache works with llama index"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/zilliztech/GPTCache"}},"_tags":["story","author_SimFG","story_36026705"],"author":"SimFG","children":[36026706],"created_at":"2023-05-22T02:18:05Z","created_at_i":1684721885,"num_comments":1,"objectID":"36026705","points":5,"story_id":36026705,"title":"How GPTCache works with llama index","updated_at":"2024-09-20T14:09:29Z","url":"https://github.com/zilliztech/GPTCache"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"sabrina_ramonov"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Advanced RAG Cheat Sheet from LlamaIndex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://www.llamaindex.ai/blog/a-cheat-sheet-and-some-recipes-for-building-advanced-rag-803a9d94c41b"}},"_tags":["story","author_sabrina_ramonov","story_40486617"],"author":"sabrina_ramonov","created_at":"2024-05-27T00:42:35Z","created_at_i":1716770555,"num_comments":0,"objectID":"40486617","points":5,"story_id":40486617,"title":"Advanced RAG Cheat Sheet from LlamaIndex","updated_at":"2024-09-20T17:08:36Z","url":"https://www.llamaindex.ai/blog/a-cheat-sheet-and-some-recipes-for-building-advanced-rag-803a9d94c41b"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"T-A"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Nvidia and LlamaIndex Developer Contest"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://developer.nvidia.com/llamaindex-developer-contest"}},"_tags":["story","author_T-A","story_41443590"],"author":"T-A","children":[41444943],"created_at":"2024-09-04T09:24:49Z","created_at_i":1725441889,"num_comments":0,"objectID":"41443590","points":4,"story_id":41443590,"title":"Nvidia and LlamaIndex Developer Contest","updated_at":"2024-09-20T17:44:59Z","url":"https://developer.nvidia.com/llamaindex-developer-contest"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"9woc"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Mass document analytics platform based on LlamaIndex, Pgvector, React and Django"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/JSv4/OpenContracts"}},"_tags":["story","author_9woc","story_40875450"],"author":"9woc","created_at":"2024-07-04T14:55:58Z","created_at_i":1720104958,"num_comments":0,"objectID":"40875450","points":4,"story_id":40875450,"title":"Mass document analytics platform based on LlamaIndex, Pgvector, React and Django","updated_at":"2024-09-20T17:25:48Z","url":"https://github.com/JSv4/OpenContracts"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"chkelly9"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Building a Chatbot for HN and Stack Overflow with LlamaIndex and ClickHouse"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://clickhouse.com/blog/building-hackernews-stackoverflow-chatbot-with-llamaindex-and-clickhouse"}},"_tags":["story","author_chkelly9","story_39551324"],"author":"chkelly9","created_at":"2024-02-29T16:16:58Z","created_at_i":1709223418,"num_comments":0,"objectID":"39551324","points":4,"story_id":39551324,"title":"Building a Chatbot for HN and Stack Overflow with LlamaIndex and ClickHouse","updated_at":"2024-09-20T16:30:04Z","url":"https://clickhouse.com/blog/building-hackernews-stackoverflow-chatbot-with-llamaindex-and-clickhouse"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"cheptsov"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Rag with Llama Index and Weaviate, running LLMs in your preferred cloud"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://dstack.ai/examples/llama-index-weaviate/"}},"_tags":["story","author_cheptsov","story_37584702"],"author":"cheptsov","created_at":"2023-09-20T14:35:47Z","created_at_i":1695220547,"num_comments":0,"objectID":"37584702","points":4,"story_id":37584702,"title":"Rag with Llama Index and Weaviate, running LLMs in your preferred cloud","updated_at":"2024-09-20T15:15:26Z","url":"https://dstack.ai/examples/llama-index-weaviate/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Brajeshwar"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"LlamaIndex is a data framework for your LLM applications"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/run-llama/llama_index"}},"_tags":["story","author_Brajeshwar","story_39853078"],"author":"Brajeshwar","created_at":"2024-03-28T15:55:10Z","created_at_i":1711641310,"num_comments":0,"objectID":"39853078","points":3,"story_id":39853078,"title":"LlamaIndex is a data framework for your LLM applications","updated_at":"2024-09-20T16:42:24Z","url":"https://github.com/run-llama/llama_index"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tosh"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Running Mixtral 8x7 locally with LlamaIndex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://blog.llamaindex.ai/running-mixtral-8x7-locally-with-llamaindex-e6cebeabe0ab"}},"_tags":["story","author_tosh","story_38737693"],"author":"tosh","created_at":"2023-12-22T19:32:57Z","created_at_i":1703273577,"num_comments":0,"objectID":"38737693","points":3,"story_id":38737693,"title":"Running Mixtral 8x7 locally with LlamaIndex","updated_at":"2024-09-20T15:59:15Z","url":"https://blog.llamaindex.ai/running-mixtral-8x7-locally-with-llamaindex-e6cebeabe0ab"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"yding"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"This was mostly a nights and weekends project for the last 6 weeks. Porting LlamaIndex to TS was a lot of fun, and my first real NPM library, so hope people find it useful."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Show HN: LlamaIndex.TS"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://medium.com/llamaindex-blog/introducing-llamaindex-ts-89f41a1f24ab"}},"_tags":["story","author_yding","story_36873841","show_hn"],"author":"yding","created_at":"2023-07-26T06:36:46Z","created_at_i":1690353406,"num_comments":0,"objectID":"36873841","points":3,"story_id":36873841,"story_text":"This was mostly a nights and weekends project for the last 6 weeks. Porting LlamaIndex to TS was a lot of fun, and my first real NPM library, so hope people find it useful.","title":"Show HN: LlamaIndex.TS","updated_at":"2024-09-20T14:41:02Z","url":"https://medium.com/llamaindex-blog/introducing-llamaindex-ts-89f41a1f24ab"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"yujian"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Multi-Document Q/a with LlamaIndex, LangChain, and Milvus"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://colab.research.google.com/drive/10vhji3FPOAm43zAvjOF4dlgxAeqIkHDx"}},"_tags":["story","author_yujian","story_36263968"],"author":"yujian","created_at":"2023-06-09T20:48:06Z","created_at_i":1686343686,"num_comments":0,"objectID":"36263968","points":3,"story_id":36263968,"title":"Multi-Document Q/a with LlamaIndex, LangChain, and Milvus","updated_at":"2024-09-20T14:16:26Z","url":"https://colab.research.google.com/drive/10vhji3FPOAm43zAvjOF4dlgxAeqIkHDx"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"fzliu"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"LlamaIndex Raises $8.5M"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://www.businesswire.com/news/home/20230531005251/en/LlamaIndex-Raises-8.5M-to-Unlock-Large-Language-Models-Capabilities-with-Personal-Data"}},"_tags":["story","author_fzliu","story_36218203"],"author":"fzliu","children":[36218232],"created_at":"2023-06-06T19:50:02Z","created_at_i":1686081002,"num_comments":0,"objectID":"36218203","points":3,"story_id":36218203,"title":"LlamaIndex Raises $8.5M","updated_at":"2024-09-20T14:11:19Z","url":"https://www.businesswire.com/news/home/20230531005251/en/LlamaIndex-Raises-8.5M-to-Unlock-Large-Language-Models-Capabilities-with-Personal-Data"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"yujian"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Persistent Vector Storage for LlamaIndex"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://www.youtube.com/watch?v=S4GmdrlqVKc"}},"_tags":["story","author_yujian","story_36216831"],"author":"yujian","created_at":"2023-06-06T18:10:03Z","created_at_i":1686075003,"num_comments":0,"objectID":"36216831","points":3,"story_id":36216831,"title":"Persistent Vector Storage for LlamaIndex","updated_at":"2024-09-20T14:11:05Z","url":"https://www.youtube.com/watch?v=S4GmdrlqVKc"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"manili"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"I'm curious to know, based on your experience in production, how much does Chain-of-Though Reasoning typically cost in terms of tokens for frameworks like LlamaIndex, LangChain, CrewAI, etc.?
I understand it depends on many different factors including the complexity of the product and the architecture of the agents involved, but I'd love to hear about your experiences in creating real-world-class application."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"How much does CoT Reasoning typically cost for frameworks like LlamaIndex?"}},"_tags":["story","author_manili","story_41538848","ask_hn"],"author":"manili","children":[41539834],"created_at":"2024-09-14T10:32:24Z","created_at_i":1726309944,"num_comments":4,"objectID":"41538848","points":2,"story_id":41538848,"story_text":"I'm curious to know, based on your experience in production, how much does Chain-of-Though Reasoning typically cost in terms of tokens for frameworks like LlamaIndex, LangChain, CrewAI, etc.?
I understand it depends on many different factors including the complexity of the product and the architecture of the agents involved, but I'd love to hear about your experiences in creating real-world-class application.","title":"How much does CoT Reasoning typically cost for frameworks like LlamaIndex?","updated_at":"2024-09-20T17:48:37Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"pinglin"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Ask HN: How do you deploy Python-based LangChain or LlamaIndex code on prod?"}},"_tags":["story","author_pinglin","story_41427135","ask_hn"],"author":"pinglin","children":[41431561],"created_at":"2024-09-02T17:16:46Z","created_at_i":1725297406,"num_comments":1,"objectID":"41427135","points":2,"story_id":41427135,"title":"Ask HN: How do you deploy Python-based LangChain or LlamaIndex code on prod?","updated_at":"2024-09-20T17:43:26Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Ephil012"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Hi all, I had been working with tools like LlamaIndex at work and realized that there were not many good options for monitoring RAG systems for performance. So I built a pretty simple Github Action + PyTest setup to measure the performance of LlamaIndex over time. The setup basically uses a library called Tonic Validate, which scores the quality of your RAG system\u2019s answers (Disclaimer: My current company made Tonic Validate and I am an engineer on Tonic Validate). Using Tonic Validate, it scores the responses from LlamaIndex on a set of test data I created and then uploads it to Tonic Validate\u2019s UI for visualization. If anyone is interested in it, you can find the full source code here [1]. I also wrote a guest blog post on LlamaIndex\u2019s blog about it here [2] if anyone wants more details about how it works.
1. https://github.com/TonicAI/llama-validate-demo
2. https://blog.llamaindex.ai/tonic-validate-x-llamaindex-implementing-integration-tests-for-llamaindex-43db50b76ed9"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Show HN: I Built a GitHub Action to Monitor LlamaIndex Performance"}},"_tags":["story","author_Ephil012","story_39147328","show_hn"],"author":"Ephil012","children":[39170231],"created_at":"2024-01-26T19:54:35Z","created_at_i":1706298875,"num_comments":1,"objectID":"39147328","points":2,"story_id":39147328,"story_text":"Hi all, I had been working with tools like LlamaIndex at work and realized that there were not many good options for monitoring RAG systems for performance. So I built a pretty simple Github Action + PyTest setup to measure the performance of LlamaIndex over time. The setup basically uses a library called Tonic Validate, which scores the quality of your RAG system\u2019s answers (Disclaimer: My current company made Tonic Validate and I am an engineer on Tonic Validate). Using Tonic Validate, it scores the responses from LlamaIndex on a set of test data I created and then uploads it to Tonic Validate\u2019s UI for visualization. If anyone is interested in it, you can find the full source code here [1]. I also wrote a guest blog post on LlamaIndex\u2019s blog about it here [2] if anyone wants more details about how it works.
1. https://github.com/TonicAI/llama-validate-demo
2. https://blog.llamaindex.ai/tonic-validate-x-llamaindex-implementing-integration-tests-for-llamaindex-43db50b76ed9","title":"Show HN: I Built a GitHub Action to Monitor LlamaIndex Performance","updated_at":"2024-09-20T16:14:36Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Anil1331"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Show HN: How to train a custom GPT on your data with LlamaIndex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://blog.llamaindex.ai/how-to-train-a-custom-gpt-on-your-data-with-embedai-llamaindex-8a701d141070"}},"_tags":["story","author_Anil1331","story_38655116","show_hn"],"author":"Anil1331","children":[38658626],"created_at":"2023-12-15T15:33:28Z","created_at_i":1702654408,"num_comments":1,"objectID":"38655116","points":2,"story_id":38655116,"title":"Show HN: How to train a custom GPT on your data with LlamaIndex","updated_at":"2024-09-20T15:53:32Z","url":"https://blog.llamaindex.ai/how-to-train-a-custom-gpt-on-your-data-with-embedai-llamaindex-8a701d141070"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"ofrasergreen"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Getting Started with LlamaIndex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://medium.com/@ofrasergreen/getting-started-with-llamaindex-169bbf475a94"}},"_tags":["story","author_ofrasergreen","story_35955331"],"author":"ofrasergreen","children":[35955332],"created_at":"2023-05-15T22:25:08Z","created_at_i":1684189508,"num_comments":1,"objectID":"35955331","points":2,"story_id":35955331,"title":"Getting Started with LlamaIndex","updated_at":"2024-09-20T14:03:23Z","url":"https://medium.com/@ofrasergreen/getting-started-with-llamaindex-169bbf475a94"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"jjmachan"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"The Past, Present and Future of LlamaIndex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://explodinggradients.com/the-past-present-and-future-of-llamaindex"}},"_tags":["story","author_jjmachan","story_35806672"],"author":"jjmachan","children":[35806675],"created_at":"2023-05-03T19:35:25Z","created_at_i":1683142525,"num_comments":1,"objectID":"35806672","points":2,"story_id":35806672,"title":"The Past, Present and Future of LlamaIndex","updated_at":"2024-09-20T13:57:29Z","url":"https://explodinggradients.com/the-past-present-and-future-of-llamaindex"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"momentmaker"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"The AI scaffolding layer is collapsing. LlamaIndex's CEO explains what survives"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://venturebeat.com/infrastructure/the-ai-scaffolding-layer-is-collapsing-llamaindexs-ceo-explains-what-survives"}},"_tags":["story","author_momentmaker","story_47979098"],"author":"momentmaker","created_at":"2026-05-01T19:28:29Z","created_at_i":1777663709,"num_comments":0,"objectID":"47979098","points":2,"story_id":47979098,"title":"The AI scaffolding layer is collapsing. LlamaIndex's CEO explains what survives","updated_at":"2026-05-01T20:03:10Z","url":"https://venturebeat.com/infrastructure/the-ai-scaffolding-layer-is-collapsing-llamaindexs-ceo-explains-what-survives"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"mnoorfawi"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Entity Linking and Relationship Extraction with Relik in LlamaIndex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://neo4j.com/developer-blog/entity-linking-relationship-extraction-relik-llamaindex/"}},"_tags":["story","author_mnoorfawi","story_41279471"],"author":"mnoorfawi","created_at":"2024-08-18T01:36:44Z","created_at_i":1723945004,"num_comments":0,"objectID":"41279471","points":2,"story_id":41279471,"title":"Entity Linking and Relationship Extraction with Relik in LlamaIndex","updated_at":"2024-09-20T17:41:44Z","url":"https://neo4j.com/developer-blog/entity-linking-relationship-extraction-relik-llamaindex/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bbzjk7"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Serving LlamaIndex as Rest APIs"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://www.bentoml.com/blog/serving-a-llamaindex-rag-app-as-rest-apis"}},"_tags":["story","author_bbzjk7","story_40559018"],"author":"bbzjk7","created_at":"2024-06-03T03:15:55Z","created_at_i":1717384555,"num_comments":0,"objectID":"40559018","points":2,"story_id":40559018,"title":"Serving LlamaIndex as Rest APIs","updated_at":"2024-09-20T17:13:20Z","url":"https://www.bentoml.com/blog/serving-a-llamaindex-rag-app-as-rest-apis"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"fzliu"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"LlamaIndex on Vertex AI"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://cloud.google.com/vertex-ai/generative-ai/docs/llamaindex-on-vertexai"}},"_tags":["story","author_fzliu","story_40373478"],"author":"fzliu","created_at":"2024-05-15T23:11:50Z","created_at_i":1715814710,"num_comments":0,"objectID":"40373478","points":2,"story_id":40373478,"title":"LlamaIndex on Vertex AI","updated_at":"2024-09-20T17:05:55Z","url":"https://cloud.google.com/vertex-ai/generative-ai/docs/llamaindex-on-vertexai"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"consultutah"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Building Agentic RAG with LlamaIndex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://www.deeplearning.ai/short-courses/building-agentic-rag-with-llamaindex/"}},"_tags":["story","author_consultutah","story_40303872"],"author":"consultutah","created_at":"2024-05-08T23:46:29Z","created_at_i":1715211989,"num_comments":0,"objectID":"40303872","points":2,"story_id":40303872,"title":"Building Agentic RAG with LlamaIndex","updated_at":"2024-09-20T16:58:11Z","url":"https://www.deeplearning.ai/short-courses/building-agentic-rag-with-llamaindex/"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"yujian"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"AI Agent Notebooks Using LangChain, LlamaIndex, Milvus, and More"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/ytang07/ai_agents_cookbooks"}},"_tags":["story","author_yujian","story_40247807"],"author":"yujian","created_at":"2024-05-03T14:05:55Z","created_at_i":1714745155,"num_comments":0,"objectID":"40247807","points":2,"story_id":40247807,"title":"AI Agent Notebooks Using LangChain, LlamaIndex, Milvus, and More","updated_at":"2024-09-20T17:00:31Z","url":"https://github.com/ytang07/ai_agents_cookbooks"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"kanungle"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Multistage RAG with LlamaIndex and Cohere Reranking"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://medium.com/kx-systems/multistage-rag-with-llamaindex-and-cohere-reranking-a-step-by-step-guide-51fc7e8d6ef2"}},"_tags":["story","author_kanungle","story_40092658"],"author":"kanungle","children":[40092659],"created_at":"2024-04-19T22:31:37Z","created_at_i":1713565897,"num_comments":0,"objectID":"40092658","points":2,"story_id":40092658,"title":"Multistage RAG with LlamaIndex and Cohere Reranking","updated_at":"2024-09-20T16:53:49Z","url":"https://medium.com/kx-systems/multistage-rag-with-llamaindex-and-cohere-reranking-a-step-by-step-guide-51fc7e8d6ef2"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"anupgosavi40"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"VideoDB Retriever: Instantly search and stream video with LlamaIndex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://docs.llamaindex.ai/en/stable/examples/retrievers/videodb_retriever.html"}},"_tags":["story","author_anupgosavi40","story_39575410"],"author":"anupgosavi40","created_at":"2024-03-02T20:16:28Z","created_at_i":1709410588,"num_comments":0,"objectID":"39575410","points":2,"story_id":39575410,"title":"VideoDB Retriever: Instantly search and stream video with LlamaIndex","updated_at":"2024-09-20T16:32:47Z","url":"https://docs.llamaindex.ai/en/stable/examples/retrievers/videodb_retriever.html"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"chkelly9"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Building a Chatbot for HN and StackOverflow with LlamaIndex and ClickHouse"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://twitter.com/llama_index/status/1763282902358585445"}},"_tags":["story","author_chkelly9","story_39556872"],"author":"chkelly9","created_at":"2024-03-01T00:00:17Z","created_at_i":1709251217,"num_comments":0,"objectID":"39556872","points":2,"story_id":39556872,"title":"Building a Chatbot for HN and StackOverflow with LlamaIndex and ClickHouse","updated_at":"2024-09-20T16:30:41Z","url":"https://twitter.com/llama_index/status/1763282902358585445"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"tslmy"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Llama Lab: Ambitious projects built on top of LlamaIndex"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://github.com/run-llama/llama-lab"}},"_tags":["story","author_tslmy","story_38764594"],"author":"tslmy","created_at":"2023-12-25T17:57:53Z","created_at_i":1703527073,"num_comments":0,"objectID":"38764594","points":2,"story_id":38764594,"title":"Llama Lab: Ambitious projects built on top of LlamaIndex","updated_at":"2024-09-20T16:02:37Z","url":"https://github.com/run-llama/llama-lab"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"Ephil012"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Validating the RAG Performance of OpenAI vs. LlamaIndex"},"url":{"matchLevel":"none","matchedWords":[],"value":"https://tonicai.substack.com/p/rag-evaluation-series-validating-0df"}},"_tags":["story","author_Ephil012","story_38436457"],"author":"Ephil012","created_at":"2023-11-27T18:50:26Z","created_at_i":1701111026,"num_comments":0,"objectID":"38436457","points":2,"story_id":38436457,"title":"Validating the RAG Performance of OpenAI vs. LlamaIndex","updated_at":"2024-09-20T15:47:38Z","url":"https://tonicai.substack.com/p/rag-evaluation-series-validating-0df"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"bbzjk7"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Chat-Llamaindex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://github.com/run-llama/chat-llamaindex"}},"_tags":["story","author_bbzjk7","story_38095104"],"author":"bbzjk7","created_at":"2023-11-01T06:11:26Z","created_at_i":1698819086,"num_comments":0,"objectID":"38095104","points":2,"story_id":38095104,"title":"Chat-Llamaindex","updated_at":"2024-09-20T15:33:09Z","url":"https://github.com/run-llama/chat-llamaindex"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"omarfarooq"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"LlamaIndex Chat: Create chat bots that know your data"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://github.com/run-llama/chat-llamaindex"}},"_tags":["story","author_omarfarooq","story_38073116"],"author":"omarfarooq","created_at":"2023-10-30T17:57:16Z","created_at_i":1698688636,"num_comments":0,"objectID":"38073116","points":2,"story_id":38073116,"title":"LlamaIndex Chat: Create chat bots that know your data","updated_at":"2024-09-20T15:31:00Z","url":"https://github.com/run-llama/chat-llamaindex"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"kaycebasques"},"story_text":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"What are your experiences with it? If you're currently using it, how's it going?
I like the conceptual model quite a bit. Some of my colleagues bootstrapped a project with LlamaIndex but eventually moved away from it; I don't know the exact reasons."},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Ask HN: Thoughts on LlamaIndex"}},"_tags":["story","author_kaycebasques","story_37902943","ask_hn"],"author":"kaycebasques","created_at":"2023-10-16T17:09:15Z","created_at_i":1697476155,"num_comments":0,"objectID":"37902943","points":2,"story_id":37902943,"story_text":"What are your experiences with it? If you're currently using it, how's it going?
I like the conceptual model quite a bit. Some of my colleagues bootstrapped a project with LlamaIndex but eventually moved away from it; I don't know the exact reasons.","title":"Ask HN: Thoughts on LlamaIndex","updated_at":"2024-09-20T15:19:38Z"},{"_highlightResult":{"author":{"matchLevel":"none","matchedWords":[],"value":"yujian"},"title":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"Persistent Vector Storage for LlamaIndex"},"url":{"fullyHighlighted":false,"matchLevel":"full","matchedWords":["llamaindex"],"value":"https://pub.towardsai.net/persistent-vector-storage-for-llamaindex-4117e306f34d?gi=9095c1fb975b"}},"_tags":["story","author_yujian","story_36244551"],"author":"yujian","created_at":"2023-06-08T16:27:31Z","created_at_i":1686241651,"num_comments":0,"objectID":"36244551","points":2,"story_id":36244551,"title":"Persistent Vector Storage for LlamaIndex","updated_at":"2024-09-20T14:14:23Z","url":"https://pub.towardsai.net/persistent-vector-storage-for-llamaindex-4117e306f34d?gi=9095c1fb975b"}],"hitsPerPage":50,"nbHits":212,"nbPages":5,"page":0,"params":"query=LlamaIndex&tags=story&hitsPerPage=50&advancedSyntax=true&analyticsTags=backend","processingTimeMS":9,"processingTimingsMS":{"_request":{"roundTrip":16},"afterFetch":{"merge":{"mergeLoop":{"prepareNextHit":1,"total":1},"total":1},"total":1},"fetch":{"query":6,"total":7},"total":9},"query":"LlamaIndex","serverTimeMS":11}