thank you @sundarpichai and @OfficialLoganK for gemini 2.5 pro
literally like buying a better desk chair or mattress
everything is more beautiful now
Francisco
1,314 posts
making farm work llm-native @ FieldData
automate the boring
๐ฆ๐ท โ๏ธ
Joined January 2023
- Replying to @noor_siddiqui_ and @OrchidIncwhat happens to all the other embryos? you're not preventing your child from going blind, you're making sure your blind child is not born at all
- So... I did a video ๐ฌ youtube.com/watch?v=iUcoHxโฆ I go over how to extract meaningful entities from a passage and how to best tag a document for its content. If you want to learn more @langchain document tagging and extracting functionality, check it out!The new @OpenAI functions are good for other things besides agents Another killer use case is extracting structured information from unstructured docs We've adding support for extraction AND tagging in @langchain - thanks to @fpingham for code and @jxnlco for review ๐งต
- langsmith really is a fantastic product it just feels so natural to use, so obvious its like mac for llms - everything just works as you would expect it to if you ever built a product for real users you know how hard it is to achieve this
- Replying to @chiprowhen you're reaching limits but dont want to hurt user experience by saying there's a token budget
- Need to extract very specific data from your documents? Check out the new extraction docs for @langchain! They include some tips and tricks to get the most out of your extraction solution ๐Extraction ๐โก๏ธ๐๏ธ Getting structured LLM output is hard! Part 3 of our initiative to improve @langchain docs covers this w/ functions and parsers (see @GoogleColab ntbk). Thanks to @fpingham for improving the docs on this: python.langchain.com/docs/use_casesโฆ
- Honored to have had the opportunity to collaborate with James on this - @langchain is *the* place to start if you are thinking in building LLM-based apps. Check it out!๐จ Everything you need to know about @langchain! The LangChain AI Handbook is a free eight-chapter ebook + videos, interactive notebooks, and bonus projects by myself and @fpingham pinecone.io/learn/langchaiโฆ #NLProc #GenerativeAI #LLMs #GPT4
- Lauta spitting fire ๐ฅ๐ฅ Our chosen stack for building world-class agents: - @langchain for langgraph agent framework - @TryArcade for tools with pre-built authentication - @firecrawl for web scraping - @AnthropicAI for MCP protocol (h/t @dsp_) Building agents has nevertry this agent with this query: "generate a summary of the {{website}} and publish it directly on X or send it to Slack {{user}}" stack: - langGraph: mcp client, orchestrating - firecrawl: mcp server, intelligent web search - arcade: toolkits with auth (Google, X, Slack) -
- One of the biggest hacks on using LLMs for write ups by @jxnlco: 'No adjectives' Worth each token in gold
- Replying to @kevinhou22many people in our LLM Native community going all in windsurf problems with cursor + half the price even if you don't see major differences between the two, paying double for the same experience doesn't compile
- Pampa Labs is now an official LangChain partner ๐ Excited to continue our journey of building great LLM-based solutions for clients across the boardwelcomeโ๏ธ๐ฝnew LangChain Partners Pampa Labs via @fpingham & @manuelsoria_ and Parlance Labs via @HamelHusain we've been working with Francisco, Manuel, and Hamel since the beginning, and we're excited for you all to get to know them, too! langchain.com/partners
- Another @langchain video with James, presenting the key building block in langchain: agents Take a look ๐@langchain agents are one of the most important tools offered by the library and a key building block in the current AI boom ๐ค Check out this @pinecone deep dive on agents from @fpingham and myself pinecone.io/learn/langchaiโฆ #NLProc #ArtificialIntelligence









