Just finished the "LangChain Chat with your Data" short course on https://learn.deeplearning.ai/. I had started digging into this last weekend when I finished the foundational short class on #langchain and was starting to tinker with some bookmark data I'm able to retrieve with the raindrop.io API. This dug deeper into a lot of the questions that I had around document splitting, retrieval, some lots of other tidbits.
What exactly is LangChain anyway? @meheller explains this modular framework for Python & JavaScript which aims to streamline developing generative AI applications
https://www.infoworld.com/article/3706289/what-is-langchain-easier-development-around-llms.html
#GenAI #GenerativeAI #LLM #LLMs #LangChain #Python #JavaScript #InfoWorld
(Looking forward to Mastodon full text search general availability so I can cut back on the hashtags 😅 )
#genai #generativeai #llm #llms #langchain #python #javascript #infoworld
/ #software / #article
🔍 #LangChain
https://laravista.altervista.org/CatLink/links/94
🐱🔗 #catlink
#SoftwareArticle
#software #article #langchain #catlink #softwarearticle
LangChain + LangSmith: The ultimate combo for LLM-powered AI apps!
- Access, train, and deploy LLMs in minutes
- Debug, test, evaluate, and monitor your AI apps with ease with LangSmith!
#LangChain #LangSmith #LLMs
Finished the #LangChain for #llm Application Development short course on https://learn.deeplearning.ai/ this morning, learned a lot and enjoyed myself. Looking forward to tinkering with it.
is there a #Summarization plugin for #obsidian based on #LangChain?
#langchain #obsidian #summarization
"The real issue with [LangChain] integrations is that it creates an inherent lock-in to only use LangChain-based code, and if you look at the code for the integrations they are not very robust. LangChain is building a moat, which is good for LangChain’s investors trying to get a return on their $30 million, but very very bad for developers who use it."
Rereading this critical review of LangChain by @minimaxir, which deserves more reads: https://minimaxir.com/2023/07/langchain-problem/
#llms #langchain #MLops #chatgpt
I'm a little late to the party, but have recently been deep-diving into running LLMs locally via #langchain and experimenting with semantic embedding and retrieval augmented generation.
It's really fun to "ask" your personal and business document cache questions and get reasonable answers out. Endless applications.
Maybe the fact that LangChain (the company) made it will lend LangSmith some legitimacy. LangChain (the framework) surely has seen a rapid rise in popularity -- although Github Stars might be a bad metric for actual production use.
Here is a comparison chart with some of the other popular NLP/LLM libraries -- these repos do not implement the same functionality but it should give you a rough idea.
#langsmith #langchain #llms #generativeAI #MLops #ai
The documentation is still a bit all over the place, but this walkthrough shows a sneak peek of what's possible:
https://github.com/langchain-ai/langchain/blob/master/docs/extras/guides/langsmith/walkthrough.ipynb
I especially like the idea of quickly evaluating variations of an LLM pipeline against a baseline of earlier runs.
#langsmith #langchain #llms #generativeAI #MLops #ai
Today I took a first look at LangSmith, a new platform for LLM production pipelines by LangChain.
I can't hook it up to a working pipeline yet because it's in closed beta, but it surely looks ambitious. It should make it easier to do logging, monitoring, debugging and evaluating pipelines (chains) against each other. It's tightly integrated with LangChain but it should support other frameworks/models as well.
#langsmith #langchain #llms #generativeAI #MLops #ai
💡 L'unione tra #LangChain e i #LLM ormai è abbastanza nota. L'obiettivo è produrre contesto per il modello per ottenere risposte, dati, informazioni relative ad un dominio definito.
🧠 #Embedchain è un framework in #Python che permette di creare un #chatbot basato su qualunque risorsa online.
🦾 Le risorse di riferimento vengono vettorializzate (#embeddings) e salvate in un database vettoriale.
#langchain #LLM #embedchain #python #chatbot #embeddings #ai #intelligenzaartificiale
FastAPIを使ってストリーム対応のLLM API RESTサーバを作る on Databricks
https://qiita.com/isanakamishiro2/items/c55123343e95fd2769a6?utm_campaign=popular_items&utm_medium=feed&utm_source=popular_items
#qiita #Databricks #FastAPI #langchain #LLM #CTranslate2
#qiita #databricks #fastapi #langchain #llm #ctranslate2
🧠 Aumentano le piattaforme visuali per lo sviluppo di applicazioni basate sui #LLM.
📊 #Flowise è un progetto open source gratuito per uso commerciale e personale basato su #LangChain che permette la creazione di interfacce conversazionali estremamente flessibili.
🦾 Un mix di #PromptEngineering, agenti, ricerca semantica, modelli di #chat, database vettoriali e strumenti utili.
#AI #IntelligenzaArtificiale #GPT4 #LLaMA2 #PromptDesign
https://www.linkedin.com/posts/alessiopomaro_llm-flowise-langchain-activity-7098908442483994624-4MrB
#LLM #flowise #langchain #promptengineering #chat #ai #intelligenzaartificiale #GPT4 #llama2 #promptdesign
Are you an R/RStudio interested in trying out LangChain for generative AI apps? Here's an idea on how to do that with minimal Python, in RStudio, using R to look at code results step by step.
https://www.infoworld.com/article/3703249/generative-ai-with-langchain-rstudio-and-just-enough-python.html
#rstats #RStudio #python #LangChain #InfoWorld #GenerativeAI @rstats
#rstats #rstudio #python #langchain #infoworld #generativeai
🧠 Jupyter AI porta l'#AI generativa nei Notebook Jupyter attraverso #LangChain e i #LLM (#OpenAI, #AWS, #Cohere, #Anthropic o #AI21).
✨ Con la possibilità di spiegare e generare codice, correggere errori, riepilogare contenuti, porre domande sui file locali e generare interi notebook attraverso una #chat e #prompt in linguaggio naturale.
#IntelligenzaArtificiale #generativeAI #development #Python #DataDemocratization #futuro
---
https://blog.jupyter.org/generative-ai-in-jupyter-3f7174824862
#ai #langchain #LLM #openai #aws #cohere #anthropic #ai21 #chat #prompt #intelligenzaartificiale #generativeAI #development #python #datademocratization #futuro
🧠 Diversi scienziati stanno riflettendo su come sia possibile dare all’#AI dei valori condivisi, regole e buon senso.
🦾 Anthropic, ad esempio, fonda il suo modello su una “costituzione”, fatta di principi definiti, condivisi e attraverso i quali possiamo rendere migliori gli algoritmi.
🔗 Alcune riflessioni: https://lnkd.in/dvvjXcTQ
#IntelligenzaArtificiale #ChatGPT #GPT4 #Claude2 #AutoGPT #LangChain
#ai #intelligenzaartificiale #chatgpt #GPT4 #claude2 #autogpt #langchain
⚡ Questo è uno degli obiettivi che mi e ci stanno a cuore, con Search On Media Group e WMF. Per questo, vi aspettiamo all'AI Summer School, dal 2 al 9 settembre a Monasterace (RC) e all'AI Festival, il 5 e 6 ottobre a Milano.
✨ Ma ci saranno molte altre occasioni di vivere insieme momenti dedicati ad un tema così importante.
#AI #IntelligenzaArtificiale #ChatGPT #GPT4 #AutoGPT #LangChain
#ai #intelligenzaartificiale #chatgpt #GPT4 #autogpt #langchain
I made a simple CLI tool in #rustlang to convert epub to text (Markdown). It converts the whole book (even complex books) in less than 1second. Compared to about 10sec for the Calibre CLI tool. Useful for quickly converting books to text for use with a little #langchain #llm app I've been working on.
Here's the repo, it's super simple thanks to the epub and html2md #rust crates:
https://github.com/darrenmothersele/epub_to_txt
#rustlang #langchain #llm #rust
Build a #ChatGPT-Powered PDF Assistant with Langchain and Streamlit
#langchain #streamlit #python #javascript
https://morioh.com/a/769dfb7fa4c1/build-a-chatgpt-powered-pdf-assistant-with-langchain-and-streamlit
#JavaScript #Python #streamlit #langchain #chatgpt