Discover and read the best of Twitter Threads about #LangChain

Most recents (14)

1/5 🔍 Unleash the power of me, "Q, ChatGPT for Slack" to answer queries based on your company's PDF manuals using @LangChainAI. 🚀

🎥 Demo Video and its Challenges
🛠 Getting Ready
🎯 Sample Queries
📝 Analysis & Suggestions
💡 Finally

Join us as we dive deep into each topic!
2/5 We've captured a demo of "Q, ChatGPT for Slack" answering questions based on @nvidia 's latest GPU (RTX 4090 by @NVIDIAGeForce) manual. 📺 Imagine the same for your company's product or business manual, and how it can help solve recurring Q&A issues in your organization! 🙌
3/5 Getting ready is simple: Upload your PDF by direct messaging it to me and activate the 'Pre-Uploaded Document Search' plugin from the home tab. 📁💡

Once done, ask away! Check out our demo for some inspiration:
#LangChain #GPT4 ImageImage
Read 6 tweets
Putting @LangChainAI to the test.

I've used LangChain and OpenAI to generate 9 questions and answers to the paper: "Eight Things to Know about Large Language Models" by @sleepinyourhat

Inspiration by @gael_duval

Code in last Tweet. Let's learn! 🧵

#AI #langchain #LLM Image
Question 1:

What are the eight potentially surprising claims about large language models discussed in the text? Image
Question 2:

How do large language models (LLMs) become more capable with increasing investment? Image
Read 11 tweets
🧵 Exciting Apps You Can Build with @LangChainAI by @hwchase17

Have you ever thought about the possibilities offered by LangChain?
Let's dive into five amazing app ideas you can bring to life using this versatile tool and get access to code!
#AI #ChatGPT Image
First up, a context-aware Chatbot! 🤖

Harness the power of natural language processing to create a chatbot that delivers contextual and relevant answers to user queries. The integration of additional data sources can make your bot!
Repo: tinyurl.com/4y9rt92j
#LangChain
Ever drowned in lengthy documents? Here's a solution - A SummarizationApp! 📃

LangChain can help you condense long articles or documents while preserving their core meaning, making it easier to absorb information. #AI
github.com/ncodepro/pdfch…
Read 7 tweets
Excited to announce our new course: "Introduction to @LangChainAI : A Framework for Large Language Model Applications"!🎉
Dive into the world of #LangChain, a software development framework designed to streamline the creation of applications using LLM
#ChatGPT #LLM #course Image
Agenda: We've packed this course with everything from understanding what LangChain is, to building your own application. A complete guide to get you started with LangChain.📚🚀 Image
Check our course at the link below. news.thesamur.ai/courses/introd…
Repo link:
github.com/SamurAIGPT/lan…
Read 5 tweets
Suite à mon thread sur les sites automatisés en #IA, on m’a beaucoup demandé « Mais comment t’as fait ».
J'ai pu le présenter à @genaiparis

Je vais détailler mais profitons-en pour parler de comment on « code » avec #ChatGPT #langchain
⤵️⤵️
@genaiparis Je vais essayer de vulgariser un peu, on verra mon workflow spécifique après.
Outre la version grand public, ChatGPT existe aussi en version APIsé, c’est-à-dire que l’on peut donc intégrer dans un programme (soit via OpenAI, soit sur Microsoft Azure).
datascientest.com/api-tout-savoir
@genaiparis De ce côté, il n’y a rien de différent avec d’autres services (par exemple se connecter à l’API de twitter pour créer un bot). Là où c’est très différent, c’est que les paramètres que l’on va indiquer sont plus qualitatif. On va coder de manière littérale !
Read 30 tweets
🎉 Exciting news! An early preview of our @LangChainAI beginner's course is now live 🚀

We'll dive into the basics of Langchains, Interacting with LLMs(OpenAI), Prompts, and Chains,
Stay tuned for more details below ↓
#AI #LLM
🦜️🔗 LangChain: A revolutionary #OpenSource framework simplifying the creation of applications with large language models.
Powering everything from chatbots to code analysis, this Python & JavaScript toolkit bridges the gap between AI and application development.
#AI #LLM
"🦜️🔗 #LangChain features:
1️⃣ Simplified app development with large language models 🤖
2️⃣ Integrations with popular platforms like Amazon, Google, & Microsoft Azure
3️⃣ Support for document analysis 📄, chatbots 💬, code analysis 🔍
4️⃣ Open-source with a vibrant community 👥
Read 8 tweets
1/5 📣Introducing #DataChad, the #ChatGPT for any local or cloud data. Chat with any data source: a JSON, PDF, URL, or even an entire GitHub repo! 🌐📚

Built with #DeepLake, @LangChainAI, @OpenAI & open-sourced by an awesome community member @thegreatgustby.
2/5 And guess what? It's not just a shiny demo. You can try it out yourself! (Link in the next tweet) 💡🔗

github.com/gustavz/DataCh… DataChad is a ChatGPT for a...
3/5 @thegreatgustby shared tips to avoid common pitfalls while building AI apps with #LangChain & #DeepLake. 🧭🛠️

Adjusting parameters like k, chunk_size, max_tokens, and temperature. Read below to learn more about creating a Chat with Any Data app!
bit.ly/datachad
Read 3 tweets
@LangChainAI 相关文档翻译】📚🌐
近期 #langchain 特别火🔥,其提供了与LLM交互的组件和接口,便于开发。

受到 @GPTDAOCN @zbruceli 的启发💡,我翻译了 相关文档,包括案例库,官方博客,并收录了国内相关的介绍文章🌟

🔗 相关 Notion 链接: three-recorder-52a.notion.site/langchain-5-4-…

🧵 Thread:(1/n) Image
1️⃣Langchain 官方信息:🌐

🐦 推特(6.1 万人关注): @LangChainAI
推特上经常会发布基于 Langchain 的项目,如 Bot,AutoGPT 等。

🌟 GitHub(3.5 万星): github.com/hwchase17/lang…

📚 官方文档: python.langchain.com/en/latest/inde…

🖋️ 官方博客: blog.langchain.dev
(2/n)
1️⃣ Langchain案例库:🔍
汇集了最常见的需求,如:
🎮 Agent Simulations: 代理模拟
❓ Question Answering: 基于文件的问答
💬 Chatbots: 聊天机器人
📊 Querying Tabular Data: 查询表格数据
这些案例为开发者提供了丰富的参考和灵感💡
three-recorder-52a.notion.site/langchain-5-4-…
(3/n) Image
Read 5 tweets
Just gave GPT-4 access to use Chrome however it wants (click, scroll, fill forms) thru @LangChainAI Auto-GPT agent. The results were mind-blowing!

Here's what it did: 👇

🎧Bought me an AirPod
🎉Helped me find an event venue and filled out the contact form
🍽️Booked restaurants
I’ve also open-sourced the project so you can try it out too! ChromeGPT is built using @LangChainAI and @SeleniumHQ , supports Zero-shot, #BabyAGI and #AutoGPT agents. github.com/richardyc/Chro…

More ChromeGPT demos: 🧵

2/4

#ChromeGPT #ChatGPT #langchain #generative #GPT4
Demo using #langchain Auto-GPT agent

Prompt: Find me a bar that can host a 20 person event near Chelsea Manhattan. Fill out contact us form if they have one. 👇

3/4
Read 4 tweets
@LangChainAI is a very powerful tool but you don't need to be a coder to utilize its full potential. Which is why, I have created a CLI for @LangChainAI.

Here's a screenshot of LangChain-CLI in action: Image
Features:
- LangChain accessible through CLI
- No need to save OpenAI Key locally/remotely
- Ability to decide the Temperature of the model
- Decide the number of tokens to be spend during runtime

Installation is pretty simple. Use the below command:

pip install langchain-cli
I am looking for sponsors, backers or funders for this project. I want to be able to cover @LangChainAI in its entirety within a CLI. If you want to contribute to the code, go ahead and open a PR. Create a fork, download the code to your system or give it a star. #langchain
Read 3 tweets
🧵1/8 Here is how to build a pipeline that automates the process of creating, researching, improving & finalizing an article on any topic. I used #langchain & @OpenAI, Google Search and Google News API! Let's dive in!👇 Image
🧵2/8 The pipeline starts by loading news articles on a chosen topic. In our example it is "Canada budget". It then creates a summary of these articles, which will be used as the basis for our first draft. Image
🧵3/8 The first draft is generated by using custom author and question chains in a sequential manner. The author chain creates a coherent narrative, while the question chain generates relevant questions to research further. #langchain #OpenAI
Read 10 tweets
🔥1/8
Introducing "🤖 Task-driven Autonomous Agent"

An agent that leverages @OpenAI's GPT-4, @pinecone vector search, and @LangChainAI framework to autonomously create and perform tasks based on an objective.

"Paper": yoheinakajima.com/task-driven-au…

[More 🔽] Image
🚀2/8 The system can complete tasks, generate new tasks based on results, and prioritize tasks in real-time. It demonstrates the potential of AI-powered language models to autonomously perform tasks within various constraints and contexts.
💡3/8 The autonomous agent uses GPT-4 for task completion, Pinecone for efficient search and storage of task-related data, and the LangChain framework to enhance decision-making processes. #GPT4 #Pinecone #LangChain
Read 16 tweets
I recently experimented with OpenAI's API using LangChain. The possibilities of what we can achieve with this technology are truly endless! In this thread, I'll share how I used LangChain to build an app that generates responses to questions based on YouTube video content. Image
First, I extracted the transcript from the videos. For longer videos, I split the document with enough overlap(to ensure continuity), sent the smaller parts to the LLM, got the summary for each part, and combined them for the final result. #OpenAI #LangChain #AI #NLP
Next, I used LangChain's map-rerank method to get the final answer. By tuning the prompts, I was able to generate responses limited to the video's context. #AI #NLP #MachineLearning #ChatGPT
Read 4 tweets
AI提示工程系列第五篇:构建一个基于知识库的AI机器人

1/12
在第二篇讲了如何让ChatGPT写长文,是从生成的角度来说。
那如果我们手头有一套知识库,如何根据知识库来建立一个类似 #chatpdf 的问答系统呢?今天就来聊聊这个话题👇🧵

#AI #ChatGPT #提示工程 #promptengineering #SemanticSearch
2/12
本文偏系统设计方面,适合于AI领域的产品/技术同学阅读。

没看过前四篇的朋友可以回顾一下:
3/12
假设我们的场景是要建立一个公司的AI自动客服系统,手头有公司的一整套知识库。

我们清楚ChatGPT有4096的Token上下文的限制,是无法一次性将整套知识库灌给ChatGPT的。这就要求我们想办法将数据“剪枝”,而剪枝的方法就是将用户的“问题”和知识库中可能的“段落上下文”联系起来。
Read 12 tweets

Related hashtags

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!