🤖Build an Autonomous Research Assistant with LangGraph and GPT Researcher

See a step-by-step walkthrough by Assaf Elovic on how flow engineering and multi-agent collaboration can help automate in-depth research on any given topic — from architecture to run.

In this example,…

🔒Role Based Access Control (RBAC) for LangSmith

Admins can now assign roles to users in their workspace or organization in LangSmith. Create/edit custom roles with granular permissions to determine who can access resources.

We've also introduced revamped API Keys to support…

🛠️ Personal prompts in LangSmith are now easier to access and manage.

You'll see a new home for your organization's prompts, separate from the LangChain Hub. Organize and pull existing prompts by their commit versions — so you can track the performance of different versions of…

LangSmith Evaluations: RAG Evaluation (Intermediate Steps)

Evaluations can accelerate LLM app development, but it can be challenging to get started. We've kicked off a new video series focused on evaluations in LangSmith.

This is the 16th video in our series…

I just migrated my financial RAG evals to LangSmith.

Previously, I was doing evals by hand.

Now, LangSmith takes care of:
• managing datasets
• evaluating correctness
• measuring latency
• visualizing prediction vs. answer

These features come built-in.

My financial RAG…

Excited to share some thoughts on building AI customer support bots!

💡ReAct agents are powerful but inconsistent.
♽ It *can* be easier to build/optimize/evaluate if you target specific user journeys.
🎛️ LangGraph lets you factor out key workflows to give you more control.

Today, I am open sourcing my latest project diving into AI Devices

Tech:
Groq Inc Llama3🦙(whisper sneak peak coming 🔜)
LangChain & Langsmith🦜
OpenAI TTS, Vision, Whisper🤫
Vercel AI SDK & Next.js🔺
Serper API Search🔍
Upstash Rate Limiting🛑
fal Llava🌋
🎥 & Repo👇

GPT Researcher is the best OSS research project

Excited to work with them on a more advanced 'cognitive architecture' powered by LangGraph!

This is one of the most exciting releases yet. Proud to introduce the latest GPT Researcher x LangGraph integration showcasing the power of flow engineering and multi agent collaboration!

Generates a 6+ page research report in multiple formats such as PDF, Docx and Markdown. 🤯…

🔧Building LLM Agents with Tool Use

This great video from our friend Jay Alammar at Cohere walks through how to build a data-analyst LLM agent with Cohere's newest Command R+ model

Agents are complex, but Jay does a great job of breaking them down!

youtube.com/watch?v=5drn2D…

🕸️Introducing Schema Controlled Automated Knowledge Graphs

WhyHow.ai is building tools to help you structure your data with your opinion, through knowledge graph tooling

Check out a recent blog highlighting some of their releases

medium.com/enterprise-rag…

📄Prompt Engineering with LangChain

This LinkedIn course by harpreet is a great resource for getting started

It's over 5 hours long, and Harpreet has been a fantastic member of the community since the early days. Big thanks for all the effort!

linkedin.com/learning/promp…

🌎Building an AI Agent That Has Access to the Internet Using LangChain and Tavily’s API

This setup enables the AI agent to access a vast range of data, understand and interact with it in a meaningful way.

Full blog here: medium.com/thoughts-on-ma…

🚀Rocketnotes

Rocketnotes is a OSS, web-based Markdown note taking app with the following features:

📝 Code syntax highlighting
🌳 Hierarchical document tree
🔍 Content search
🔦 Semantic search
✍️ Text completion
🤖 Chat with your docs
📦 Local mode

github.com/fynnfluegge/ro…

⚡️Multi-Agent RAG Online Workshop⚡️

If there’s anything better than agentic RAG, it’s multi-agent RAG!

In this event, we’ll explore the big idea behind “multi-agent” applications. These types of workflows combine multiple independent agents, which can be structured to work…