The latest paper from @salesforce AI, et al. discovers a new prompt called Chain of Density (CoD) that produces more dense and human-preferable summaries compared to vanilla GPT-4. I gave it a try for a few articles and it's really solid. Pasted it here if you want to try it 👇 --- Article: {{ ARTICLE }} You will generate increasingly concise, entity-dense summaries of the above article. Repeat the following 2 steps 5 times. Step 1. Identify 1-3 informative entities (";" delimited) from the article which are missing from the previously generated summary. Step 2. Write a new, denser summary of identical length which covers every entity and detail from the previous summary plus the missing entities. A missing entity is: - relevant to the main story, - specific yet concise (5 words or fewer), - novel (not in the previous summary), - faithful (present in the article), - anywhere (can be located anywhere in the article). Guidelines: - The first summary should be long (4-5 sentences, ~80 words) yet highly non-specific, containing little information beyond the entities marked as missing. Use overly verbose language and fillers (e.g., "this article discusses") to reach ~80 words. - Make every word count: rewrite the previous summary to improve flow and make space for additional entities. - Make space with fusion, compression, and removal of uninformative phrases like "the article discusses". - The summaries should become highly dense and concise yet self-contained, i.e., easily understood without the article. - Missing entities can appear anywhere in the new summary. - Never drop entities from the previous summary. If space cannot be made, add fewer new entities. Remember, use the exact same number of words for each summary. Answer in JSON. The JSON should be a list (length 5) of dictionaries whose keys are "Missing_Entities" and "Denser_Summary". ```

Shade thrown at graph-based agent frameworks in @OpenAI's Practical Guide to Building Agents

Rather large 🦜🔗0.0.131 release! 🆓GPT4all model (@nomic_ai) 🦙Llama-cpp model ⏹️Support for @qdrant_engine local db 🌲Zilliz cloud (@milvusio) Vectorstore support 📧New OutlookMessage Document Loader 🕸️New Selenium Document Loader 🪟 Support for SQL views in SQLChain 🧵

Most "agents" today are shallow while loops around an LLM and tools. Works for simple tasks, but fails when a task requires 50+ steps over several days. To solve complex problems, we need an architectural shift towards Deep Agents (Agents 2.0). We have to decouple planning from execution. Explicit state, sub-agents, and persistent memory.

Is MCP just Zapier without UI but powered by a prompt?

I see a lot of people make the same mistakes building agents. So we shared a few of the principles we use cognition.ai/blog/dont-build…

Tutorial: How to build an e-commerce chatbot using #OpenAI, @Redisinc, and @langchain -- useful just if you want to see how this sort of system works. redis.com/blog/build-ecommer…

🚀Announcing LangGraph Studio: The first agent IDE LangGraph Studio offers a new way to develop LLM applications by providing a specialized agent IDE that enables visualization, interaction, and debugging of complex agentic applications With visual graphs and the ability to edit state, you can better understand agent workflows and iterate faster. LangGraph Studio integrates with LangSmith so you can collaborate with teammates to debug failure modes LangGraph Studio is available for free to all LangSmith users on any plan tier during its early development. Read more about it here: blog.langchain.dev/langgraph… Watch a YouTube walkthrough: piped.video/watch?v=pLPJoFvq… Try out LangGraph Cloud for free here: github.com/langchain-ai/lang… Sign up for a LangSmith account: smith.langchain.com

🦜🤖OpenGPTs Some big updates to OpenGPTs - an open-source, fully configurable GPTs experience You can now: 📁Upload files to a retrieval tool (with full configurability over the ingestion, vectorstore, and retrieval used) 🌐Share public bots that you've created 🛠️Use more tools by default (wikipedia, arxiv, pudmed, @YouSearchEngine, @tavilyai, Kay.ai (@vishalrohra_) 👍/👎Log feedback to LangSmith 💬Store chat message history (with @Redisinc) Check out the open source repo here: github.com/langchain-ai/open… And check out the "research preview" hosted app here: opengpts-example-vz4y4ooboq-…

what is something other agentic frameworks do that langgraph doesnt? not abstractions, but functionality currently the only one i can think of is dspy by @lateinteraction (which does optimization) what am i missing?

You should try @tryhighlight - you can just @ any MCP server from anywhere. Runs natively. With context grounding so it can use what you’re looking at as inputs and outputs.

⚙️How Dosu used LangSmith to achieve a 30% accuracy improvement with no prompt engineering One of the goals of LangSmith is to help teams set up a data flywheel. By capturing LLM outputs alongside user feedback, we can help developers automatically use that feedback to improve their application That's exactly what @devstein64 and the @dosu_ai team did. They have GitHub bot that auto-labels your issues and PRs (among other features). We sat down with them to understand how they used logging, datasets, and our new automations feature to automatically improve their application by 30% purely by capturing user feedback. We then set up a cookbook so ANY LangSmith user can replicate what they did. Blog: blog.langchain.dev/dosu-lang… YouTube: piped.video/tHZtq_pJSGo Cookbook: docs.smith.langchain.com/mon…

🏆Top 5 LangGraph Agents in Production 2024 #3: LinkedIn While "agents" are the buzzword of the moment, agentic apps built with LangGraph have been in production throughout 2024. Among those who shared insights publicly, we're doing a countdown of our 5 favorite. Next up, number 3: LinkedIn One of the big use cases for LLMs is in making data more accessible to everyone. LinkedIn recently rolled out SQL Bot, an AI-powered assistant internally This internal tool transforms natural language questions into SQL: it finds the right tables, writes queries, fixes errors, and enables employees across functions to independently access the data insights they need under the appropriate permissions. Behind the scenes, SQL Bot is a multi-agent system built on top of LangChain and LangGraph. linkedin.com/blog/engineerin…