Multi Needle in a Haystack Benchmark RAG often isn't about just retrieving a fact, it's about retrieving multiple facts and reasoning over them We find that: Retrieval performance decreases with more needles
Reasoning over retrieved needles is harder than retrieving
@langchain
-
Multi Needle Haystack: RAG Retrieval and Reasoning Challenges
By
–
-
Deploy LangChain Applications on AWS with Pulumi Workshop
By
–
Sign up for our workshop with @PulumiCorp tomorrow! You'll learn the basics of Pulumi for infrastructure as code, the basics of LangChain and LangServe, and how to deploy a LangChain/LangServe application on AWS using Pulumi. https://
pulumi.com/resources/depl
oying-langchain-applications-on-aws-with-pulumi/
… -
PyAirbyte LangChain Document Loading Webinar
By
–
Document Loading Webinar with @AirbyteHQ Need a last-minute way to celebrate Pi Day? Join a webinar focused on document loading with PyAirbyte and LangChain tomorrow 3/14 at 10am PDT. Features our founding engineer @eyfriis and the team behind PyAirbyte, @aaronsteers and
-
Test Prompts LangSmith Playground Generalization
By
–
🛝 Execute a Test Run in the LangSmith Prompt Playground🛝
— LangChain (@LangChain) 13 mars 2024
With this new LangSmith feature, you can test your prompt over a series of inputs to see how well it generalizes across different contexts or scenarios.
Furthermore, you can compare the outputs of your runs to… pic.twitter.com/5rEczY0Z7UExecute a Test Run in the LangSmith Prompt Playground With this new LangSmith feature, you can test your prompt over a series of inputs to see how well it generalizes across different contexts or scenarios. Furthermore, you can compare the outputs of your runs to
-
LangServe Introduces New Chat-Focused Playground Feature
By
–
💬🛝 LangServe Chat Playground 💬🛝
— LangChain (@LangChain) 12 mars 2024
We've added a brand-new, chat-focused playground to LangServe. Any chain that takes chat input/output can use it.
It supports streaming and message history editing, as well as feedback and sharing traces publicly with LangSmith.
Enable it by… pic.twitter.com/60YYNOzGNYLangServe Chat Playground We've added a brand-new, chat-focused playground to LangServe. Any chain that takes chat input/output can use it. It supports streaming and message history editing, as well as feedback and sharing traces publicly with LangSmith. Enable it by
-
Graph Databases and LLMs Integration in LangChain
By
–
Use Case: Graph DBs & LLMs Using a graph database in association with LLMs can open the gates for allowing your LLM to access more complex relationships, and queries. Because of this immense potential, we just added in depth use case documentation to LangChain JS/TS:
-
Building RAG Chatbots with LangChain and OpenAI
By
–
Check out this detailed walkthrough on building a chatbot with RAG, using LangChain and OpenAI! @qdrant_engine
-
Client-Side PDF Chat with RAG and Vector Store
By
–
🏠 Fully Client-Side Chat Over Documents
— LangChain (@LangChain) 11 mars 2024
This app reads the content of an uploaded PDF, chunks it, adds it to a vector store, and performs RAG – all client side.
By our own @Hacubu (trending on GitHub!)https://t.co/oolcWyoubV pic.twitter.com/RFZsv09J4wFully Client-Side Chat Over Documents This app reads the content of an uploaded PDF, chunks it, adds it to a vector store, and performs RAG – all client side. By our own @Hacubu (trending on GitHub!) https://
github.com/jacoblee93/ful
ly-local-pdf-chatbot
… -
Improving LLM Reliability Through Evaluation Driven Development
By
–
Iterating Towards LLM Reliability with Evaluation Driven Development If you've interacted with the LangChain GitHub repo, you may have noticed a helpful GitHub bot called Dosu You may have also noticed that it's been improving over time! In this blog @devstein64 dives into
-
Fast RAG Application with Ollama and Nomic Embedding Model
By
–
Crazy FAST RAG with Ollama, Nomic Embedding Model, Groq API Cool attempt by @mesudarshan to create a really really fast RAG application. Utilizes a lot of OSS models and frameworks! YouTube: https://
youtube.com/watch?v=TMaQt8
rN5bE
… GitHub Repo: https://
github.com/sudarshan-koir
ala/rag-chat-with-pdf
…