2/ Reflexion The actor reflects on each response, using citations for more actionable critique. Reflections stored in chat history as an "episodic memory buffer" to help the agent learn from past iterations. This better steers the generator in responding to the feedback.
@langchain
-
Language Agent Tree Search: Balancing Exploration and Reward
By
–
3/ Language Agent Tree Search (LATS) Algorithm combines reflection and Monte-Carlo tree search to find the “best” trajectory for a task. The search process balances exploration and expected reward. It has 4 main steps: 1. Select: pick the best next actions based on the
-
Reflection Agents Improve AI System Success Rates
By
–
Reflection Agents Reflection can improve the success rate of agents and similar AI systems by instructing the agent to explicitly critique and learn from past actions. This has been shown to improve outcomes across a number of domains, from program synthesis to multi-step
-
LLM Reflection Architecture: Generator and Reflector Pattern
By
–
1/ Basic Reflection Two LLM nodes: a generator and a reflector. The generator tries to answer the request, while the reflector offers constructive criticism. Python: https://
github.com/langchain-ai/l
anggraph/blob/main/examples/reflection/reflection.ipynb
…
Youtube: https://
youtube.com/watch?v=v5ymBT
XNqtk&t=48s
… -
AI21 Jurassic-2 and Task-Specific Models in LangChain
By
–
@AI21Labs Foundation and Task-Specific Models Unlock the full potential of AI21's Jurassic-2 and Task-Specific models directly in LangChain! Effortlessly build and scale generative AI applications that meet today's business needs. No NLP expertise required; just seamless
-
JSON Agents with Mixtral: Open Source Graph Database Navigation
By
–
JSON Agents with @ollama & LangChain Explore the cutting-edge application of the Open Source Mixtral model from @MistralAI to an agent that navigates a graph database in our latest blog. Authored by @tb_tomaz from @neo4j
, this insightful post demonstrates how leveraging a -
RAG Query Translation: Decomposition Approaches From Scratch
By
–
RAG From Scratch: Query Translation (Decomposition) Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is the third in our videos on Query Translation, focused on approaches for decomposition w/ ideas from Least-to-Most
-
Upsy: Open Source Slack Bot for Conversation Memory
By
–
Upsy: Your new mate on Slack Upsy is an open source Slack bot that remembers your conversations to provide fast, accurate answers whenever you have a question. Fully open source! Great work by the @upstash team to create this template!
-
LangChain Embeddings and Vectorstores Guide RAG
By
–
LangChain 101: Embeddings and Vectorstores Embeddings and Vectorstores are key to understanding RAG Good community blog by Ivan Reznikov (3rd one in the series) explaining these concepts https://
pub.towardsai.net/langchain-101-
part-3b-talking-to-documents-embeddings-and-vectorstores-c37d460f1519
… -
Enhancing If-Statements Through LLM Prompt Classification With Ollama
By
–
Supercharging If-Statements With Prompt Classification Using Ollama and LangChain Lumos is an LLM co-pilot for browsing the web, powered by local LLMs There are a lot of small architectural decisions made that contain a ton of nuance, and so we're super excited to post