@AstraDB Cassandra-based Vector DB Explore the langchain-astradb integration package! Harness the serverless, vector-capable database built on Apache Cassandra for scalable NoSQL solutions enhanced with the power of vector similarity search. https://
python.langchain.com/docs/integrati
ons/vectorstores/astradb
…
LLMS
-
AstraDB Vector Database Integration with LangChain
By
–
-
Reflexion: Agents Learn to Reflect and Self-Correct
By
–
2/ Paper: Reflexion, by Shinn, @ashwingop
, @ShunyuYao12 , et. al. https://
arxiv.org/abs/2303.11366 -
Reflexion: Language Agents Learn via Verbal Reinforcement
By
–
Reflexion: Language Agents with Verbal Reinforcement Learning Reflexion lets LLMs learn without updating its weights. Its actor reflects on each agent decision, using citations and other targeted feedback to generate actionable critique. Reflections are stored in chat history
-
Sequence Text Embeddings vs Word Embeddings Explained
By
–
i'm talking about sequence text embeddings not word embeddings
-
Sequence-Based Models Capture High-Level Features
By
–
don't think so! these are based on sequences so they should capture much higher-level features
-
RAG Production Challenges and Enterprise LLM Solutions
By
–
A common enterprise use of #LLMs is in RAG (Retrieval Augmented Generation) applications on an organization's own custom #KnowledgeBase. They are difficult to put in production. @AbacusAI addresses the key challenges for you. See how in their thread below:
-
HyDE Query Translation Technique for RAG Systems
By
–
RAG From Scratch: Query Translation (HyDE) Our RAG From Scratch video series walks through impt RAG concepts in short / focused videos w/ code. This is our final video on Query Translation, focused on Hypothetical Document Embeddings (HyDE) from Gao et al. Problem:
-
ChatGPT Outages and Performance Issues Discussion
By
–
Loving these tests! Curious when you recorded these? Only asking because I know that yesterday ChatGPT had pretty significant outages/performance issues
-
Gemini’s 750K Token Processing Unlocks Major AI Capabilities
By
–
Watching Gemini ingest 750,000+ tokens in ~1 minute and then spit out near-perfect details (on things I wouldn't have even noticed) was a real tipping point for me. SO many capabilities just unlocked. It's going to be a wild year.
-
Groq LPU Achieves 500 Tokens Per Second Inference Speed
By
–
🏎️ Incredible Speeds with Groq's LPU-Powered Inference 🕔
— LangChain (@LangChain) 22 février 2024
The langchain-groq package exposes inference capabilities powered by @GroqInc's Language Processing Units (LPUs), soaring to new heights with up to 500 tokens per second on this @MistralAI Mixtral model. Welcome to the… pic.twitter.com/2aBTv7KCfPIncredible Speeds with Groq's LPU-Powered Inference The langchain-groq package exposes inference capabilities powered by @GroqInc
's Language Processing Units (LPUs), soaring to new heights with up to 500 tokens per second on this @MistralAI Mixtral model. Welcome to the