Matryoshka Retriever A recent blog post by @supabase described a new technique for higher performance retrieval, without compromising accuracy. So we've just released a new retriever in LangChain.js which implements this exactly! Use any vector store, and two embedding
@langchain
-
LangChain Matryoshka Retriever Documentation and Supabase Integration
By
–
Read the JS docs: https://
js.langchain.com/docs/modules/d
ata_connection/retrievers/matryoshka_retriever
…
Supabase article: -
Query Analysis Techniques for RAG Systems with LLMs
By
–
Query Analysis In OpenAI's retrieval talk on DevDay, they mention a bunch of strategies they experimented with 3 of these can be classified as **query analysis** a RAG technique that is becoming popular to do with LLMs We've added a docs deep-dive on this We cover six
-
Advanced RAG Series: Indexing Optimization Techniques
By
–
Advanced RAG series: Indexing Indexing is a huge part or RAG. Lot's of different stuff to optimize: 1. Chunk Optimization
2. Multi-representation indexing
3. Specialized Embeddings
4. Hierarchical Indexing Great article by @divyanshu_van diving into all these topics! Blog: -
Models Support Function Calling Documentation Updates
By
–
As more and more models support function calling, we're updating our docs to highlight them all! Function calling
-
LangChain Founders Share Building Story at ClickHouse Meetup
By
–
Want to hear more about the story of how we built LangChain? Come join us at the ClickHouse meetup in SF on March 4! Note: Signup required before this Friday, March 1st. https://
meetup.com/clickhouse-sil
icon-valley-meetup-group/events/299058486/
… -
LangSmith Expands Custom Model Cost Tracking Capabilities
By
–
Custom Model Costs in LangSmith ✎ We've expanded token-based cost tracking to be fully customizable! This means that, in addition to tracking costs for OpenAI models, you can track costs for *any* model that you use. To register a model for cost tracking, navigate to
-
Building JSON Agents with Ollama LangChain Neo4j
By
–
JSON-based Agents With Ollama & LangChain Learn to implement a Mixtral agent that interacts with a graph database Neo4j through a semantic layer This work by @tb_tomaz is great for a few reasons: – Shows how to build an agent with an OSS model
– Shows how to build and use a -
Semantic Chunking: Three Methods for Document Splitting
By
–
Semantic Chunking Semantic chunking using embedding distances between sentences to figure out how to split a document. A key decision is what threshold to split at. We now support three methods: Percentile
Interquartile Range
Standard Deviation Big shout out to -
Self-Corrective LLM Coding Assistant Build Tutorial
By
–
Building a self-corrective coding assistant from scratch @RLanceMartin walks through building an LLM powered system that writes code, checks the code programmatically, and then self-corrects if there's an error A complex topic, but a great video!