LangSmith Tracing and Evaluation in TypeScript It's now easier than ever to trace non-LangChain TS code and run evaluations in LangSmith! We've added a cookbook here: https://
github.com/langchain-ai/l
angsmith-cookbook/blob/main/typescript-testing-examples/traceable-example/LangSmith_TS_Demo-Traceable.ipynb
… For tracing, we've added – wrapOpenAI(new OpenAI()) allows you to call @OpenAI
OPEN SOURCE
-
LangSmith Tracing and Evaluation Tools Now Available for TypeScript
By
–
-
Natural Language to SQL with Local LLM Models
By
–
natural language -> sql, visualizations, analytics impressive stuff. uses a local LLM
-
FireFunction V1: Open-Weights Function Calling Model from Fireworks
By
–
FireFunction V1 – a new, open-weights function calling model from @FireworksAI_HQ Returning structured outputs is (a) hard, (b) incredibly useful Excited to highlight **4** different ways to use this model with LangChain #1: Function Calling with LangChain JS Cookbook:
-
AstraDB Vector Database Integration with LangChain
By
–
@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
… -
Implementing Reflexion for Your App in LangGraph
By
–
1/ See how to implement Reflexion for your app in LangGraph at the links below: Python: https://
github.com/langchain-ai/l
anggraph/blob/main/examples/reflexion/reflexion.ipynb
…
Youtube: https://
youtube.com/watch?v=v5ymBT
XNqtk&t=299s
… H/T @WHinthorn -
LoRAX v0.8 Release: JSON Structured Outputs Support Added
By
–
New minor release for #LoRAX, our open-source framework for serving 100s of #LLMs on a single #GPU:
LoRAX v0.8 now supports structured outputs (#JSON mode) courtesy of #Outlines! -
TheProfessor V1: Abacus Introduces LLM Merging Technology
By
–
Introducing TheProfessor (V1) From Abacus, an LLM cocktail! We’ve recently talked about a fascinating property of LLMs, merging, where you can combine different layers from LLMs without needing pre-training. The merged LLM will then show combined properties of the different
-
LangChain Launches People Page to Recognize Community Contributors
By
–
We've added a People page! There are some incredible humans from all over the world who have been instrumental in helping the LangChain community flourish, and we'd like to do more to recognize them and thank them for their efforts. To start, we're highlighting top
-
Input Output Paragraph State Changes Open Source
By
–
The input is generally the previous paragraph. The paragraph's outcome is its output. If a paragraph hasn't changed your input state, then there's the probability that the paragraph isn't necessary." https://
technicallywewrite.com/2024/01/29/set
hkenlon
… #opensource -
Machine Learning and Predictive Analytics with Python Libraries
By
–
Machine Learning, Predictive Analytics, and Forecasting: You can leverage Python libraries like scikit-learn & statsmodels to apply machine learning, predictive analytics, and forecasting techniques such as regression analysis, time series modeling, and more.