Improvement on Airtable, Qdrant, PGVector, Milvus, LocalAI Thanks for all contributors, there have been lots of improvements on other node integrations. Read more from patch note: https://
github.com/FlowiseAI/Flow
ise/releases/tag/flowise1.4.10
…
AI
-

Flowise 1.4.10 Improves Airtable, Qdrant, PGVector, Milvus
By
–
-
AstraDB Vector Database Integration for Generative AI RAG
By
–
💾 AstraDB@DataStax AstraDB is a NoSQL and Vector DB for Generative AI, powered by Apache Cassandra.
— FlowiseAI (@FlowiseAI) 17 janvier 2024
Use it within Flowise as a vector store for your RAG apps.
Thanks goes to hakeemsyd who contributed to this integration! pic.twitter.com/I6a5AwlRjIAstraDB @DataStax AstraDB is a NoSQL and Vector DB for Generative AI, powered by Apache Cassandra. Use it within Flowise as a vector store for your RAG apps. Thanks goes to hakeemsyd who contributed to this integration!
-

Vectara Introduces Max Marginal Relevance in Flowise Node
By
–
Vectara MMR Thanks to @ofermend
, max marginal relevance is now available to be used on Vectara node in Flowise, more coming soon! -

LangChain Rewrites Chains and Agents with Expression Language
By
–
LCEL We've completely re-written our chains and agents using the new LangChain Expression Language. This ensure better composability, optimised parallel execution, and many other benefits.
-

Global Variables in Custom Tool Functions for API Integration
By
–
Global variables Create variables that can be used in Custom Tool Function: `$vars.` This is useful when you need the function to get dynamic variables, particularly when making API calls. https://
docs.flowiseai.com/integrations/t
ools/custom-tool#pass-variables-to-function
… -
LangChain v1.4.10 Release: New Features and Improvements
By
–
1st release in 2024 v1.4.10: Global variables LCEL AstraDB Vectara MMR Langfuse SessionId Improvement on Airtable, Qdrant, PGVector, Milvus, LocalAI
-

Multimodal Deep Learning Models for Asynchronous Data Streams
By
–
A deep learning paper from our team on how to build multimodal models, where data for individual modalities arrives at different speeds, by combining powerful pretrained text, image and video models. Useful for robotics. Congrats @konradzolna @serkancabi @yutianc Eric, Claudio,… https://t.co/vPmZpDkve3
— Nando de Freitas (@NandoDF) 17 janvier 2024A deep learning paper from our team on how to build multimodal models, where data for individual modalities arrives at different speeds, by combining powerful pretrained text, image and video models. Useful for robotics. Congrats @konradzolna @serkancabi @yutianc Eric, Claudio,
-
Building Useless Apps vs Solving Real Problems
By
–
"Why are people making all this useless stuff? Maybe they should focus on solving real problems!" – HN commenter working on his 3rd unshipped to-do app
-
LLMLingua: Microsoft Tool on Hugging Face
By
–
HF:
https://huggingface.co/spaces/microsoft/LLMLingua -
Open-Source Developer AI Meetup in San Francisco January 23
By
–
Come to our open-source and local developer AI meetup in SF on Tuesday, January 23rd! https://
lu.ma/devs1 We're co-hosting with our friends from @ollama
, @continuedev
, @langchain
, @huggingface and more. Space is limited, so make sure to register: