LangChain4j @langchain4j Twitter profile

Last Seen Profiles

@SonmezMMA

@Scott_Hadley

@FKim90

@ugomonye

@ovo_ynn

@AfcKerala

@tusknyc

@shaydechelle

@IndyMayorJoe

@thetimes

@artytoastVT

@soobstr

@yjwthinker

@wallisweaver

@RMadridFrance_

@JoeGalliNews

@gabrielrufian

@TheMrBirch

@chef_T_bow

@garymasonglobe

@Met_Komori

@AthleticClub

@denizliso

@HuskerNation__

@MMikeMMa

@yolorenaaa

@PlasticJeezus

@TeamCollectionS

@The1st_Montana

@SweetMiorita

@PrblyNoteWorthy

@twan1021

@MrJoeIconis

@BBCBreakfast

@zeshiNNNS

@PakPoppa

LangChain4j

@langchain4j

9 days

Woohoo 🥳 #LangChain4j celebrates its first anniversary today! What an exciting year it has been! Generative AI in Java has made a significant leap forward, and we are very proud to be part of this! It wouldn't have been possible without all the help and support from the…

18

39

187

LangChain4j

@langchain4j

3 months

Finally, it's the weekend🎉Time for experiments! Using GPT-4 to evaluate content generated by Llama2. Seems to integrate well with standard JUnit/AssertJ tests. WDYT?

4

7

71

LangChain4j

@langchain4j

2 months

#LangChain4j 0.29.0 is out! 🎉 We have a lot of cool stuff here: 1. #EasyRAG : an easy way to get started with RAG. It can't get any easier! 2. Advanced RAG with @Azure AI Search 3. Seamless integration into @SpringBoot applications 4. Tools/functions support for @MistralAI 5.…

2

14

53

LangChain4j

@langchain4j

5 months

🎁Christmas presents from #LangChain4j ☕🦜 are here!🎉 Support for @GoogleAI Gemini, @OpenAI DALL·E, updated @Azure , @neo4j and lots of other good stuff in version 0.25.0: Enjoy your holidays! 🎄🎅

GitHub - langchain4j/langchain4j: Java version of LangChain

Java version of LangChain. Contribute to langchain4j/langchain4j development by creating an account on GitHub.

github.com

4

15

53

LangChain4j

@langchain4j

7 months

First public debute of #LangChain4j 🎉 Many thanks to our awesome presenter @LizeRaes 🙏 and extra thank to organiser of @Devoxx for an opportunity to demonstrate the possibles of the library💪

Java Meets AI: A Hands On Guide to Building LLM Powered Applications...

Are you interested in building applications powered by Large Language Models (LLMs) using Java and Spring Boot?You can create your own AI-powered chatbots, p...

www.youtube.com

0

18

49

LangChain4j

@langchain4j

3 months

LangChain4j 0.26.1 is now available🎉 In this release, we are excited to introduce: - Advanced RAG support - Multimodality with image inputs - Integrations with @MistralAI , @cohere , @Azure AI Search, @qdrant_engine , @github - And much more:

Release 0.26.1 · langchain4j/langchain4j

New Core Features: Advanced RAG by @langchain4j in #538 Multimodality: support image inputs by @langchain4j in #428 ConversationalRetrievalChain: adding metadata in the prompt by @mateusscheper in...

github.com

0

10

47

LangChain4j

@langchain4j

2 months

LangChain4j 0.28.0 is here! 🥳 In this release: - 2 new integrations: @AnthropicAI and @Zhipu_AI - The @Google Gemini integration now supports tools (functions)! - A new core feature: "metadata filtering", with initial support for @Milvusio , @Elastic , and in-memory embedding…

7

13

48

LangChain4j

@langchain4j

2 months

Great post on design patterns for LLM-powered applications:

Generative AI Design Patterns: A Comprehensive Guide

Reference architecture patterns and mental models for working with Large Language Models (LLM’s)

towardsdatascience.com

0

7

43

LangChain4j

@langchain4j

2 months

Wow, we are trending📈 2K+🌟 A Big Thank You to everyone who contributed to and used #LangChain4j !🤗

2

7

41

LangChain4j

@langchain4j

3 months

If you are looking for some fun weekend learning, I recommend short courses on @DeepLearningAI :

Short Courses | Learn Generative AI from DeepLearning.AI

Take your generative AI skills to the next level with short courses from DeepLearning.AI. Enroll today to learn directly from industry leaders, and practice generative AI concepts via hands-on...

www.deeplearning.ai

1

7

38

LangChain4j

@langchain4j

3 months

Great tutorial from @kenkousen on how easy it is to use tools (functions) with LangChain4j:

The Definitive Guide to Tool Support in LangChain4J

LangChain4J lets you add classes and methods that an AI model can invoke automatically. That allows you to supply functions that do well what the AI model do...

www.youtube.com

0

9

36

LangChain4j

@langchain4j

25 days

#LangChain4j 0.30.0 is out! This is a small ad-hoc release. Many cool features are brewing, so stay tuned! In this release: - AI Services improvements - Support for tools in @AnthropicAI - Many bug fixes A short thread 🧵

1

8

33

LangChain4j

@langchain4j

3 months

0.27.0 is out🥳 Integrations with @Infinispan @MongoDB @nomic_ai , updates to @DataStax AstraDB and more:

Release 0.27.0 · langchain4j/langchain4j

New Integrations Embedding Stores Integration with Infinispan by @karesti in #552 Integration with MongoDB by @Martin7-1 in #535 Embedding Models NomicEmbeddingModel by @langchain4j in #592 Not...

github.com

2

6

32

LangChain4j

@langchain4j

8 months

Thanks to our awesome contributors there are lots of new integrations in LangChain4j 0.23.0! @AstraDB @cassandra @elastic @milvusio @Redisinc @vespaengine

GitHub - langchain4j/langchain4j: Java version of LangChain

Java version of LangChain. Contribute to langchain4j/langchain4j development by creating an account on GitHub.

github.com

1

11

26

LangChain4j

@langchain4j

11 months

Did you know that you can moderate texts or messages for free using the OpenAI moderation API? Now, you can do this hassle-free with #LangChain4j :

1

4

24

LangChain4j

@langchain4j

3 months

Do you want to understand RAG? Here is an excellent tutorial from @sivalabs !

Siva

@sivalabs

3 months

LangChain4j Retrieval-Augmented Generation (RAG) Tutorial #java #GenerativeAI @langchain4j

1

7

64

1

4

24

LangChain4j

@langchain4j

2 months

A good beginners guide to running local LLMs:

From the LocalLLaMA community on Reddit

Explore this post and more from the LocalLLaMA community

www.reddit.com

0

6

24

LangChain4j

@langchain4j

3 months

I highly recommend checking this out if you're wondering how to design the architecture of your LLM application:

DataStax

@DataStax

3 months

Your guide to LLM agent reference architecture is here! 📍🗺 We teamed up with @LangChainAI to provide: ◆ Common Gen AI design patterns and use cases ◆ In-depth architectural examples ◆ Important considerations to keep in mind Grab your copy ➡️

3

8

72

1

4

23

LangChain4j

@langchain4j

4 months

@sebi2706 Hi @sebi2706 , here is a good place to start: Current implementation in langchain4j is very primitive, but we are already working on the next version that will allow for advanced methods.

Deconstructing RAG

Context In a recent overview on the state of large language models (LLMs), Karpathy described LLMs as the kernel process of a new kind of operating system. Just as modern computers have RAM and...

blog.langchain.dev

0

1

21

LangChain4j

@langchain4j

2 months

1. Easy RAG RAG can be hard to understand and implement for beginners. @dandreadis challenged us to make RAG super easy. So, we made it easy! To get started with RAG, you do not have to learn about parsers, splitters, embeddings, and other stuff. Just point to your documents,…

1

2

18

LangChain4j

@langchain4j

7 months

Very excited about our talk on #LangChain4j tomorrow! Many thanks to @Stephan007 for organising #Devoxx ! See you tomorrow at 11:50!

0

4

17

LangChain4j

@langchain4j

2 months

OK, we weren't completely honest when we said "Easy RAG can't get any easier"🤭 @janmartiska from the @QuarkusIO team went further and made it even easier, great job! More details here:

1

7

16

LangChain4j

@langchain4j

21 days

@mariofusco Current LLM architectures are very primitive, here is a great video on this topic:

Yann Lecun: Meta AI, Open Source, Limits of LLMs, AGI & the Future of...

Yann LeCun is the Chief AI Scientist at Meta, professor at NYU, Turing Award winner, and one of the most influential researchers in the history of AI. Please...

www.youtube.com

0

5

15

LangChain4j

@langchain4j

2 months

How are you currently using (or planning to use) #LangChain4 ?

In bare Java

36

With Quarkus

67

With Spring Boot

102

Other framework (comment)

18

9

18

14

LangChain4j

@langchain4j

10 months

We're excited to announce experimental support for in-process embeddings in LangChain4j! Now, you can perform text embedding directly within your Java application. Yes, within the same JVM process! There's no need for GPUs or external services, nor any network overhead. 1/5

1

5

15

LangChain4j

@langchain4j

2 months

3. Seamless integration into @SpringBoot applications @geoand86 from the @QuarkusIO team did an excellent job making AI Services much easier to use in Quarkus applications. Since many of our users use Spring Boot, we decided to introduce a similar feature with #LangChain4j …

1

14

LangChain4j

@langchain4j

2 months

2. Thanks to @glaforge , @Google Gemini integration now supports tools (functions)! An example can be found here:

1

5

14

LangChain4j

@langchain4j

7 months

Many thanks to @glaforge for the simple and elegant explanation of how RAG works! It was an awesome talk about LLM use cases in Java!

0

4

13

LangChain4j

@langchain4j

11 months

There is now #LangChain for #Java ! #LangChain4j

GitHub - langchain4j/langchain4j: Java version of LangChain

Java version of LangChain. Contribute to langchain4j/langchain4j development by creating an account on GitHub.

github.com

0

4

13

LangChain4j

@langchain4j

3 months

How can you ensure that your LLM-powered app behaves as expected? How do you determine if your prompt template is good enough? How can you tell if your RAG setup is optimal? What is the ideal segment size for your data? Overlap? Which RAG techniques provide the best results for…

2

12

LangChain4j

@langchain4j

19 days

NEW RAG benchmark including LLaMa-3 70B and 8B, CommandR, Mistral 8x22b:

From the LocalLLaMA community on Reddit: NEW RAG benchmark including LLaMa-3 70B and 8B, CommandR,...

Explore this post and more from the LocalLLaMA community

www.reddit.com

1

2

12

LangChain4j

@langchain4j

25 days

1. AI Services improvements Thanks to @mariofusco , AI Services have become more flexible and powerful! Now, you can define system messages dynamically. This is especially helpful if you wish to implement a state machine and/or use different system messages for different…

1

2

11

LangChain4j

@langchain4j

3 months

@sivalabs Thank you! Lots of examples can be found here: We are also working on improving our docs:

LangChain4j | LangChain4j

Description will go into a meta tag in

docs.langchain4j.dev

0

10

LangChain4j

@langchain4j

2 months

How Chunk Sizes Affect Semantic Retrieval Results

An in-depth introduction to the concept of “chunking” and its relevance when working with Large Language Models (LLMs).

ai.plainenglish.io

1

3

10

LangChain4j

@langchain4j

3 months

A few LLM hallucination leaderboards:

GitHub - vectara/hallucination-leaderboard: Leaderboard Comparing LLM Performance at Producing...

Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents - vectara/hallucination-leaderboard

github.com

0

5

10

LangChain4j

@langchain4j

2 months

4. Tools/functions support for @MistralAI @c_zela did a great job by adding a support for tools/functions in @MistralAI integration! Now tools can be used with: - @Azure OpenAI - @Google Gemini - @LocalAI_API - @MistralAI - @OpenAI - @Baidu_Inc Qianfan - #ZhipuAI More…

1

2

9

LangChain4j

@langchain4j

4 months

@Stephan007 @VoxxedCERN Advanced RAG is coming to LangChain4J pretty soon!

1

2

10

LangChain4j

@langchain4j

2 months

@ichbinSagar Awesome! Please let us know how it went and which pain points did you encounter, so that we can improve! BTW, we plan to release an "Easy RAG" feature very soon (in 1-2 weeks), here is a sneak peek:

Easy RAG by langchain4j · Pull Request #686 · langchain4j/langchain4j

Easy RAG Example Implementing RAG applications is hard. Especially for those who are just getting started exploring LLMs and RAG. This PR introduces an "Easy RAG" feature that should help...

github.com

2

1

10

LangChain4j

@langchain4j

2 months

5. Integration with @AzureCosmosDB A new embedding store integration with @AzureCosmosDB ! More details here:

Julien Dubois

@juliendubois

2 months

Thanks to my colleague Zhiyong Li (from Microsoft DevDiv China), we will soon have Spring Boot support in @langchain4j for Azure OpenAI and Azure AI Search! This will greatly simplify configuration!

2

1

8

1

7

LangChain4j

@langchain4j

4 months

Good point regarding OpenAI's text-embedding-ada-002. There are open-source models that outperform OpenAI (see MTEB leaderboard), and they are free and available offline! Some of these popular models are available in LangChain4j out of the box, making embedding straightforward in…

Omar Sanseviero

@osanseviero

4 months

You keep reading about sentence embeddings, but you might still not know exactly what they are. You are not alone! 🤗 I wrote a step-by-step walkthrough with code, math, applications, and memes. Kick off your year understanding what embeddings are!

16

100

651

1

3

9

LangChain4j

@langchain4j

4 months

If you're curious about embeddings and want to develop an intuition for them, check out this visualization tool I've recently been working on:

Omar Sanseviero

@osanseviero

4 months

You keep reading about sentence embeddings, but you might still not know exactly what they are. You are not alone! 🤗 I wrote a step-by-step walkthrough with code, math, applications, and memes. Kick off your year understanding what embeddings are!

16

100

651

0

5

8

LangChain4j

@langchain4j

2 months

3. We've added a new core feature called "metadata filtering". If your documents/segments contain metadata entries, you can now apply strict filters when doing similarity search in embedding store. Think of it as a "WHERE" clause in SQL. This feature is quite generic and has many…

1

8

LangChain4j

@langchain4j

5 months

@EdduMelendez @testcontainers Not helped, you did it all yourself! Thank you so much, you're a @testcontainers wizard! I've learned a lot from your PRs :)

0

7

LangChain4j

@langchain4j

3 months

Cohere reranker is already supported by LangChain4j, looking forward to integrating @lateinteraction 's ColBERT!

virat

@virattt

3 months

I have found my RAG rerankers I spent the past few days testing rerankers and there are two that I'll use going forward. • Cohere • ColBERT Both performed as well as GPT-4 in reranking quality and are lightning fast. Cohere's avg inference time was ~200ms. It's…

18

29

275

0

2

6

LangChain4j

@langchain4j

2 months

@sebi2706 @QuarkusIO You should be able to extract the POJO even without manually explaining the JSON format. JSON schema and formatting instructions are generated automatically by AiServices and appended to the prompt. You can enable logging on LLM level and see the final prompt sent to the LLM.

1

0

7

LangChain4j

@langchain4j

9 months

#LangChain4j 0.22.0 is out! - Integration with @GoogleAI Vertex AI - Offline text classification with embeddings - Reworked document splitters - In-process embedding models can now embed longer texts - In-memory embedding store can now be easily persisted - And more:…

2

3

7

LangChain4j

@langchain4j

2 months

gpt-4-0125-preview keeps calling the get_current_weather function with the "felsius" temperature unit, although only "fahrenheit" and "celsius" are allowed 😆 Now I have to disable this test to unblock the release 🤦‍♂️

2

7

LangChain4j

@langchain4j

10 months

This is how simple it is to begin using #LLMs in #Java with #LangChain4 :

1

0

7

LangChain4j

@langchain4j

3 months

How to ensure that the test is "reproducible": 1. Use a static "seed" parameter. This is supported by many LLM providers, such as OpenAI, VertexAI, Mistral, Ollama, etc. 2. Check the system_fingerprint. 3. Set temperature to 0. How to ensure that the test is "diverse": 1. Use…

0

7

LangChain4j

@langchain4j

3 months

@Stephan007 @agishaun 😁 On a serious note, the cost and latency of using 1M tokens is not mentioned here. It is a tradeoff between simplicity, recall, cost, latency. Doing retrieval before LLM call is an incredibly low-hanging fruit though.

1

0

7

LangChain4j

@langchain4j

11 months

Defining prompt templates has never been so easy in Java: #Java #AI #LLM #LangChain #LangChain4j

0

3

6

LangChain4j

@langchain4j

2 months

Fantastisch!

Michael Kramarenko

@Michael47242613

2 months

Generative AI - Teil 2: Hello World! | Lab Coffee #8 about @langchain4j 0.25 and Spring Boot app in Kotlin via @YouTube

0

1

4

0

2

6

LangChain4j

@langchain4j

3 months

@S1lv3rd3m0n @Infinispan @MongoDB @nomic_ai @DataStax Right? We are lucky to have so many amazing contributors! And releases will become smaller, but more frequent.

0

6

LangChain4j

@langchain4j

9 months

🚀 #LangChain4j 0.19.0 is out! ✅ Integration with @weaviate_io ✅ DOC/XLS/PTT document loaders ✅ Separate chat memory per user ✅ Support for custom in-process embedding models ✅ Many other improvements Details ➡️

Release 0.19.0 · langchain4j/langchain4j

Weaviate integration by @Heezer DOC, XLS and PPT loaders by @oognuyh Separate chat memory for each user Custom in-process embedding models Added lots of Javadoc Added DocumentTransformer and it'...

github.com

0

2

6

LangChain4j

@langchain4j

10 months

#LangChain4j 0.10.0 is out! Now you can add your custom knowledge base to "AI Services". Relevant information will be automatically retrieved and injected into the prompt. This way, the LLM will have a context of your data and will answer based on it!

0

2

6

LangChain4j

@langchain4j

10 months

Hello World with #LangChain4j : #LLM #AI #Java #SpringBoot

LangChain4j: Supercharge your Java application with the power of AI

Hello Java devs! Are you interested in building applications powered by Large Language Models (LLMs) using Java and Spring Boot?

link.medium.com

0

5

6

LangChain4j

@langchain4j

3 months

What are you missing the most in LangChain4j for implementing RAG? Please provide more feedback in the comments!

Docu/examples/cookbook

20

Advanced RAG features

6

Tools for RAG evaluation

10

Other (in the comments)

1

4

6

LangChain4j

@langchain4j

2 months

Great to have a yet another GPT-4-level alternative! BTW, @AnthropicAI Claude Opus and Sonnet are available in #LangChain4j 0.28.0!

lmsys.org

@lmsysorg

2 months

[Arena Update] Our community has cast 20,000 more votes for Claude-3 Opus and Sonnet, showing great enthusiasm for the new Claude model family! Claude-3-Opus now shares the top-1* rank with GPT-4-Turbo, while Sonnet has surpassed GPT-4-0314. Big congrats @AnthropicAI 🔥 In…

21

96

546

0

1

6

LangChain4j

@langchain4j

2 months

2. Advanced RAG with @Azure AI Search @juliendubois worked hard to add this to #LangChain4j , so now you can use not only vector search, but also full-text search, hybrid (full-text + vector) search and re-ranking with @Azure AI Search! More details here:

Julien Dubois

@juliendubois

2 months

Advanced RAG is coming to @langchain4j with Azure AI Search, including semantic re-ranking! Thanks to @pmc and his team for their help!

1

2

13

2

3

6

LangChain4j

@langchain4j

11 months

We have added new cool feature called "AI Services"! Now you can hide complicated logic of communication with LLM behind a simple Java interface! Check it out:

0

3

5

LangChain4j

@langchain4j

10 months

LangChain4j 0.8.0 release is here! - Added Spring Boot Starter - Added support for HuggingFace models More details:

Release 0.8.0 · langchain4j/langchain4j

Added Spring Boot Starter: https://github.com/langchain4j/langchain4j-examples/blob/main/spring-boot-example/src/test/java/dev/example/CustomerSupportApplicationTest.java Added support for HuggingF...

github.com

0

1

5

LangChain4j

@langchain4j

23 days

@juliendubois Contribution guidelines as well 🙂

langchain4j/CONTRIBUTING.md at main · langchain4j/langchain4j

Java version of LangChain. Contribute to langchain4j/langchain4j development by creating an account on GitHub.

github.com

0

2

5

LangChain4j

@langchain4j

10 months

OpenAI Functions are very powerful! Check this conversation between customer and customer support agent (AI): [User]: Hi, I forgot when my booking is. [Agent]: Sure, I can help you with that. Can you please provide me with your booking number, customer name, and surname? 1/6

1

5

LangChain4j

@langchain4j

11 months

We have added new cool feature called "AI Services"! Now you can easily extract structured information from unstructured text! Check it out:

0

3

5

LangChain4j

@langchain4j

21 days

Great stuff! This reminds me of a flow that @IrynaLiubarska and I developed for our IntelliJ IDEA AI-assisted coding plugin a while ago. Apart from the basic features like "explain this code," "refactor this code," and "document this code," we wanted a more systematic way of…

LangChain

@LangChainAI

22 days

😍 The recording from our Flow Engineering webinar with @hwchase17 and @itamar_mar is up! "Flow Engineering" is a term that has been gaining in popularity recently. The first time it was mentioned as term was in CodiumAI paper on AlphaCodium, where they…

1

23

111

1

3

5

LangChain4j

@langchain4j

2 months

4. Self-Querying This one is very cool! Building on top of metadata filtering, you can now use an LLM to automatically generate a filter from a natural language query before doing similarity search. This can narrow down the search space and improve the quality of your RAG. More…

1

5

LangChain4j

@langchain4j

4 months

New MTEB leader🔥

AK

@_akhaliq

4 months

Microsoft announces Improving Text Embeddings with Large Language Models paper page: introduce a novel and simple method for obtaining high-quality text embeddings using only synthetic data and less than 1k training steps. Unlike existing methods that…

12

169

977

0

2

5

LangChain4j

@langchain4j

5 months

@alexsotob @LangChainAI Yes, you can run lots of models from HuggingFace using @OLLAMA and @LocalAI_API , @langchain4j has integrations with both. Or any other inference server that exposed OpenAI-compatible API (oobabooga, gpt4all, etc).

1

0

4

LangChain4j

@langchain4j

18 days

@aheritier Hi, thanks a lot for heads up! Indeed, the fix in the spring boot starter was released only for spring boot dependencies. Will do better next time!

0

5

LangChain4j

@langchain4j

9 months

LLaMA finetuned to use tools, performance is close to gpt-3.5-turbo:

GitHub - OpenBMB/ToolBench: [ICLR'24 spotlight] An open platform for training, serving, and...

[ICLR'24 spotlight] An open platform for training, serving, and evaluating large language model for tool learning. - OpenBMB/ToolBench

github.com

0

1

5

LangChain4j

@langchain4j

2 months

6. RAG with @Neo4j knowledge graphs @theawesomenayak did a great job making it possible to use @Neo4j knowledge graphs in a RAG pipeline! Now, LLM can convert a natural language query into a Cypher query, which will be executed on a knowledge graph to retrieve relevant…

2

0

5

LangChain4j

@langchain4j

25 days

2. Support for tools in @AnthropicAI We welcome Anthropic to the club of models that support tools! Here is an example:

langchain4j-examples/anthropic-examples/src/main/java/AnthropicToolsTest.java at main · langchain...

Contribute to langchain4j/langchain4j-examples development by creating an account on GitHub.

github.com

1

5

LangChain4j

@langchain4j

2 months

@marcushellberg Sorry! We're already cooking the next release 😅

1

0

5

LangChain4j

@langchain4j

3 months

@EdduMelendez Thank you @EdduMelendez for keeping us on the bleeding edge! :)

0

4

LangChain4j

@langchain4j

4 months

@jamescalam @LangChainAI Awesome! LangChain (for Java) also has a text classifier powered by embeddings. Simple, but very powerful thing:

1

4

LangChain4j

@langchain4j

3 months

@holdeeer @sivalabs RAG is a very new and still developing concept, so there is no established and definitive metric for determining its readiness for production use. One has to develop their own metrics and decide for themselves. One can use a multitude of "advanced RAG" techniques which improve…

1

0

3

LangChain4j

@langchain4j

3 months

@LizeRaes This is peanuts for you, good luck!

0

4

LangChain4j

@langchain4j

25 days

@marcushellberg Fixed in 0.30.0!

2

0

4

LangChain4j

@langchain4j

2 months

@cakmakum @milvusio Hi again! Your concern regarding inefficiency in Milvus implementation has been addressed in the latest (0.28.0) release. Cheers!

0

4

LangChain4j

@langchain4j

5 months

@agoncal @testcontainers @huggingface @EdduMelendez did something like this in @langchain4j , we are now running models in docker using @OLLAMA . Code:

2

3

4

LangChain4j

@langchain4j

3 months

@LangChainAI @sequoia Congratulations!

0

3

LangChain4j

@langchain4j

9 months

Now any text (e.g. document, message from a user, etc) can be classified completely offline and without any external calls. See example here:

1

0

4

LangChain4j

@langchain4j

10 months

@hwchase17 @Shroominic Java version supports sandboxed code execution as well!

LangChain4j

@langchain4j

10 months

#LangChain4j 0.11.0 is out 🎉 #GPT4 #CodeInterpreter is so cool, but it is not available via the API. To "fix" this, we've added dynamic code execution! Now, the LLM can generate code for tasks that require precise calculations, such as math and string manipulation. 1/3

1

2

0

4

LangChain4j

@langchain4j

3 months

@sivalabs Awesome! You might be interested in the documentation page which I just updated with more examples (I will keep adding more and more in the coming days): Thanks a lot for these excellent articles, you are doing much better job than me documenting this😅

1

4

LangChain4j

@langchain4j

10 months

[User]: 123-457 [Agent]: Thank you for providing the booking number. May I also have your customer name and surname? [User]: I'm sorry I'm so inattentive today. Klaus Heisler. [Function]: Getting details for booking 123-457 for Klaus Heisler... 2/6

1

0

4

LangChain4j

@langchain4j

10 months

🎉LangChain4j 0.18.0 is out!🎉 We've added an integration with @LocalAI_API , so you can now use LLMs hosted locally, even on your laptop!

0

4

LangChain4j

@langchain4j

10 months

[Function]: org.example.BookingNotFoundException [Agent]: I apologize, but I couldn't find any booking under the name Klaus Heisler with the booking number 123-457. Could you please double-check the information and provide me with the correct details? 3/6

1

0

4

LangChain4j

@langchain4j

3 months

@DataStax @LangChainAI Thank you for a very nice and clear visualization, great job! This architecture can now be easily implemented using @langchain4j thanks to @DataStax AstraDB integration and a data ingestion pipeline (see ) as well as an advanced RAG flow (see…

0

4

LangChain4j

@langchain4j

5 months

@Stephan007 @glaforge @aheritier It does not work just yet, we are now upgrading to the brand new Google VertexAI java sdk, so Gemini will be supported soon

2

0

4

LangChain4j

@langchain4j

9 months

#Azure #OpenAI models are now supported in #LangChain4j 0.21.0 🎉

1

2

4

LangChain4j

@langchain4j

3 months

@sebi2706 Yes! You can find more info here: And a few examples here: Would love to hear feedback and more ideas!

Foundation for advanced RAG by langchain4j · Pull Request #538 · langchain4j/langchain4j

So far, LangChain4j had only a simple (a.k.a., naive) RAG implementation: a single Retriever was invoked on each interaction with the LLM, and all retrieved TextSegments were appended to the end of...

github.com

1

0

4

LangChain4j

@langchain4j

10 months

You can find the above example and experiment with it here: 6/6

0

4

LangChain4j

@langchain4j

7 months

Thanks for the awesome talk!

AndriyMulyar

@andriy_mulyar

7 months

Learn how to build and run local large language models from my recent talk at #Devoxx Belgium

1

3

21

0

1

4

LangChain4j

@langchain4j

17 days

@rseroter @Docker @springboot @testcontainers Agreed :)

LangChain4j

@langchain4j

3 months

Finally, it's the weekend🎉Time for experiments! Using GPT-4 to evaluate content generated by Llama2. Seems to integrate well with standard JUnit/AssertJ tests. WDYT?

4

7

71

0

4

LangChain4j

@langchain4j

9 months

#LangChain4j 0.21.0 is here! - Integration with @trychroma - Integration with Qwen models (DashScope) - Support for persistent chat memory More details:

Release 0.21.0 · langchain4j/langchain4j

Integration with Azure OpenAI by @kuraleta Integration with Qwen models (DashScope) by @jiangsier-xyz Integration with Chroma by @kuraleta Support for persistent ChatMemory

github.com

0

1

4

LangChain4j

@langchain4j

3 months

What are you building or planning to build with LangChain4j?

Data processing pipelines

13

Chatbots and assistants

12