Again, we're really excited to see how this develops! We are extremely open to contributions and suggestions – please open PRs, file issues, DM us, or get in touch on the discord:
OPEN SOURCE
-
MRKL agents and Hub loading in LangChain
By
–
Agents MRKL: https://
hwchase17.github.io/langchainjs/do
cs/modules/chains/load_from_hub
… Load from Hub: https://
hwchase17.github.io/langchainjs/do
cs/modules/agents/load_from_hub
… -
LangChain Buffer Memory: Essential Tool for AI Agents
By
–
Memory Buffer Memory: https://
hwchase17.github.io/langchainjs/do
cs/modules/memory/buffer_memory
… -
LangChain JS Indexes: Text Splitter, Embeddings, Vectorstores
By
–
Indexes Text Splitter: https://
hwchase17.github.io/langchainjs/do
cs/modules/indexes/text_splitter
… Embeddings: https://
hwchase17.github.io/langchainjs/do
cs/modules/indexes/embeddings
… Vectorstores: https://
hwchase17.github.io/langchainjs/do
cs/modules/indexes/vectorstore
… -
Cross-language AI abstractions with shared serializable formats
By
–
Relationship to Python Package We built the same abstractions (prompts, LLMs, etc) we had in Python In particular, we built them in a way where they share the same serializable format This means you can load the same prompt, chain, agent in both languages
-
Why TypeScript Became Priority for LangChain Community
By
–
Why TypeScript? LLMs started out as popular for the ML/data engineering crowd, who prefer Python However, as the LangChain community grew over time, we started to hear a lot of requests for Javascript support And so it became a priority to deliver this
-
LLM abstractions now natively available in JavaScript
By
–
HighLights All the same abstractions (prompts, LLMs, textsplitters, embeddings, vectorstores, chains, agents, memory) are now natively available in js There is a common serializable format for cross-language sharing This was only doable with community support
-
LangChain JavaScript TypeScript Support Launch
By
–
It's finally here… Javascript/TypeScript support for LangChain BIG thank you to everyone in the community who contributed to this, especially @_seanyneutron and @nfcampos GitHub: https://
github.com/hwchase17/lang
chainjs
…
Blog: https://
blog.langchain.dev/typescript-sup
port/
… LOTS to discuss, lets -
XLA and Automatic Parallelization in JAX for Computation Speed
By
–
XLA & Automatic Parallelization It also supports XLA or Accelerated Linear Algebra, which is an optimizing compiler, designed specifically to increase the computation speed. And also supports Parallelization and can be done using "pmap()" https://
jax.readthedocs.io/en/latest/note
books/quickstart.html
… -
Automatic Vectorization with JAX vmap Function
By
–
Automatic Vectorization Vectorization helps faster code execution and Jax has an inbuilt function to do the same And can be done with using "vmap()" function Here are the detailed use cases and implementation of Vectorization. http://
jax.readthedocs.io/en/latest/_aut
osummary/jax.vmap.html#jax.vmap
…