AI - AI Dynamics

LangChain v0.0.39: Document Analysis with OpenAI Integration

By

–

16 December 2022 18h10

Analyzing documents just got a lot easier with v0.0.39 (with major assist from @OpenAI
) Added a `collapse` step into the map-reduce chain (
@johnjnay
)
Added support for @OpenAI new embeddings
Added support for @OpenAI new tokenizer Heres how they all work together

→ View original post on X — @langchain

16 December 2022

Collapse Step for Map-Reduce Chain Scaling

By

@langchain

–

16 December 2022 18h10

Adding a `collapse` step into the map-reduce chain This recursively collapses documents into smaller and smaller chunks, allowing you to scale to arbitrarily many documents This was a @johnjnay special – see his thread for more

→ View original post on X — @langchain

16 December 2022

OpenAI Releases New Embedding Model for Semantic Search

By

@langchain

–

16 December 2022 18h10

@OpenAI released a new embedding model (`text-embedding-ada-002`) This makes it possible to more easily do semantic search over collections of documents This is now the default OpenAI embedding model in LangChain

→ View original post on X — @langchain

16 December 2022

Stability SDK failure dumps all data

By

@levelsio

–

16 December 2022 17h50

Okay looks like if Stability SDK fails it dumps all of this

→ View original post on X — @levelsio

16 December 2022

Stability SDK Python generates massive 3.5 GB ProtoBuffer files

By

@levelsio

–

16 December 2022 17h39

Anyone know why @StabilityAI
's Stability SDK Python lib generates massive 3.5 GB folders full of ProtoBuffer *.pb files?

→ View original post on X — @levelsio

16 December 2022

Constitutional AI: Moving Beyond Researcher-Defined Constitutions

By

@anthropicai

–

16 December 2022 17h36

In our paper we used an ad hoc constitution drafted purely for research purposes. Ultimately, we think constitutions shouldn’t be just defined by researchers in isolation, but by groups of experts from different disciplines working together.

→ View original post on X — @anthropicai

16 December 2022

Constitutional AI: Making Implicit Principles Explicit in AI Systems

By

@anthropicai

–

16 December 2022 17h36

While the name “Constitutional AI” may sound ambitious, we chose it to emphasize that powerful, general-purpose AI systems will always be operating according to *some* principles, even if they are left implicit, or encoded in privately held data.

→ View original post on X — @anthropicai

16 December 2022

Hugging Face Reaches 100,000 Public AI Models Milestone

By

@clementdelangue

–

16 December 2022 17h31

We crossed 100,000 public AI models on the @huggingface hub available for free to all. Thank you to the whole community of contributors. Proud to make ML more open & collaborative!

→ View original post on X — @clementdelangue

16 December 2022