Can GPT3 do math? Or do you need to hook it up to other tools to allow it to best do so? A really cool demo by @JavaFXpert allowing you to easily compare GPT3 vs GPT3 with PAL on @huggingface spaces!
@langchain
-
PAL: Combining LLMs with Python Interpreter for Better Reasoning
By
–
PAL (
https://
arxiv.org/pdf/2211.10435
.pdf
…) is a method from @urialon1 @luyu_gao @aman_madaan combining LLMs with a python interpreter to achieve better results on numeric and reasoning tasks Check out the LangChain implementation/documentation here: https://
langchain.readthedocs.io/en/latest/exam
ples/chains/pal.html
… -
LangChain v0.0.45 Release: Redis Cache and Documentation Updates
By
–
LangChain v0.0.45 Redis Cache support from @sjwhitmore Documentation improvements (one from @dheeraja486
, one highlighted by @altryne
) .gitignore improvements from @gojira -
LangChain v0.0.44: OpenAI Timeout, Azure Integration, HyDE
By
–
v0.0.44 Timeout argument for OpenAI LLM – Sam Bean, @YouSearchEngine Azure OpenAI LLM integration – @gojira Hypothetical Document Embeddings, based on https://
arxiv.org/abs/2212.10496 – h/t @luyu_gao For docs on Azure OpenAI, see https://
langchain.readthedocs.io/en/latest/exam
ples/prompts/azure_openai_example.html
… -
LangChain v0.0.43: Weaviate and Pinecone vectorstore support
By
–
v0.0.43 @weaviate_io vectorstore support! h/t @CShorten30 for help here – keep out for more! @pinecone vectorstore support – @cameroncohen Improvements to text splitter And better docs for data augmented generation in general! https://
langchain.readthedocs.io/en/latest/exam
ples/data_augmented_generation.html
… -
Embeddings Integration and Prototype Support Offer
By
–
yeah as @devonbrackbill said, probably pretty doable with embeddings! and should fit into the current abstractions pretty nicely. if youve got a concrete usecase and need, happy to help prototype some stuff!
-
Fine-tuning vs. In-context Learning: Exploring Alternative Approaches
By
–
this is great question! i think its an unexplored space. finetuning is much more heavy weight (error prone, hard to do, more data required, etc), so it will be interesting to see if you can achieve similar performance just by using examples
-
LangChain Enables Selective LLM Caching Control
By
–
Caching improvements Previously, caching was enabled for either all LLMs or None But @devonbrackbill pointed out you may want to turn off caching for certain LLM calls – eg in recursive summarization This is now possible Docs: https://
langchain.readthedocs.io/en/latest/exam
ples/prompts/llm_caching.html
… -
MMR Example Selector for Optimal Contextual Diversity
By
–
Max Marginal Relevance (MMR) Example Selector Based on this preprint by @xiye_nlp et al, the MMR example selector chooses diverse, in-context examples H/t @johnjnay for surfacing this paper Docs: https://langchain.readthedocs.io/en/latest/examples/prompts/prompt_management.html Original Paper: https://x.com/xiye_nlp/status/1603821850592628738?s=20&t=wQPcRd8IJ8URbmytuYP7QA
-
LangChain Extends Prompt Formatting with Jinja Support
By
–
Jinja Formatting Up until now, all the formatting in prompts has been done using Python f-strings But the template_format abstraction is pretty flexible, and @benderville easily extended it to support Jinja, a more advanced formatter Docs: https://
langchain.readthedocs.io/en/latest/exam
ples/prompts/prompt_management.html#Alternative-formats
…