Releases · dottxt-ai/outlines

What's Changed

Parse scripts and transpile to Outlines graphs by @rlouf in #10
Add LanguageModel Op and integration with HuggingFace's GPT2 implementation by @rlouf in #30
Add ImageVariable Op and integrations with HF's StableDiffusion implementation by @rlouf in #33
Add an interactive execution mode by @rlouf in #34
Integrate all causal LM models available with HuggingFace's transformers library by @rlouf in #37
Integration with the OpenAI API by @rlouf in #38
Simplify and clean the codebase by @rlouf in #40
Add decorator to turn python functions into an Op by @rlouf in #41
Add eval method and chain function to compile outlines graphs by @rlouf in #42
Refactor the language model interface by @rlouf in #44
Add max_tokens and temperature kwargs for the text.completion operator by @rlouf in #45
Image generation by @rlouf in #46
Remove the symbolic structure by @rlouf in #48
Update the BabyAGI example by @rlouf in #57
Add integration with the OpenAI embeddings endpoint by @rlouf in #59
Add integration for OpenAI's image generation API by @rlouf in #60
Remove whitespaces introduced by the use of \ by @rlouf in #63
Remove chat completion and refactor the model router by @rlouf in #65
Add tool decorator to automatically document tools by @rlouf in #64
Add a utility to build "natural language functions" by @rlouf in #66
Add an in-memory vector store by @rlouf in #67
Use Jinja filters instead of a tool decorator by @rlouf in #69
Use tempfile to generate test cache directories by @brandonwillard in #74
Add "Pick the odd one out" example by @rlouf in #84
Update the BabyAGI demo by @brandonwillard in #73
Add react example by @rlouf in #83
Remove the completion decorator by @rlouf in #86
Add documentation draft by @rlouf in #92
Update the documentation with installation instructions and overview by @rlouf in #94
Takes several samples from the generative models by @rlouf in #95
Add type constraint to generation by @rlouf in #91
Allow disabling caching by @rlouf in #102
Pretty print dictionary when passed to prompt by @rlouf in #103
Add tests for the HuggingFace integrations by @rlouf in #105
Move stop_at parameter to completion call by @brosand in #110
Add is_in and stop_at generation constraints to transformers integration by @rlouf in #108
Simplify the OpenAI text completion interface by @rlouf in #112
Add a Conda dev environment file by @brandonwillard in #114
Add LICENSE by @rlouf in #111
Update the README by @rlouf in #113
Update the documentation before release by @rlouf in #104