Update from HF #12
Merged
Update from HF #12
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* Add linter rules + apply make style
* Improve tool call argument parsing
* Fix from_langchain in tools.py
* Bump version to 1.5.0.dev * Fix style --------- Co-authored-by: Albert Villanova del Moral <[email protected]>
* adapt docs * optional in pyproject.toml * get rid of some transformers imports * optional transformers in models.py * gradio, transformers, litellm * small refacto AgentType * merge conflicts * mouaif * fix tests * AgentText no longer a str * Add back AgentType as str/Image * fixed for good
* Improve python executor's error logging
… the use of compile, eval, exec (#274)
* Test evaluate_augassign
* Make e2b optional dependency with extra * Make e2b imports optional * Update e2b docs
* Add cool GIF of agent run inspection using Phoenix
…io Spaces and fix code snippet formatting (#306) - Changed the description of Hub integrations to specify sharing and loading of Gradio Spaces as tools. - Fixed a formatting issue in the code snippet by removing an extraneous comma in the import statement.
* fuse stream and non stream calls
* minor fix for console in AgentLogger
* Added support for connecting to Azure OpenAI via AzureOpenAIServerModel
* refactor(models): restructure model parameter handling - Introduce base-class level default parameters (temperature, max_tokens) - Optimize parameter handling: method args can override base config - Unify parameter handling across model implementations
… explicitely added so as to prevent the dangerous ones from being indirectly available (compile, exec, eval, breakpoint, __import__, open, ...) (#299)
* Support any and none tool types
* adding a 60 seconds timeout * lowerting the timeout to 20s
* Support interactive shells for source inspection * Add tool save e2e tests
* Test all augassign operators * Refactor evaluate_augassign
* Remove package-lock.json * Remove package.json
* Update guided_tour.md (#287) * Example for calling multiple tools from ToolCallingAgent * CodeAgent added * Default agent set to CodeAgent and Qualitty fix * Rename file
* RAG on your PDF data using chromadb and groq api * Multiple embeeding and llm support * Multiple embedding and llm support * Default embeddings set to hugging face * organize imports * huggingface_doc data source added * Update and rename Local_PDF_RAG_using_chromadb.py to rag_using_chromadb.py * Quality fix * Default agent set to CodeAgent
* improve static tools initialization safety * Allow modification of custom_tools during code execution
* Add args to MultiStepAgent docstring
* Fix MultiStepAgent docstring * Force PR doc build
* docstring args for ToolCallingAgent, CodeAgent and ManagedAgent * Fix ToolCallingAgent and CodeAgent docstring * Minor fix --------- Co-authored-by: Albert Villanova del Moral <[email protected]>
* Improve inference choice examples * Fix style --------- Co-authored-by: Albert Villanova del Moral <[email protected]>
* vlm initial commit * transformers integration for vlms * Add webbrowser example and make it work 🥳🥳 * Refactor image support * Allow modifying agent attributes in callback * Improve vlm browser example * time.sleep(0.5) before screenshot to let js animations happen * test to validate internal workflow for passing images * Update test_agents.py * Improve error logging * Switch to OpenAIServerModel * Improve the example * Format * add docs about steps, callbacks & co * Add precisions in doc * Improve browser * Tiny prompting update * Fix style * fix/add test * refactor * Fix write_inner_memory_from_logs for OpenAI format * Add back summary mode * Make it work with TransformersModel * Fix test * Fix loop * Fix quality * Fix mutable default argument * Rename tool_response_message to error_message and append it * Working browser with firefox * Use flatten_messages_as_text passed to TransformersModel * Fix quality * Document flatten_messages_as_text in docstring * Working ctrl + f in browser * Make style * Fix summary_mode type hint and add to docstring * Move image functions to tools * Update docstrings * Fix type hint * Fix typo * Fix type hints * Make callback call compatible with old single-argument functions * Revert update_metrics to have a single arg * Pass keyword args instead of args to callback * Update webbrowser * fix for single message case where final message list is empty * forgot debugger lol * accommodate VLM-like chat template and fix tests * Improve example wording * Style fixes * clarify naming and fix tests * test fix * Fix style * Add bm25 to fix one of the doc tests * fix mocking in VL test * fix bug in fallback * add transformers model * remove chrome dir from helium * Update Transformers example with flatten_messages_as_text * Add doc for flatten_messages_as_text * Fix merge error --------- Co-authored-by: Merve Noyan <[email protected]> Co-authored-by: Aymeric <[email protected]> Co-authored-by: Albert Villanova del Moral <[email protected]>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
20 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.