* Deep refacto that disentangled logging logic between logging (informing the user via console outputs) and memory (storing what happened in the agent).
---------
Co-authored-by: benediktstroebl <50178209+benediktstroebl@users.noreply.github.com>
Co-authored-by: Aymeric <aymeric.roucher@gmail.com>
* 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 <mervenoyan@Merve-MacBook-Pro.local>
Co-authored-by: Aymeric <aymeric.roucher@gmail.com>
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
* 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
* add support for tool collection from mcp servers
* add forgotten documentation
* fix link missing in documentation
* fix linting in CI, bumpruff to use modern version
* mcpadapt added as optional dependencies
* use classmethod for from_hub and from_mcp to better reflect the fact that they return a ToolCollection
* Update src/smolagents/tools.py
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
* Update src/smolagents/tools.py
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
* Test ToolCollection.from_mcp
* Rename to mcp extra
* Add mcp extra to test extra
* add a test for from_mcp
* fix typo
* fix tests
* Test ToolCollection.from_mcp
(cherry picked from commit 9284d9ea8cf24d3c934e35a38dfe34f3ce31cef3)
* Make all pytest tests
---------
Co-authored-by: Albert Villanova del Moral <8515462+albertvillanova@users.noreply.github.com>
Julien Chaumond
Clémentine Fourrier
Aymeric Roucher
Albert Villanova del Moral
Merve Noyan
Antoine Jeannot
Nicholas Broad
tandiapa
Lucain
Guillaume Raille
Edward Beeching
NeverLucky
Aymeric