Don't throw an exception when model makes a mistake. Use retries, and if
not succeeding after a fixed attempts, fall back to the previous sepaker
if available, or the first participant.
Resolves#5453
Get's SelectorGroupChat working for llama by:
1. Using a UserMessage rather than a SystemMessage
2. Normalizing how roles are presented (one agent per line)
3. Normalizing how the transcript is constructed (a blank line between
every message)
Some agent descriptions were split over multiple lines in the M1
orchestrator. This PR ensures that each description appears on one, and
only one, line. This makes it easier for smaller models to understand.
<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->
<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->
## Why are these changes needed?
Currently the way to accomplish RAG behavior with agent chat,
specifically assistant agents is with the memory interface, however
there is no way to configure it via the declarative API.
<!-- Please give a short summary of the change and the problem this
solves. -->
## Related issue number
<!-- For example: "Closes #1234" -->
## Checks
- [ ] I've included any doc changes needed for
https://microsoft.github.io/autogen/. See
https://microsoft.github.io/autogen/docs/Contribute#documentation to
build and test documentation locally.
- [ ] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [ ] I've made sure all auto checks have passed.
---------
Co-authored-by: Victor Dibia <chuvidi2003@gmail.com>
Allow AssistantAgent to drop images when not equipped with a multi-modal model.
Adds a corresponding utility function, which can be used in autogen-ext and teams, to accomplish the same.
This PR does the following:
- Fix warning messages in AGS on launch.
- Improve Cli message to include app URL on startup from command line
- Minor improvements default gallery generator. (add more default tools)
- Improve new session behaviour.
## Related issue number
Closes#5097
## Checks
This PR adds a `sources` optional parameter to CodeExecutorAgent
(similar to the termination conditions), that allows finer-grained
control on which agents can provide code for execution.
It also moves the `_extract_markdown_code_blocks` subroutine to a member
method, so that it can be overridden by subclasses. I've found this to
be very important to support benchmarks like HumanEval, where we need to
add a test harness around the implementation.
Resolves#3983
* introduce `model_client_stream` parameter in `AssistantAgent` to
enable token-level streaming output.
* introduce `ModelClientStreamingChunkEvent` as a type of `AgentEvent`
to pass the streaming chunks to the application via `run_stream` and
`on_messages_stream`. Although this will not affect the inner messages
list in the final `Response` or `TaskResult`.
* handle this new message type in `Console`.
<!-- Thank you for your contribution! Please review
https://microsoft.github.io/autogen/docs/Contribute before opening a
pull request. -->
<!-- Please add a reviewer to the assignee section when you create a PR.
If you don't have the access to it, we will shortly find a reviewer and
assign them to your PR. -->
## Why are these changes needed?
Make AssistantAgent and Handoff use BaseTool.
This ensures that they can be made declarative/serialized
<!-- Please give a short summary of the change and the problem this
solves. -->
## Related issue number
<!-- For example: "Closes #1234" -->
## Checks
- [ ] I've included any doc changes needed for
https://microsoft.github.io/autogen/. See
https://microsoft.github.io/autogen/docs/Contribute#documentation to
build and test documentation locally.
- [ ] I've added tests (if relevant) corresponding to the changes
introduced in this PR.
- [ ] I've made sure all auto checks have passed.
* initial pass on making group chats declarative
* update group chat tests
* update impl to include participant serialization for all teams
* v1 making soc declarative
* update memory test
* update chatagent and team base classes
* update serialization doc notebook
* fomating updates
Update _magentic_one_orchestrator.py
In a Magentic Group Settting, if one of the Assitant Agents uses a tool it gives the following error, note this is under a FALSE reflect_on_tool variable.
Making it true, wont happen, though more tokens will be consumed and it will have a worst output and the philosophy of a tool as an answer is not followed...
* Pass context between AssistantAgent for handoffs
* Add parallel tool call test
---------
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
* v1, make assistant agent declarative
* make head tail context declarative
* update and formatting
* update assistant, format updates
* make websurfer declarative
* update formatting
* move declarative docs to advanced section
* remove tools until implemented
* minor updates to termination conditions
* update docs
* initial base memroy impl
* update, add example with chromadb
* include mimetype consideration
* add transform method
* update to address feedback, will update after 4681 is merged
* update memory impl,
* remove chroma db, typing fixes
* format, add test
* update uv lock
* update docs
* format updates
* update notebook
* add memoryqueryevent message, yield message for observability.
* minor fixes, make score optional/none
* Update python/packages/autogen-agentchat/src/autogen_agentchat/agents/_assistant_agent.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* update tests to improve cov
* refactor, move memory to core.
* format fixxes
* format updates
* format updates
* fix azure notebook import, other fixes
* update notebook, support str query in Memory protocol
* update test
* update cells
* add specific extensible return types to memory query and update_context
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* make termination condition declarative
* make all term conditions declarative
* make And/OrTermination top level objects in base
* add basic tests
* add tutorial notebook
* update tests and formatting
* update tests
* update declarative config with updated api.
* Add lock for input and output management in m1
* Use event to signal it is time to prompt for input
* undo stop change
* undo changes
* Update python/packages/magentic-one-cli/src/magentic_one_cli/_m1.py
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
* reduce exported surface area
* fix
---------
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Hussein Mozannar <hmozannar@microsoft.com>
* Instantiate and call activate/deactivate on agents
* autoformatting
* remove activate. Rename deactivate to close
* remove unneeded import
* create close fn in runtime
* change runtime close behavior
* uv.lock
---------
Co-authored-by: Jack Gerrits <jackgerrits@users.noreply.github.com>
* Doc update to include model context usage
* add langchain tools
* update langchain tool wrapper api doc
* updat
* update
* format
* add langchain experimental dev dep
* type
* Fix type
* Fix some types in langchain adapter
* type ignores
* Emphasis on_messages is for new messages only
* update
* update uv
* update uv action
* try pin uv version
* pin all uv versions to 0.5.11
* revert uv lock file and remove unwanted file.
* Enhance MagenticOneGroupChat documentation with architecture overview and citation reference
* Fix formatting in MagenticOneGroupChat documentation and add citation reference
* Decouple model_context from AssistantAgent
* add UnboundedBufferedChatCompletionContext to mimic pervious model_context behaviour on AssistantAgent
* moving unbounded buffered chat to a different file
* fix model_context assertions in test_group_chat
* Refactor model context, introduce states
* fixes
* update
---------
Co-authored-by: aditya.kurniawan <aditya.kurniawan@core42.ai>
Co-authored-by: Eric Zhu <ekzhu@users.noreply.github.com>
Co-authored-by: Victor Dibia <victordibia@microsoft.com>
Eric Zhu
wistuba
afourney
Eitan Yarmush
Victor Dibia
Fernando Bellido Pazos
Jack Gerrits
Leon De Andrade
Jacob Alber
Roy Belio
peterychang
WcW
Leon De Andrade
Sachin Joglekar
gagb
Aditya Kurniawan
jspv