* updated dependencies versions
* Updated model validator for HuggingFace-Hub client to catch model and hub url early
* split task registration into discover + register phases, improved LLM client init in tasks and workflow wrappers
* improve decorator to access method attributes
* wrapping workflow decotrators to log, validate, etc., without losing signature/docs
* Improved LLM-based task client and cleaned execution of LLM, agent and python function
* Added an example of multiple models being defined per workflow task after updates
* Updated quickstarts basic agent runs to async
* Added model attribute to huggingface-hub client class
* Fixed random and roundrobin orchestrators TriggerAction schema, trigger action and task to process agent response
* Updated quickstart multi-agent workflows and actor-based agents docs
* added .dapr to gitignore
* add transactional `register_agent` with optimistic‑concurrency + retry
* Added basic calc example from bibryam to validate actor registration works and overall demo works
---------
Co-authored-by: Yaron Schneider <schneider.yaron@live.com>
* Fix: Return the content if hasattr(result, 'content') && hasattr(content, 'text') to reiterate from the model
Signed-off-by: Casper Guldbech Nielsen <scni@novonordisk.com>
* Remove the set on error_message as it is not returned
Signed-off-by: Casper Guldbech Nielsen <scni@novonordisk.com>
* Fix: Change the order of the if statements to ensure the return of the content text before raising error
Signed-off-by: Casper Guldbech Nielsen <scni@novonordisk.com>
* Simplify the if conditions and remove unnecessary code
Signed-off-by: Casper Guldbech Nielsen <scni@novonordisk.com>
* Add mcp==1.6.0 to requirements as the mcp client needs it
Signed-off-by: Casper Guldbech Nielsen <scni@novonordisk.com>
---------
Signed-off-by: Casper Guldbech Nielsen <scni@novonordisk.com>
* Enable async-first execution for AgentTool and ToolExecutor
* Update basic agent patterns to support async tool execution
* Updated assistant agentic workflow base to support async tool execution
* fix#70. Updated input for workflow task agent execution
* Update agent actor base to support async tool execution
* Updated logging on workflow message decorator
* Enable lazy initialization of schemas for Orchestrator agentic workflows
* minor update on quickstart 05 apps to follow the right structure
* added basic single-agent example of a dapr workflow agent
* Integrate MCP client with full tool and prompt support
* Created MCP examples in cookbook
* Fix: Fix: The Azure OpenAI docs needs update #66
Signed-off-by: Casper Guldbech Nielsen <scni@novonordisk.com>
* Ensure the addition of AZURE_OPENAI_API_VERSION env var as this is needed to run succesfully
Signed-off-by: Casper Guldbech Nielsen <scni@novonordisk.com>
---------
Signed-off-by: Casper Guldbech Nielsen <scni@novonordisk.com>
* unify iterable model wrapping and response model resolution
* added support for kwargs in decorator in WorkflowTask initialization
* feat: support arbitrary task config via decorator kwargs
* refactor: unify LLM task validation and structured output handling
* Moved Messaging under Workflow and modularized main components.
* Removed WorkflowService and added as_service() to AgenticWorkflow for pub/sub support in headless and service modes.
* Added utility to safely retrieve instance methods decorated with a specific attribute
* Updated Agent and Orchestrator workflows to support the latest messaging system changes.
* Updated AgentActors to integrate with latest messaging system under workflows.
* Made service_port optional to allow random port assignment.
* dapr agents imports and logging
* Updated Multi-agent workflows, deleted JSON logs and tested NVIDIA LLM client notebook
* Integrated new messaging system into multi-agent quickstarts
* Updated agentic workflows docs to reflect changes
* Updated quickstart multi-agent workflows app to run in headless mode
* Fixed Orchestrator as a service and exposed built-in route to start workflow over HTTP
* Updated INFO logging to DEBUG
* updated cookbook with latest changes
* updated quickstart mukti-agent workflows to integrate orchestrator as service change
* Updated docs to trigger agentic workflow over HTTP by default.
* Upgrade Jinja2 to address sandbox breakout vulnerability
* Removes additional address arguments for Dapr client init
Relies on env variables instead
Signed-off-by: Elena Kolevska <elena@kolevska.com>
correct casing in dapr multi app run files
Signed-off-by: Elena Kolevska <elena@kolevska.com>
removes dummy file
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Updates readmes
Signed-off-by: Elena Kolevska <elena@kolevska.com>
---------
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Replaced pure Dapr workflow example with parallel workflow example
Signed-off-by: Bilgin Ibryam <bibryam@gmail.com>
* Fixes parallel workflows
Signed-off-by: Elena Kolevska <elena@kolevska.com>
---------
Signed-off-by: Bilgin Ibryam <bibryam@gmail.com>
Signed-off-by: Elena Kolevska <elena@kolevska.com>
Co-authored-by: Elena Kolevska <elena@kolevska.com>
* Small fixes for llm calls with HF and Elevenlabs
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Increase timeout for tests
Signed-off-by: Elena Kolevska <elena@kolevska.com>
---------
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Added the concept of excluding orchestrator when retrieving agents metadata.
* moved tool arguments in logging to DEBUG.
* Added try except to method to get data from state store
* Removed imports not used and adjusted code indentation
* Bringing in Bilgin’s changes
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Adds hugging face quickstart
Signed-off-by: Elena Kolevska <elena@kolevska.com>
---------
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Completes all OpenAI LLM calls quickstarts
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Completes all OpenAI LLM calls quickstarts
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* More tests for multi agent actor workflows (adds llm and random orchestrators)
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Adds nvidia tests
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Adds dapr llm tests
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Readds the diff workflows
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* fix orchestrator names
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Multi agent workflows - agents as dapr workflows
Signed-off-by: Elena Kolevska <elena@kolevska.com>
not needed
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Adds a github workflow to validate quickstarts
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Adds elevenlabs llm test
Signed-off-by: Elena Kolevska <elena@kolevska.com>
---------
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Fixed tool executor reference and tool calling logic to update tool history the right way
* Removed dapr config for workflows. No needed anymore
* Implement safe parallel state writes with atomic merging
* Extend workflow state to track tool executions
* removing nested double quotes from Assistant agent logging
* first round of fixes
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Adds orchestrator interface
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Moves the abstract methods to the base class
Signed-off-by: Elena Kolevska <elena@kolevska.com>
---------
Signed-off-by: Elena Kolevska <elena@kolevska.com>
Signed-off-by: Elena Kolevska <elena-kolevska@users.noreply.github.com>
* Initial version of quickstarts
* Renames floki to dapr_agents and adds missing dotenv dependencies
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Updates all dapr dependencies
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Fixes 1
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* dapr wf fix
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* fix llm call quickstart
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Fixes readmes
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Fixes quickstarts 4 and 5. Changes orchestrator type in quickstart 5 to Random because the Roundrobin one currently has a bug
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Adds mechanical markdown to quickstarts
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Adds llm call quickstart to automated testing
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Updates docs with instructions to run tests
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Adds tests for quickstarts 3 and 4
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Added testing for quickstart 5
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Set up venv in makefile
Signed-off-by: Elena Kolevska <elena@kolevska.com>
* Test tweaks
Signed-off-by: Elena Kolevska <elena@kolevska.com>
---------
Signed-off-by: Elena Kolevska <elena@kolevska.com>
Signed-off-by: Elena Kolevska <elena-kolevska@users.noreply.github.com>
Co-authored-by: Elena Kolevska <elena@kolevska.com>
Co-authored-by: Elena Kolevska <elena-kolevska@users.noreply.github.com>
* Add AI agent overview
Signed-off-by: Marc Duiker <marcduiker@users.noreply.github.com>
* Add image to core principles
Signed-off-by: Marc Duiker <marcduiker@users.noreply.github.com>
---------
Signed-off-by: Marc Duiker <marcduiker@users.noreply.github.com>
Roberto Rodriguez
Yaron Schneider
Casper Nielsen
Bilgin Ibryam
Fabian Martinez
Juan González
Casper Nielsen
Elena Kolevska
Marc Duiker
Joni Collinge