yujunjun/autogen
1
0
Fork 0
mirror of https://github.com/microsoft/autogen.git synced 2026-01-05 19:50:50 +00:00
Code Issues Packages Projects Releases Wiki Activity
autogen/python/samples/task_centric_memory/configs/demonstration.yaml

32 lines
1012 B
YAML
Raw Normal View History

Task-Centric Memory (#5227) _(EXPERIMENTAL, RESEARCH IN PROGRESS)_ In 2023 AutoGen introduced [Teachable Agents](https://microsoft.github.io/autogen/0.2/blog/2023/10/26/TeachableAgent/) that users could teach new facts, preferences and skills. But teachable agents were limited in several ways: They could only be `ConversableAgent` subclasses, they couldn't learn a new skill unless the user stated (in a single turn) both the task and how to solve it, and they couldn't learn on their own. **Task-Centric Memory** overcomes these limitations, allowing users to teach arbitrary agents (or teams) more flexibly and reliably, and enabling agents to learn from their own trial-and-error experiences. This PR is large and complex. All of the files are new, and most of the added components depend on the others to run at all. But the review process can be accelerated if approached in the following order. 1. Start with the [Task-Centric Memory README](https://github.com/microsoft/autogen/tree/agentic_memory/python/packages/autogen-ext/src/autogen_ext/task_centric_memory). 1. Install the memory extension locally, since it won't be in pypi until it's merged. In the `agentic_memory` branch, and the `python/packages` directory: - `pip install -e autogen-agentchat` - `pip install -e autogen-ext[openai]` - `pip install -e autogen-ext[task-centric-memory]` 2. Run the Quickstart sample code, then immediately open the `./pagelogs/quick/0 Call Tree.html` file in a browser to view the work in progress. 3. Click through the web page links to see the details. 2. Continue through the rest of the main README to get a high-level overview of the architecture. 3. Read through the [code samples README](https://github.com/microsoft/autogen/tree/agentic_memory/python/samples/task_centric_memory), running each of the 4 code samples while viewing their page logs. 4. Skim through the 4 code samples, along with their corresponding yaml config files: 1. `chat_with_teachable_agent.py` 2. `eval_retrieval.py` 3. `eval_teachability.py` 4. `eval_learning_from_demonstration.py` 5. `eval_self_teaching.py` 6. Read `task_centric_memory_controller.py`, referring back to the previously generated page logs as needed. This is the most important and complex file in the PR. 7. Read the remaining core files. 1. `_task_centric_memory_bank.py` 2. `_string_similarity_map.py` 3. `_prompter.py` 8. Read the supporting files in the utils dir. 1. `teachability.py` 2. `apprentice.py` 3. `grader.py` 4. `page_logger.py` 5. `_functions.py`
2025-03-04 09:56:49 -08:00
PageLogger:
level: DEBUG # DEBUG, INFO, WARNING, ERROR, CRITICAL, or NONE.
path: ./pagelogs/demonstration
client:
model: gpt-4o-2024-08-06
temperature: 0.8
max_completion_tokens: 4096
presence_penalty: 0.0
frequency_penalty: 0.0
top_p: 1.0
max_retries: 65535
Apprentice:
name_of_agent_or_team: AssistantAgent # AssistantAgent or MagenticOneGroupChat
disable_prefix_caching: 1 # If true, prepends a small random string to the context, to decorrelate repeated runs.
MemoryController:
max_train_trials: 10
max_test_trials: 3
MemoryBank:
path: ./memory_bank/demonstration
relevance_conversion_threshold: 1.7
n_results: 25
distance_threshold: 100
test:
main_task_file: data_files/tasks/cell_towers_1.yaml # The task being tested.
demo_task_file: data_files/tasks/cell_towers_2.yaml # A similar but different task.
demo_solution_file: data_files/insights/cell_towers_2_demo.yaml # A demonstration of solving the second task.
num_trials: 10
Reference in New Issue Copy Permalink