* Fix and clean up path processing in logs module
* Fix path processing throughout the project
* Fix plugins test
* Fix borky pytest vs mkdir(exist_ok=True)
* Update docs and gitignore for new workspace location
* Fix borky pytest vol.2
* ok james
* Move rename module `agent` -> `agents`
* WIP: abstract agent structure into base class and port Agent
* Move command arg path sanitization to decorator
* Add fallback token limit in llm.utils.create_chat_completion
* Rebase `MessageHistory` class on `ChatSequence` class
* Fix linting
* Consolidate logging modules
* Wham Bam Boom
* Fix tests & linting complaints
* Update Agent class docstring
* Fix Agent import in autogpt.llm.providers.openai
* Fix agent kwarg in test_execute_code.py
* Fix benchmarks.py
* Clean up lingering Agent(ai_name=...) initializations
* Fix agent kwarg
* Make sanitize_path_arg decorator more robust
* Fix linting
* Fix command enabling lambda's
* Use relative paths in file ops logger
* Fix test_execute_python_file_not_found
* Fix Config model validation breaking on .plugins
* Define validator for Config.plugins
* Fix Config model issues
* Fix agent iteration budget in testing
* Fix declaration of context_while_think
* Fix Agent.parse_and_process_response signature
* Fix Agent cycle_budget usages
* Fix budget checking in BaseAgent.__next__
* Fix cycle budget initialization
* Fix function calling in BaseAgent.think()
* Include functions in token length calculation
* Fix Config errors
* Add debug thing to patched_api_requestor to investigate HTTP 400 errors
* If this works I'm gonna be sad
* Fix BaseAgent cycle budget logic and document attributes
* Document attributes on `Agent`
* Fix import issues between Agent and MessageHistory
* Improve typing
* Extract application code from the agent (#4982)
* Extract application code from the agent
* Wrap interaction loop in a function and call in benchmarks
* Forgot the important function call
* Add docstrings and inline comments to run loop
* Update typing and docstrings in agent
* Docstring formatting
* Separate prompt construction from on_before_think
* Use `self.default_cycle_instruction` in `Agent.think()`
* Fix formatting
* hot fix the SIGINT handler (#4997)
The signal handler in the autogpt/main.py doesn't work properly because
of the clean_input(...) func. This commit remedies this issue. The issue
is mentioned in
3966cdfd69 (r1264278776)
* Update the sigint handler to be smart enough to actually work (#4999)
* Update the sigint handler to be smart enough to actually work
* Update autogpt/main.py
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* Can still use context manager
* Merge in upstream
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* Fix CI
* Fix initial prompt construction
* off by one error
* allow exit/EXIT to shut down app
* Remove dead code
---------
Co-authored-by: collijk <collijk@uw.edu>
Co-authored-by: Cyrus <39694513+cyrus-hawk@users.noreply.github.com>
* add feature custom text embedding in plugin
* black code format
* _get_embedding_with_plugin()
* Fix docstring & type hint
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* Add links to github issues in the README and clarify run instructions
* Rename agent subpackage to agents
* Revert all unwanted changes
* Use relative import in `agents/__init__.py`
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* Consolidate all logging stuff into one module
* Merge import statement for `logs` and `logs.log_cycle`
---------
Co-authored-by: James Collins <collijk@uw.edu>
* Document function get_memory in ./scripts/memory/init.py
* Update get_memory docstring to current format
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* [Fix] Recover the azure config load function
* [Style] Apply black, isort, mypy, autoflake
* [Fix] Rename the return parameter from 'azure_model_map' to 'azure_model_to_deployment_id_map'
* [Feat] Change the azure config file path to be dynamically configurable
* [Test] Add azure_config and azure deployment_id_for_model
* [Style] Apply black, isort, mypy, autoflake
* [Style] Apply black, isort, mypy, autoflake
* Refactor Azure configuration
- Refactor the `azure_config_file` attribute in the `Config` class to be optional.
- Refactor the `azure_model_to_deployment_id_map` attribute in the `Config` class to be optional and provide default values.
- Update the `get_azure_deployment_id_for_model` function to accept additional parameters.
- Update references to `get_azure_deployment_id_for_model` in `create_text_completion`, `create_chat_completion`, and `get_embedding` functions to pass the required parameters.
* Clean up process for azure
* Docstring
* revert some unneccessary fiddling
* Avoid altering args to models
* Retry on 404s
* Don't permanently change the environment
* Formatting
---------
Co-authored-by: Luke <2609441+lc0rp@users.noreply.github.com>
Co-authored-by: lc0rp <2609411+lc0rp@users.noreply.github.com>
Co-authored-by: collijk <collijk@uw.edu>
Further changes:
* remove `init` param from `get_memory()`, replace usages by `memory.clear()`
* make token length calculation optional in `MemoryItem.dump()`
* Extract open ai api calls and retry at lowest level
* Forgot a test
* Gotta fix my local docker config so I can let pre-commit hooks run, ugh
* fix: merge artiface
* Fix linting
* Update memory.vector.utils
* feat: make sure resp exists
* fix: raise error message if created
* feat: rename file
* fix: partial test fix
* fix: update comments
* fix: linting
* fix: remove broken test
* fix: require a model to exist
* fix: BaseError issue
* fix: runtime error
* Fix mock response in test_make_agent
* add 429 as errors to retry
---------
Co-authored-by: k-boikov <64261260+k-boikov@users.noreply.github.com>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
Co-authored-by: Nicholas Tindle <nicktindle@outlook.com>
Co-authored-by: Luke K (pr-0f3t) <2609441+lc0rp@users.noreply.github.com>
Co-authored-by: Merwane Hamadi <merwanehamadi@gmail.com>
* Correct and clean up JSON handling
* Use ast for message history too
* Lint
* Add comments explaining why we use literal_eval
* Add descriptions to llm_response_format schema
* Parse responses in code blocks
* Be more careful when parsing in code blocks
* Lint
* Implement Batch Running Summarization to avoid max token error (#4652)
* Fix extra space in prompt
---------
Co-authored-by: Reinier van der Leer <github@pwuts.nl>
* Add config as attribute to Agent, rename old config to ai_config
* Code review: Pass ai_config
---------
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
Co-authored-by: merwanehamadi <merwanehamadi@gmail.com>
* Extract retry logic, unify embedding functions
* Add some docstrings
* Remove embedding creation from API manager
* Add test suite for retry handler
* Make api manager fixture
* Fix typing
* Streamline tests
* Collect all embedding code into a single module
* Collect all embedding code into a single module
* actually, llm_utils is a better place
* Oh, and remove the module now that we don't use it
---------
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
* Implemented running cost counter for chat completions
This data is known to the AI as additional system context, and is printed out to the user
* Added comments to api_manager.py
* Added user-defined API budget.
The user is now prompted if they want to give the AI a budget for API calls. If they enter nothing, there is no monetary limit, but if they define a budget then the AI will be told to shut down gracefully once it has come within 1 cent of its limit, and to shut down immediately once it has exceeded its limit. If a budget is defined, Auto-GPT is always aware of how much it was given and how much remains to be spent.
* Chat completion calls are now done through api_manager. Total running cost is printed.
* Implemented api budget setting and tracking
User can now configure a maximum api budget, and the AI is aware of that and its remaining budget. The AI is instructed to shut down when exceeding the budget.
* Update autogpt/api_manager.py
Change "per token" to "per 1000 tokens" in a comment on the api cost
Co-authored-by: Rob Luke <code@robertluke.net>
* Fixed lint errors
* Include embedding costs
* Add embedding completion cost
* lint
* Added 'requires_api_key' decorator to test_commands.py, switched to a valid chat completions model
* Refactor API manager, add debug mode, and add tests
- Extract model costs to to avoid duplication
- Add debug mode parameter to ApiManager class
- Move debug mode configuration to
- Log AI response and budget messages in debug mode
- Implement 'test_api_manager.py'
* Fixed test_setup failing. An extra user input is needed for api budget
* Linting
---------
Co-authored-by: Rob Luke <code@robertluke.net>
Co-authored-by: Nicholas Tindle <nick@ntindle.com>
File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/weaviate/schema/crud_schema.py", line 708, in _create_class_with_primitives
raise UnexpectedStatusCodeException("Create class", response)
weaviate.exceptions.UnexpectedStatusCodeException: Create class! Unexpected status code: 422, with response body: {'error': [{'message': "'Auto-gpt' is not a valid class name"}]}.
GPT4:
The error message indicates that "Auto-gpt" is not a valid class name. In Weaviate, class names must start with a capital letter and can contain only alphanumeric characters.
Took advice and code and applying to weaviate.py to great result, programs runs now with no error!
Unable to reproduce easily. Might be related to switching memory between Local and Weaviate? Either way, the proposed solution works for MacOS using Docker + Weaviate.
