emrgnt-cmplxty · emrgnt-cmplxty · Jun 30, 2023 · Jun 30, 2023 · Jun 30, 2023
diff --git a/.setup.sh.example b/.setup.sh.example
@@ -0,0 +1,48 @@
+## NOTE - the code below is contained in setup.sh.example
+
+# Clone the repository
+git clone git@github.com:emrgnt-cmplxty/Automata.git
+cd Automata
+
+# Create the local environment
+python3 -m venv local_env
+source local_env/bin/activate
+
+# Install the project in editable mode
+pip3 install -e .
+
+# Setup pre-commit hooks
+pre-commit install
+
+# Set up .env
+cp .env.example .env
+OPEN_API_KEY=your_openai_api_key_here
+GITHUB_API_KEY=your_github_api_key
+CONVERSATION_DB_PATH="$PWD/conversation_db.sqlite3"
+TASK_DB_PATH="$PWD/task_db.sqlite3"
+TASKS_OUTPUT_PATH="$PWD/tasks"
+REPOSITORY_NAME="emrgnt-cmplxty/Automata"
+sed -i "s|your_openai_api_key|$OPEN_API_KEY|" .env
+sed -i "s|your_github_api_key|$GITHUB_API_KEY|" .env
+sed -i "s|your_conversation_db_path|$CONVERSATION_DB_PATH|" .env
+sed -i "s|your_task_db_path|$TASK_DB_PATH|" .env
+sed -i "s|your_tasks_output_path|$TASKS_OUTPUT_PATH|" .env
+sed -i "s|your_repository_name|$REPOSITORY_NAME|" .env
+# Additional Notes -
+# Default Max Workers is 8, manually change the .env to update this quantity.
+# For MAC users, the example should read as follows -
+## sed -i '' "s|your_openai_api_key|$OPEN_API_KEY|" .env
+
+# Fetch the submodules
+git submodule update --init --recursive
+
+### NOTE - You must install git-lfs, if you have not done so already
+
+### For Ubuntu, run the following:
+##  sudo apt-get install git-lfs
+### For Mac, run the following:
+##  brew install git-lfs
+###
+### Then, initialize by running the following:
+##  git lfs install
+##  git lfs pull
diff --git a/README.md b/README.md
@@ -12,16 +12,14 @@
 
 This project is inspired by the theory that code is essentially a form of memory, and when furnished with the right tools, AI can evolve real-time capabilities which can potentially lead to the creation of AGI. The word automata comes from the Greek word αὐτόματος, denoting "self-acting, self-willed, self-moving,", and [Automata theory](https://en.wikipedia.org/wiki/Automata_theory) is the study of abstract machines and [automata](https://en.wikipedia.org/wiki/Automaton), as well as the computational problems that can be solved using them. More information follows below.
 
-## 🧠 [Read the Docs](https://automata.readthedocs.io/en/latest/)
-
 ---
 
-## Demo
+## 🧠 [Read the Docs](https://automata.readthedocs.io/en/latest/)
 
+## Demo
 
 https://github.com/emrgnt-cmplxty/Automata/assets/68796651/2e1ceb8c-ac93-432b-af42-c383ea7607d7
 
-
 <img width="1059" alt="Automata_Rough_Schematic_06_22_23" src="https://github.com/emrgnt-cmplxty/Automata/assets/68796651/57ae3418-c01b-4b3f-a548-2f050c234b34">
 
 ---
@@ -33,83 +31,27 @@ https://github.com/emrgnt-cmplxty/Automata/assets/68796651/2e1ceb8c-ac93-432b-af
 Follow these steps to setup the Automata environment
 
 ```bash
-## NOTE - the code below is contained in setup.sh.example
-
-# Clone the repository
-git clone git@github.com:emrgnt-cmplxty/Automata.git
-cd Automata
-
-# Create the local environment
-python3 -m venv local_env
-source local_env/bin/activate
-
-# Install the project in editable mode
-pip3 install -e .
-
-# Setup pre-commit hooks
-pre-commit install
-
-# Set up .env
-cp .env.example .env
-OPEN_API_KEY=your_openai_api_key_here
-GITHUB_API_KEY=your_github_api_key
-CONVERSATION_DB_PATH="$PWD/conversation_db.sqlite3"
-TASK_DB_PATH="$PWD/task_db.sqlite3"
-TASKS_OUTPUT_PATH="$PWD/tasks"
-REPOSITORY_NAME="emrgnt-cmplxty/Automata"
-sed -i "s|your_openai_api_key|$OPEN_API_KEY|" .env
-sed -i "s|your_github_api_key|$GITHUB_API_KEY|" .env
-sed -i "s|your_conversation_db_path|$CONVERSATION_DB_PATH|" .env
-sed -i "s|your_task_db_path|$TASK_DB_PATH|" .env
-sed -i "s|your_tasks_output_path|$TASKS_OUTPUT_PATH|" .env
-sed -i "s|your_repository_name|$REPOSITORY_NAME|" .env
-# Additional Notes -
-# Default Max Workers is 8, manually change the .env to update this quantity.
-# For MAC users, the example should read as follows -
-## sed -i '' "s|your_openai_api_key|$OPEN_API_KEY|" .env
-
-# Fetch the submodules
-git submodule update --init --recursive
-
-### NOTE - You must install git-lfs, if you have not done so already
-
-### For Ubuntu, run the following:
-##  sudo apt-get install git-lfs
-### For Mac, run the following:
-##  brew install git-lfs
-###
-### Then, initialize by running the following:
-##  git lfs install
-##  git lfs pull
-```
-
-### Indexing
-
-[SCIP indices](https://about.sourcegraph.com/blog/announcing-scip) are required to run the Automata Search. These indices are used to create the code graph which relates all dependencies. New indices are generated and uploaded periodically for the Automata Interpreter codebase, but developers must be generate them manually if necessary for their local development. If you encounter issues, we recommending referring to the [instructions here](https://github.com/sourcegraph/scip-python).
-
-```bash
-# Activate the local repository
-source local_env/bin/activate
+# Copy the env and setup files
+cp .setup.sh.example setup.sh && cp .env.example .env
 
-# Install scip-python locally
-cd scip-python
-npm install
+# Allow for execution  
+chmod 755 setup.sh
 
-# Build the tool
-cd packages/pyright-scip
-npm run build
+# Update the setup and env files with your local paths
+vim setup.sh
+vim .env
 
-# Return to working dir
-cd ../../../
-
-# Generate the local index
-node scip-python/packages/pyright-scip/index index  --project-name automata --output index_from_fork.scip  --target-only automata
+# Run the setup script
+./setup.sh
+```
 
-# Copy into the default index location
-mv index_from_fork.scip automata/config/symbol/index.scip
+### Indexing
 
+[SCIP indices](https://about.sourcegraph.com/blog/announcing-scip) are required to run the Automata Search. These indices are used to create the code graph which relates symbols by dependencies across the codebase. New indices are generated and uploaded periodically for the Automata codebase, but programmers must be generate them manually if necessary for their local development. If you encounter issues, we recommend referring to the [instructions here](https://github.com/sourcegraph/scip-python).
 
-### Alternatively, you mean run ./regenerate_index after changing local permissions and completing the above install.
+```bash
+# Install dependencies and run indexing on the local codebase
+./install_indexing.sh && ./regenerate_index.sh
 ```
 
 ### Build the embeddings + docs
@@ -122,11 +64,9 @@ automata run-code-embedding
 
 # "L1" docs are the docstrings written into the code
 # "L2" docs are generated from the L1 docs + symbol context
-# Build/refresh and embed the L2 docs
 automata run-doc-embedding-l2
 
 # "L3" docs are generated from the L2 docs + symbol context
-# Build/refresh and embed the L3 docs
 automata run-doc-embedding-l3
 ```
 

diff --git a/automata/docs/config/agent_config.rst b/automata/docs/config/agent_config.rst
@@ -1,62 +1,117 @@
-AgentConfig
-===========
+``AgentConfig`` Class
+=====================
+
+The ``AgentConfig`` class is a base abstraction for creating specific
+configurations to be used by agent instances. It includes necessary
+parameters such as instructions to be executed by the agent, a list of
+tools used, a model name, and various boolean flags for stream and
+verbose logging status.
+
+In addition, it holds the max iterations and temperature settings for
+the agent’s operation. It also has an optional session id attribute.
+
+This class is an abstract base class (ABC), and it includes abstract
+methods, requiring subclasses to provide concrete implementations of
+these methods.
+
+Attributes
+----------
+
+-  ``config_name``: Defines the name of the configuration.
+-  ``tools``: Sets a list of Tools to be used by the agent.
+-  ``instructions``: A string set by the user to handle instructions for
+   the agent.
+-  ``description``: A string to hold any necessary description.
+-  ``model``: Defines the model to be used by the agent.
+-  ``stream``: Boolean variable to define whether to use stream
+   functionality.
+-  ``verbose``: Boolean variable to define whether verbose logging
+   should be used.
+-  ``max_iterations``: Sets the maximum iterations count for the agent
+   operations.
+-  ``temperature``: Sets the temperature scalar for the agent
+   operations.
+-  ``session_id``: (Optional) Defines the session id for the agent.
+
+Methods
+-------
 
-``AgentConfig`` is an abstract base class that provides a template for
-configurations related to providers. It contains abstract methods like
-``setup()`` and ``load()`` that need to be implemented by subclasses.
-This class also handles the configuration of arbitrary types during the
-initialization.
+setup
+~~~~~
 
-Overview
---------
+A method that subclasses must implement. Its purpose is to be defined by
+the subclasses.
 
-``AgentConfig`` is designed for ensuring configurability of providers.
-Subclasses need to provide implementations for the ``setup()`` and
-``load()`` methods in order to properly define the behavior during the
-agent setup and configuration loading processes. This class follows the
-BaseModel design, making it easy to extend and customize according to
-specific agent requirements.
+load
+~~~~
 
-Related Symbols
----------------
+A method that subclasses must implement. It should load the agent
+configuration based on the provided name.
 
--  ``automata.core.agent.instances.AutomataOpenAIAgentInstance.Config``
--  ``automata.tests.unit.test_automata_agent_builder.test_builder_default_config``
--  ``automata.tests.unit.test_task_environment.TestURL``
--  ``automata.core.base.agent.AgentInstance.Config``
+get_llm_provider
+~~~~~~~~~~~~~~~~
 
-Example
--------
+A static method that subclasses must implement. The method should return
+the provider for the agent.
 
-The following example demonstrates how to create a custom agent
-configuration by extending the ``AgentConfig`` class:
+\_load_automata_yaml_config
+~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
-.. code:: python
+This method is responsible for loading YAML configuration for the agent.
+It opens a YAML file, processes its content, and loads them into an
+agent configuration instance. If ``config_name`` appears in the loaded
+YAML, it raises an Exception. Once the loading completes, it adds
+``config_name`` to the loaded YAML and returns it.
 
-   from config.config_types import AgentConfig
+Inherited Classes
+-----------------
 
-   class CustomAgentConfig(AgentConfig):
+The ``AutomataOpenAIAgentConfig`` is a concrete class that inherits from
+``AgentConfig``. This class specifies ``OPENAI`` as the ``LLMProvider``
+and allows the use of different models. It further enriches the
+configuration by defining the system template, system template
+variables, system template formatter, instruction version, and system
+instruction.
 
-       def setup(self):
-           # Define your custom agent setup process
-           pass
+Example
+-------
 
-       @classmethod
-       def load(cls, config_name: AgentConfigName) -> "CustomAgentConfig":
-           # Load the config for your custom agent
-           pass
+Creating a derived class ``AutomataOpenAIAgentConfig`` and using the
+``load`` method:
+
+.. code:: python
+
+       from automata.config.openai_agent import AutomataOpenAIAgentConfig
+       from automata.config.base import AgentConfigName
+
+       config = AutomataOpenAIAgentConfig.load(AgentConfigName.DEFAULT)
+       assert isinstance(config, AutomataOpenAIAgentConfig)
 
 Limitations
 -----------
 
-``AgentConfig`` itself is an abstract class and cannot directly be
-instantiated. It must be subclassed, and its methods need to be
-implemented by the extending class according to the specific agent
-requirements. Additionally, the current implementation allows for
-arbitrary types, which may lead to code that is not type-safe.
+The class ``AgentConfig`` is an abstract base class and cannot be
+directly used to create an object. It must be subclassed, and each
+subclass must provide implementations for the abstract methods.
+
+A derived class can load YAML configurations from a specific file
+location, and this could raise file operation related exceptions. For
+instance, if the configuration file is not found or if the YAML file is
+not in the correct format, corresponding exceptions will be raised.
+
+When a ``config_name`` is found in the loaded_yaml, the
+``_load_automata_yaml_config`` method throws an error stating:
+“config_name already specified in YAML. Please remove this from the YAML
+file.” This could be a limitation when the user does not have much
+control over the yaml content or if the yaml modification would conflict
+with other requirements.
 
 Follow-up Questions:
 --------------------
 
--  How can we ensure type safety while maintaining the flexibility and
-   customizability provided by ``AgentConfig``?
+-  How to manage the file operation exceptions when loading yaml
+   configuration?
+-  Can we modify ``_load_automata_yaml_config`` to allow ``config_name``
+   in yaml or provide a mechanism to overwrite it?
+-  What to do when we need to set up an ``AgentConfig`` with varying
+   attributes not defined in existing classes?