Merge pull request #207 from sirji-ai/create-and-sync-assistant-actions

Create and sync assistant actions

README.md

@@ -27,27 +27,9 @@
 
 Sirji is a framework designed to build and run custom AI agents for your everyday development tasks.
 
-Sirji has two main product components: Sirji Studio and Sirji VS Code Extension.
+An agent in the Sirji framework is a modular AI component designed to perform specific task based on custom pseudocode. [Here](./docs/How%20to%20Write%20an%20Agent.md) is a guide for writing your own custom agent.
 
-### Sirji Studio
-
-We have built the framework that allows the developer community to build custom agents simply by writing pseudocode in plain English.
-
-Custom agents help capture and convey the developer's code writing style and domain knowledge to Sirji. They performs a specific task based on a custom pseudocode. The community can create a custom agent either by modifying an existing agent or by writing an entirely new agent with a different pseudocode.
-
-[Here](./docs/How%20to%20Write%20Agent%20Pseudocode.md) is a guide for writing agent pseudocode.
-
-### Sirji VS Code Extension
-
-We have build and released the [VS Code Extension](https://marketplace.visualstudio.com/items?itemName=TrueSparrow.sirji) on the Visual Studio Marketplace.
-
-This extension has the following features implemented:
-- Interactive chat interface allows user to submit their problem statements and give feedback to Sirji.
-- Messaging protocol implements the allowed response templates for messages exchanged between various agents.
-- Orchestrator enables requirement gathering, recipe selection, recipe execution by invoking agents
-- Executor makes these functionalities accessible to the agents: file system access, search, find & replace, insert text in project files, install packages, execute commands, run code, run test cases.
-- Agent Sessions provide the ability to invoke an agent with a fresh LLM conversation or continue on an existing LLM conversation.
-- Logs and Token Usage Summary are displayed alongside the interactive chat interface.
+[Here](./docs/Sirji%20Studio.md) is a guide to organize and share your custom agents.
 
 ## Installation
 
@@ -59,7 +41,7 @@ Make sure you have installed all of the following prerequisites on your machine:
 - Python (>= 3.10) - Make sure `python --version` runs without error.
 - tee command - Make sure `which tee` runs without error.
 
-Also, you will need an OpenAI API key to access the GPT-4o model.
+For LLM inference, you would need an API key from at least one of OpenAI, Anthropic or DeepSeek.
 
 ## Demo Video
 

agents/README.md

@@ -28,7 +28,6 @@
 `sirji-agents` is a PyPI package that implements the following components of the Sirji AI agentic framework:
 - **Orchestrator**: The Orchestrator is the central component in the Sirji framework, responsible for managing the flow and execution of tasks across different agents.
 - **Generic Agent**: Run time composable class providing the agent functionality as per the pseudo code provided in the agent.yml file.
-- **Research Agent**: Utilizes RAG (Retrieval-Augmented Generation) and gets trained on URLs and search terms.
 
 By default, it utilizes:
 - OpenAI Chat Completions API
@@ -69,7 +68,6 @@ Ensure that the following environment variables are set:
 export SIRJI_PROJECT="Absolute folder path for Sirji to use as its project folder."
 export SIRJI_INSTALLATION_DIR='Absolute path of the Sirji installation directory.'
 export SIRJI_RUN_PATH='Folder path containing run related logs, etc.'
-export SIRJI_OPENAI_API_KEY='OpenAI API key for Chat Completions API and Assistants API'
 export SIRJI_MODEL_PROVIDER='Model Provider to be used for LLM inference. Defaults to "openai".'
 export SIRJI_MODEL='Model to be used for LLM inference. Defaults to "gpt-4o".'
 export SIRJI_MODEL_PROVIDER_API_KEY='API key to be used for LLM inference.'
@@ -161,63 +159,6 @@ message_str = "***\nFROM: ORCHESTRATOR\nTO: CODER\nACTION: INVOKE_AGENT\nSUMMARY
 response_message, history, prompt_tokens, completion_tokens = agent.message(message_str, history)
 ```
 
-### Research Agent
-
-The Research Agent utilizes RAG (Retrieval-Augmented Generation) and gets trained on URLs and search terms.
-
-### Initialization
-
-```python
-from sirji_agents import ResearchAgent
-
-# Initialize Researcher without assistant ID
-researcher = ResearchAgent('openai_assistant', 'openai_assistant')
-
-# init_payload fetched from researcher object should be persisted
-init_payload = researcher.init_payload
-
-# Initialize Researcher with assistant ID
-researcher = ResearchAgent('openai_assistant', 'openai_assistant', init_payload)
-```
-
-Some example message handling usages are given below.
-
-#### Train using URL
-
-```python
-from sirji_messages import MessageFactory, ActionEnum
-
-message_class = MessageFactory[ActionEnum.TRAIN_USING_URL.name]
-
-body = {
-    "URL": "https://www.w3schools.com/python/python_json.asp"
-}
-
-message_str = message_class().generate({
-            "from_agent_id": "Id of the agent, who is invoking the action",
-            "summary": "{{Display a concise summary to the user, describing the action using the present continuous tense.}}",
-            "body": body
-        })
-
-researcher.message(message_str)
-```
-
-#### Infer
-
-```python
-from sirji_messages import MessageFactory, ActionEnum
-
-message_class = MessageFactory[ActionEnum.INFER.name]
-infer_query = "What is the capital of India?"
-message_str = message_class().generate({
-            "from_agent_id": "Id of the agent, who is invoking the action",
-            "summary": "{{Display a concise summary to the user, describing the action using the present continuous tense.}}",
-            "body": infer_query
-        })  
-
-response, total_tokens = researcher.message(message_str)
-```
-
 ## For Contributors
 
 1. Fork and clone the repository.

agents/requirements.txt

@@ -1,4 +1,4 @@
-sirji-messages==0.0.28
-sirji-tools==0.0.14
-openai==1.14.1
+sirji-messages==0.0.29
+sirji-tools==0.0.15
+openai==1.35.7
 anthropic==0.29.0

agents/setup.py

@@ -2,7 +2,7 @@
 
 setup(
     name='sirji-agents',
-    version='0.0.40',
+    version='0.0.41',
     author='Sirji',
     description='Orchestrator, Generic Agent, and Research Agent components of the Sirji AI agentic framework.',
     license='MIT',

agents/sirji_agents/__init__.py

@@ -1,9 +1,10 @@
-from .researcher import ResearchAgent
+from .researcher import ResearchAgent, CleanupFactory
 from .llm.orchestrator import Orchestrator
 from .llm.generic import GenericAgent
 
 __all__ = [
     'ResearchAgent',
     'Orchestrator',
-    'GenericAgent'
+    'GenericAgent',
+    'CleanupFactory'
 ]

agents/sirji_agents/researcher/__init__.py

@@ -1,3 +1,4 @@
 from .researcher import ResearchAgent
+from .cleanup.factory import CleanupFactory
 
-__all__ = ['ResearchAgent']
+__all__ = ['ResearchAgent', 'CleanupFactory']

agents/sirji_agents/researcher/cleanup/base.py

@@ -0,0 +1,31 @@
+from abc import ABC, abstractmethod
+
+
+class CleanupBase(ABC):
+
+    @abstractmethod
+    def delete_assistant(self, assistant_id):
+        """
+        Deletes the assistant.
+
+        :param assistant_id: The assistant ID to be deleted.
+        """
+        pass
+
+    @abstractmethod
+    def delete_vector_store(self, vector_store_id):
+        """
+        Deletes the vector store.
+
+        :param vector_store_id: The vector store ID to be deleted.
+        """
+        pass
+
+    @abstractmethod
+    def delete_file(self, file_path):
+        """
+        Deletes the file.
+
+        :param file_path: The file path to be deleted.
+        """
+        pass

agents/sirji_agents/researcher/cleanup/factory.py

@@ -0,0 +1,14 @@
+from .openai_cleanup import OpenAICleanup
+import os
+
+
+class CleanupFactory:
+    @classmethod
+    def get_instance(cls):
+
+        provider_name = os.environ.get('SIRJI_MODEL_PROVIDER').lower()
+
+        if provider_name == "openai":
+            return OpenAICleanup()
+        else:
+            raise ValueError("Unsupported provider: {}".format(provider_name))

agents/sirji_agents/researcher/cleanup/openai_cleanup.py

@@ -0,0 +1,52 @@
+import os
+from openai import OpenAI
+
+from sirji_tools.logger import create_logger 
+
+from .base import CleanupBase
+
+class OpenAICleanup(CleanupBase):
+    def __init__(self):      
+        self.logger = create_logger("researcher.log", "debug")
+        api_key = os.environ.get("SIRJI_MODEL_PROVIDER_API_KEY")
+
+        if api_key is None:
+            raise ValueError(
+                "OpenAI API key is not set as an environment variable")
+
+        # Initialize OpenAI client
+        client = OpenAI(api_key=api_key)
+
+        self.logger.info("Completed initializing OpenAI client")
+        self.client = client
+
+
+    def delete_assistant(self, assistant_id):
+        self.logger.info("Deleting assistant")
+        try:
+            response = self.client.beta.assistants.delete(assistant_id)
+            print(response)
+            self.logger.info(response)
+        except Exception as e:
+            print(e)
+            self.logger.error(e)
+
+    def delete_vector_store(self, vector_store_id):
+        try:
+            response = self.client.beta.vector_stores.delete(
+            vector_store_id = vector_store_id
+            )
+            print(response)
+            self.logger.info(response)
+        except Exception as e:
+            print(e)
+            self.logger.error(e)
+
+    def delete_file(self, file_path):
+        try:
+            response = self.client.files.delete(file_path)
+            print(response)
+            self.logger.info(response)
+        except Exception as e:
+            print(e)
+            self.logger.error(e)

agents/sirji_agents/researcher/embeddings/factory.py

@@ -1,10 +1,14 @@
 from .openai_assistant import OpenAIAssistantEmbeddings
+import os
 
 
 class EmbeddingsFactory:
     @classmethod
-    def get_instance(cls, embeddings_type, init_payload):
-        if embeddings_type == "openai_assistant":
+    def get_instance(cls, init_payload):
+
+        provider_name = os.environ.get('SIRJI_MODEL_PROVIDER').lower()
+
+        if provider_name == "openai":
             return OpenAIAssistantEmbeddings(init_payload)
         else:
             raise ValueError("Unsupported embeddings_type.")