Prompt changes

README.md

@@ -87,11 +87,11 @@ pip install -r requirements.txt
 ### Step 4: Create a new .env and store the API Key
 
 1. Create a new file called `.env` in the root of the project.
-2. Copy the contents of the `.env.example` file into the `.env` file.
+2. Copy the contents of the `.env.sample` file into the `.env` file.
 3. Replace the placeholder values with your API key and project ID.
 4. Set the `ENV_TYPE` variable to `dev`.
 
-### Step 4: Run the Application with Local Shell Script
+### Step 5: Run the Application with Local Shell Script
 
 1. Run the following command to start the application:
 

app/features/syllabus_generator/core.py

@@ -0,0 +1,50 @@
+# This is code from quizbuilder - repurpose for syllabus generator
+from services.logger import setup_logger
+from gemini_api_client import generate_response
+from tools import course_objectives,course_description,course_outline,grading_policy,rules_policies,study_materials,final_output
+logger = setup_logger()
+
+def executor(grade_level: str, topic: str, context: str) -> str:
+    """
+    Executes the tool's functionality.
+
+    Args:
+        grade_level (int): The grade level for the content.
+        topic (str): The topic of interest.
+        context (str): Additional context or information.
+
+    Returns:
+        str: The result or output of the tool's functionality.
+    """
+    try:
+        description = course_description(grade_level,topic,custom_info=context)
+
+        objectives = course_objectives(grade_level,topic,description,custom_info=context)
+
+        outline = course_outline(grade_level,topic,description,objectives,custom_info=context)
+
+        grading = grading_policy(grade_level,topic,outline,custom_info=context)
+
+        class_rules = rules_policies(grade_level,topic,outline,custom_info=context)
+
+        materials = study_materials(grade_level,topic,outline,custom_info=context)
+
+        response = final_output(description,objectives,outline,grading,class_rules,materials)
+        # Example of tool's logic (this should be detailed and explicit before abstraction)
+        #logger.error(f"Executing with grade_level={grade_level}, topic={topic}, context={context}")
+
+        # Here you would define the core functionality
+        #Prompt
+        #prompt_template = f"Create content for grade {grade_level} on {topic}. Context: {context}"
+        # Call the Gemini API to generate a response
+        #response = generate_response(prompt_template) 
+
+        #logger.error(f"Execution successful: {response}")
+
+
+    except Exception as e:
+        error_message = f"Error in executor: {e}"
+        logger.error(error_message)
+        raise ValueError(error_message)
+
+    return response

app/features/syllabus_generator/metadata.json

@@ -0,0 +1,19 @@
+{
+    "inputs": [
+        {
+            "label": "Grade",
+            "name": "grade_level",
+            "type": "text"
+        },
+        {
+            "label": "Subject",
+            "name": "topic",
+            "type": "text"
+        },
+        {
+            "label": "Custom Info",
+            "name": "context",
+            "type": "text"
+        }
+    ]
+}

app/features/syllabus_generator/prompt/course_description.txt

@@ -0,0 +1,7 @@
+You are an expert syllabus generator. Your have to create a concise and hollistic course descriptionfor:
+Grade : {grade}
+Subject : {subject}
+Customized information : {custom_info}
+
+*Respond only with The descripion that should be a brief summary convering key aspects of the course
+Answer: 

app/features/syllabus_generator/prompt/course_objectives.txt

@@ -0,0 +1,18 @@
+You are an expert syllabus generator. Your have to create a concise and hollistic course objectives for:
+Grade : {grade}
+Subject : {subject}
+Customized information : {custom_info}
+------------
+Course Description ( Use as reference ):
+{course_description}
+
+*The response should be structured as a list. Ensure that the response can be loaded using json.loads in Python.
+Answer: 
+
+Example structure of the response:
+[
+    "<Objective 1 here ...>",
+    "<Objective 2 here ...>",
+    "<Objective 3 here ...>",
+    ...
+]

app/features/syllabus_generator/prompt/course_outline.txt

@@ -0,0 +1,29 @@
+You are an expert syllabus generator. Your have to create a detailed course outline or:
+Grade : {grade}
+Subject : {subject}
+Customized information : {custom_info}
+-----------------
+Course Description ( use as reference ):
+{course_description}
+------------------
+Course Objectives ( use as reference ):
+{course_objectives}
+*The outline should be well structured and detail all the syllabus in a form of a list of dictionnaries . Ensure that the response can be loaded using json.loads in Python.
+Answer: 
+
+Example structure of the response:
+[
+    {{
+        "week": 1, 
+        "topic": "<The topic for week 1 ...>"
+    }},
+    {{
+        "week": 2, 
+        "topic": "<The topic for week 2 ...>"
+    }},
+    {{
+        "week": 3, 
+        "topic": "<The topic for week 3 ...>"
+    }},
+    ...
+]

app/features/syllabus_generator/prompt/grading_policy.txt

@@ -0,0 +1,9 @@
+You are an expert syllabus generator. Your have to create a grading policy for:
+Grade : {grade}
+Subject : {subject}
+Customized information : {custom_info}
+------------------
+Course Outline ( use as reference ):
+{course_outline}
+*The grading policy should be suitable and relevant , the response should be only the grading policy
+Answer: 

app/features/syllabus_generator/prompt/rules_policies.txt

@@ -0,0 +1,17 @@
+You are an expert syllabus generator. Your have to create class rules and instructions for:
+Grade : {grade}
+Subject : {subject}
+Customized information : {custom_info}
+------------------
+Course Outline ( use as reference ):
+{course_outline}
+*The rules and policies should be numerically listed in order of importance in a form of a python list.Ensure that the response can be loaded using json.loads in Python.
+Answer: 
+
+Example structure of the response:
+[
+    "<Rule 1 here ...>",
+    "<Rule 2 here ...>",
+    "<Rule 3 here ...>",
+    ...
+]

app/features/syllabus_generator/prompt/study_materials.txt

@@ -0,0 +1,28 @@
+You are an expert syllabus generator. Your have to create the study material listfor:
+Grade : {grade}
+Subject : {subject}
+Customized information : {custom_info}
+------------------
+Course Outline ( use as reference ):
+{course_outline}
+
+*Explain which study material is used for which purpose
+The response should be structured as a list of dictionaries with the study material and it's purpose. Ensure that the response can be loaded using json.loads in Python.
+Answer: 
+
+Example structure of the response:
+[
+    {{
+        "material": "<Material 1 here>",
+        "purpose" : "<The purpose for material 1 ...>"
+    }},
+    {{
+        "material": "<Material 2 here>",
+        "purpose" : "<The purpose for material 2 ...>"
+    }},
+    {{
+        "material": "<Material 3 here>",
+        "purpose" : "<The purpose for material 3 ...>"
+    }},
+    ...
+]

app/features/syllabus_generator/tests/test_core.py

@@ -0,0 +1,5 @@
+
+from core import executor
+
+def test_executor():
+    assert executor 

app/features/syllabus_generator/tests/test_tools.py

@@ -0,0 +1,175 @@
+import unittest
+import os
+from unittest.mock import patch, MagicMock
+from tools import (
+    read_text_file, 
+    build_prompt, 
+    course_description, 
+    course_objectives, 
+    course_outline, 
+    grading_policy, 
+    rules_policies, 
+    study_materials, 
+    final_output
+)
+class TestFunctions(unittest.TestCase):
+
+    def setUp(self):
+        # Setup a test file
+        self.test_file_name = 'test_file.txt'
+        self.test_content = 'Hello, world!'
+        script_dir = os.path.dirname(os.path.abspath(__file__))
+        self.test_file_path = os.path.join(script_dir, self.test_file_name)
+        with open(self.test_file_path, 'w') as f:
+            f.write(self.test_content)
+
+
+    def tearDown(self):
+        # Clean up the test file after each test
+
+        os.remove(self.test_file_path)
+
+    def test_read_text_file(self):
+        result = read_text_file(self.test_file_name)
+        self.assertEqual(result, self.test_content)
+
+    @patch('your_module.read_text_file')
+    @patch('your_module.PromptTemplate')
+    def test_build_prompt(self, MockPromptTemplate, mock_read_text_file):
+        mock_read_text_file.return_value = self.test_content
+        mock_prompt_template_instance = MockPromptTemplate.from_template.return_value
+        mock_prompt_template_instance.return_value = self.test_content
+
+        result = build_prompt(self.test_file_name)
+        MockPromptTemplate.from_template.assert_called_once_with(self.test_content)
+        self.assertEqual(result, mock_prompt_template_instance)
+
+    @patch('your_module.build_prompt')
+    @patch('your_module.GoogleGenerativeAI')
+    def test_course_description(self, MockGoogleGenerativeAI, mock_build_prompt):
+        mock_build_prompt.return_value = MagicMock()
+        mock_model = MockGoogleGenerativeAI.return_value
+        mock_chain = MagicMock()
+        mock_model.__or__.return_value = mock_chain
+        mock_chain.invoke.return_value = "Generated course description"
+
+        result = course_description(10, "Math")
+        mock_chain.invoke.assert_called_once_with({"grade": 10, "subject": "Math", "custom_info": 'None'})
+        self.assertEqual(result, "Generated course description")
+
+    @patch('your_module.build_prompt')
+    @patch('your_module.GoogleGenerativeAI')
+    def test_course_objectives(self, MockGoogleGenerativeAI, mock_build_prompt):
+        mock_build_prompt.return_value = MagicMock()
+        mock_model = MockGoogleGenerativeAI.return_value
+        mock_chain = MagicMock()
+        mock_model.__or__.return_value = mock_chain
+        mock_chain.invoke.return_value = "Generated course objectives"
+
+        result = course_objectives(10, "Math", "Course description")
+        mock_chain.invoke.assert_called_once_with({
+            "grade": 10, 
+            "subject": "Math", 
+            "custom_info": 'None', 
+            'course_description': 'Course description'
+        })
+        self.assertEqual(result, "Generated course objectives")
+
+    @patch('your_module.build_prompt')
+    @patch('your_module.GoogleGenerativeAI')
+    def test_course_outline(self, MockGoogleGenerativeAI, mock_build_prompt):
+        mock_build_prompt.return_value = MagicMock()
+        mock_model = MockGoogleGenerativeAI.return_value
+        mock_chain = MagicMock()
+        mock_model.__or__.return_value = mock_chain
+        mock_chain.invoke.return_value = "Generated course outline"
+
+        result = course_outline(10, "Math", "Course description", "Course objectives")
+        mock_chain.invoke.assert_called_once_with({
+            "grade": 10, 
+            "subject": "Math", 
+            "custom_info": 'None', 
+            'course_description': 'Course description',
+            'course_objectives': 'Course objectives'
+        })
+        self.assertEqual(result, "Generated course outline")
+
+    @patch('your_module.build_prompt')
+    @patch('your_module.GoogleGenerativeAI')
+    def test_grading_policy(self, MockGoogleGenerativeAI, mock_build_prompt):
+        mock_build_prompt.return_value = MagicMock()
+        mock_model = MockGoogleGenerativeAI.return_value
+        mock_chain = MagicMock()
+        mock_model.__or__.return_value = mock_chain
+        mock_chain.invoke.return_value = "Generated grading policy"
+
+        result = grading_policy(10, "Math", "Course outline")
+        mock_chain.invoke.assert_called_once_with({
+            "grade": 10, 
+            "subject": "Math", 
+            "custom_info": 'None', 
+            'course_outline': 'Course outline'
+        })
+        self.assertEqual(result, "Generated grading policy")
+
+    @patch('your_module.build_prompt')
+    @patch('your_module.GoogleGenerativeAI')
+    def test_rules_policies(self, MockGoogleGenerativeAI, mock_build_prompt):
+        mock_build_prompt.return_value = MagicMock()
+        mock_model = MockGoogleGenerativeAI.return_value
+        mock_chain = MagicMock()
+        mock_model.__or__.return_value = mock_chain
+        mock_chain.invoke.return_value = "Generated rules and policies"
+
+        result = rules_policies(10, "Math", "Course outline")
+        mock_chain.invoke.assert_called_once_with({
+            "grade": 10, 
+            "subject": "Math", 
+            "custom_info": 'None', 
+            'course_outline': 'Course outline'
+        })
+        self.assertEqual(result, "Generated rules and policies")
+
+    @patch('your_module.build_prompt')
+    @patch('your_module.GoogleGenerativeAI')
+    def test_study_materials(self, MockGoogleGenerativeAI, mock_build_prompt):
+        mock_build_prompt.return_value = MagicMock()
+        mock_model = MockGoogleGenerativeAI.return_value
+        mock_chain = MagicMock()
+        mock_model.__or__.return_value = mock_chain
+        mock_chain.invoke.return_value = "Generated study materials"
+
+        result = study_materials(10, "Math", "Course outline")
+        mock_chain.invoke.assert_called_once_with({
+            "grade": 10, 
+            "subject": "Math", 
+            "custom_info": 'None', 
+            'course_outline': 'Course outline'
+        })
+        self.assertEqual(result, "Generated study materials")
+
+    def test_final_output(self):
+
+        course_desc = "Course description"
+        course_obj = "Course objectives"
+        course_out = "Course outline"
+        grading_pol = "Grading policy"
+        rules_pol = "Rules and policies"
+        study_mat = "Study materials"
+
+        result = final_output(course_desc, course_obj, course_out, grading_pol, rules_pol, study_mat)
+
+        expected_output = (
+
+            f"#Course Description\n{course_desc}\n\n"
+            f"#Course Objectives\n{course_obj}\n\n"
+            f"#Course Outline\n{course_out}\n\n"
+            f"#Grading Policy\n{grading_pol}\n\n"
+            f"#Class Rules\n{rules_pol}\n\n"
+            f"#Study Materials\n{study_mat}\n\n"
+        )
+
+        self.assertEqual(result, expected_output)
+
+if __name__ == '__main__':
+    unittest.main()