Merge pull request #23 from beautiful-code/course_lessons_extraction

endpoints.py

@@ -2,6 +2,8 @@ from dotenv import load_dotenv
 import uvicorn
 from fastapi import FastAPI, Query
 from .workflows.til import TilCrew, TilFeedbackResponse
+from .workflows.courses.suggest_expectations import SuggestExpectations, Inputs as SuggestExpectationsInputs, Expectations, Expectation
+from .workflows.courses.expectation_revision import ExpectationRevision, Inputs as ExpectationRevisionInputs
 from .workflows.utils.feedback import Feedback
 from fastapi.middleware.cors import CORSMiddleware
 from typing import List, Optional
@@ -52,6 +54,18 @@ async def capture_feedback(run_id: UUID4, feedback: Feedback) -> str:
     TilCrew.post_feedback(run_id=run_id, feedback=feedback)
     return "ok"
 
+@app.post("course_learn/suggest_expectations", tags=["course_learn"])
+async def course_learn_suggest_expectations(inputs: SuggestExpectationsInputs) -> Expectations:
+    print("Inputs: ", inputs)
+    result = SuggestExpectations().kickoff(inputs=inputs)
+    return result
+
+@app.post("course_learn/expectation_revision", tags=["course_learn"])
+async def course_learn_suggest_expectations(inputs: ExpectationRevisionInputs) -> Expectation:
+    print("Inputs: ", inputs)
+    result = ExpectationRevision().kickoff(inputs=inputs)
+    return result
+
 @app.get("/healthcheck")
 async def read_root():
      return {"status": "ok"}

workflows/courses/expectation_revision.py

@@ -0,0 +1,50 @@
+from langchain import hub
+from langchain_core.output_parsers import JsonOutputParser
+from langchain_openai import ChatOpenAI
+from pydantic import BaseModel
+from workflows.courses.suggest_expectations import Expectation
+from typing import List, Optional
+import os
+
+class Inputs(BaseModel):
+    expectation: str
+    check_question: str
+    request: str
+
+class ExpectationRevision:
+    def kickoff(self, inputs={}):
+        self.learning_outcome = inputs["expectation"]
+        self.check_question = inputs["check_question"]
+        self.request = inputs["request"]
+        return self._get_suggestion()
+
+    def _get_suggestion(self):
+        parser = JsonOutputParser(pydantic_object=Expectation)
+        prompt = hub.pull("course_learn_expectation_revision")
+        llm = ChatOpenAI(model=os.environ['OPENAI_MODEL'], temperature=0.2)
+        chain = (prompt | llm | parser).with_config({
+            "tags": ["course_learn", "suggest_expectations"], "run_name": "Suggest Module Expectations",
+            "metadata" : {
+                "versoin": "v1.0.0",
+                "growth_activity": "course_learn",
+                "env": os.environ["ENV"],
+                "model": os.environ["OPENAI_MODEL"],
+            }
+        })
+
+        response = chain.invoke({
+            "learning_outcome": self.learning_outcome, "check_question": self.check_question, "request": self.request,
+            "format_instructions": parser.get_format_instructions()
+          })
+
+        return response
+
+
+# Example usage
+# rework = ExpectationRevision()
+# response = rework.kickoff(inputs={
+#     "expectation": "Recognize the importance of query rewriting and how to transform inefficient queries into more efficient ones.",
+#     "check_question": "Can you provide an example of a poorly written SQL query and demonstrate how you would rewrite it to optimize its performance?",
+#     "request": "Can you provide the poorly written SQL query that user has to rewrite"
+# })
+# print(response)

workflows/courses/suggest_expectations.py

@@ -0,0 +1,63 @@
+from langchain import hub
+from langchain_core.output_parsers import JsonOutputParser
+from langchain_openai import ChatOpenAI
+from pydantic import BaseModel, Field
+from typing import List
+from pydantic import BaseModel
+from typing import List, Optional
+import os
+
+class Expectation(BaseModel):
+    expectation: str = Field(description="The learning outcome that the course designer has identified for the learner to demonstrate upon successful completion of the module.")
+    check_question: str = Field(description="Targeted question that the course designer have developed to assess the learner's understanding of the learning outcomes.")
+
+class Expectations(BaseModel):
+    expectations: List[Expectation]
+
+class Inputs(BaseModel):
+    course: str
+    module: str
+    tasks: List[str]
+
+
+class SuggestExpectations:
+    def kickoff(self, inputs={}):
+        self.course = inputs["course"]
+        self.module = inputs["module"]
+        self.tasks = inputs["tasks"]
+        return self._get_suggestions()
+
+    def _get_suggestions(self):
+        parser = JsonOutputParser(pydantic_object=Expectations)
+        prompt = hub.pull("course_learn_suggest_expectations_from_learner")
+        llm = ChatOpenAI(model=os.environ['OPENAI_MODEL'], temperature=0.2)
+        chain = (prompt | llm | parser).with_config({
+            "tags": ["course_learn", "suggest_expectations"], "run_name": "Suggest Module Expectations",
+            "metadata" : {
+                "versoin": "v1.0.0",
+                "growth_activity": "course_learn",
+                "env": os.environ["ENV"],
+                "model": os.environ["OPENAI_MODEL"],
+            }
+        })
+
+        response = chain.invoke({
+            "course": self.course, "module": self.module, "tasks": "* " + ("\n* ".join(self.tasks)),
+            "format_instructions": parser.get_format_instructions()
+          })
+
+        return response
+
+
+# Example usage
+# suggester = SuggestExpectations()
+# response = suggester.kickoff(inputs={
+#     "course": "SQL",
+#     "module": "Query Optimization Techniques",
+#     "tasks": [
+#         "Watch this video https://youtu.be/BHwzDmr6d7s?si=sfFYnd73y9w0EjGB to understand SQL execution order and some optimization techniques.",
+#         "Watch this video https://youtu.be/FoznjTU929c?si=6M3xUIUwAxE6EbKS to understand SQL explain command usage.",
+#         "Go over these articles https://intellipaat.com/blog/sql-optimization-techniques/ & https://www.thoughtspot.com/data-trends/data-modeling/optimizing-sql-queries  to understand various query optimization techniques."
+#     ]
+# })
+# print(response)

workflows/utils/feedback.py

@@ -2,7 +2,6 @@ from pydantic import BaseModel
 from typing import List, Optional
 
 class Feedback(BaseModel):
-    helpful_score: Optional[float]=None
     metric_type: Optional[str]
     metric_score: Optional[float]
     feedback_on: Optional[str]