Update learning_path_model.py

learning_path_model.py

@@ -1,67 +1,67 @@
-# learning_path_model.py
-from sentence_transformers import SentenceTransformer
-from transformers import pipeline
-from langchain import PromptTemplate, LLMChain, SequentialChain
-from langchain_groq import ChatGroq
-from langchain.embeddings import HuggingFaceEmbeddings
-from dotenv import load_dotenv
-import os
-
-load_dotenv()
-api_key = os.getenv('GROQ_API_KEY')
-# print(api_key)
-
-class LearningPathModel:
-    def __init__(self):
-        # Initialize embedding and NLP models
-        self.embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
-        self.qa_pipeline = pipeline('question-answering', model='distilbert-base-cased-distilled-squad')
-        self.summarizer = pipeline('summarization', model='facebook/bart-large-cnn')
-
-        # Define LangChain elements
-        self.embedding_chain = LLMChain(
-            llm=ChatGroq(model_name="llama-3.1-70b-versatile"),  # Example: replace with Groq LLM chain if needed
-            prompt=PromptTemplate(template="Generate an embedding for the following text: {text}", input_variables=["text"])
-        )
-
-        self.qa_chain = LLMChain(
-            llm=ChatGroq(model_name="llama-3.1-70b-versatile"),
-            prompt=PromptTemplate(template="Based on the context provided, answer the question: {question}. Context: {context}", input_variables=["question", "context"])
-        )
-
-        self.summarization_chain = LLMChain(
-            llm=ChatGroq(model_name="llama-3.1-70b-versatile"),
-            prompt=PromptTemplate(template="Summarize the following text: {text}", input_variables=["text"])
-        )
-
-        # Combine chains into a sequential chain
-        self.sequential_chain = SequentialChain(chains=[self.embedding_chain, self.qa_chain, self.summarization_chain], input_variables=['text', 'question', 'context'])
-
-    def generate_embeddings(self, content_list):
-        # Generate embeddings for a list of content items
-        embeddings = [self.embedding_model.encode(content) for content in content_list]
-        return embeddings
-
-    def assess_knowledge(self, question, context):
-        # Use the QA pipeline to assess knowledge
-        response = self.qa_pipeline(question=question, context=context)
-        return response['answer'], response['score']
-
-    def summarize_content(self, content):
-        # Summarize content using the summarizer chain
-        summary = self.summarizer(content, max_length=60, min_length=30, do_sample=False)[0]['summary_text']
-        return summary
-
-    def recommend_learning_path(self, user_input, content_data):
-        # Generate embeddings
-        content_embeddings = self.generate_embeddings([c['description'] for c in content_data])
-        user_embedding = self.generate_embeddings([user_input])[0]
-        
-        # Simple similarity scoring (cosine similarity) to match user input with content
-        import numpy as np
-        similarities = np.dot(content_embeddings, user_embedding) / (np.linalg.norm(content_embeddings, axis=1) * np.linalg.norm(user_embedding))
-        
-        # Recommend top 3 most similar content items
-        top_indices = np.argsort(similarities)[-3:][::-1]
-        recommendations = [content_data[i] for i in top_indices]
-        return recommendations
+# learning_path_model.py
+from sentence_transformers import SentenceTransformer
+from transformers import pipeline
+from langchain.chains import PromptTemplate, LLMChain, SequentialChain
+from langchain_groq import ChatGroq
+from langchain.embeddings import HuggingFaceEmbeddings
+from dotenv import load_dotenv
+import os
+
+load_dotenv()
+api_key = os.getenv('GROQ_API_KEY')
+# print(api_key)
+
+class LearningPathModel:
+    def __init__(self):
+        # Initialize embedding and NLP models
+        self.embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
+        self.qa_pipeline = pipeline('question-answering', model='distilbert-base-cased-distilled-squad')
+        self.summarizer = pipeline('summarization', model='facebook/bart-large-cnn')
+
+        # Define LangChain elements
+        self.embedding_chain = LLMChain(
+            llm=ChatGroq(model_name="llama-3.1-70b-versatile"),  # Example: replace with Groq LLM chain if needed
+            prompt=PromptTemplate(template="Generate an embedding for the following text: {text}", input_variables=["text"])
+        )
+
+        self.qa_chain = LLMChain(
+            llm=ChatGroq(model_name="llama-3.1-70b-versatile"),
+            prompt=PromptTemplate(template="Based on the context provided, answer the question: {question}. Context: {context}", input_variables=["question", "context"])
+        )
+
+        self.summarization_chain = LLMChain(
+            llm=ChatGroq(model_name="llama-3.1-70b-versatile"),
+            prompt=PromptTemplate(template="Summarize the following text: {text}", input_variables=["text"])
+        )
+
+        # Combine chains into a sequential chain
+        self.sequential_chain = SequentialChain(chains=[self.embedding_chain, self.qa_chain, self.summarization_chain], input_variables=['text', 'question', 'context'])
+
+    def generate_embeddings(self, content_list):
+        # Generate embeddings for a list of content items
+        embeddings = [self.embedding_model.encode(content) for content in content_list]
+        return embeddings
+
+    def assess_knowledge(self, question, context):
+        # Use the QA pipeline to assess knowledge
+        response = self.qa_pipeline(question=question, context=context)
+        return response['answer'], response['score']
+
+    def summarize_content(self, content):
+        # Summarize content using the summarizer chain
+        summary = self.summarizer(content, max_length=60, min_length=30, do_sample=False)[0]['summary_text']
+        return summary
+
+    def recommend_learning_path(self, user_input, content_data):
+        # Generate embeddings
+        content_embeddings = self.generate_embeddings([c['description'] for c in content_data])
+        user_embedding = self.generate_embeddings([user_input])[0]
+        
+        # Simple similarity scoring (cosine similarity) to match user input with content
+        import numpy as np
+        similarities = np.dot(content_embeddings, user_embedding) / (np.linalg.norm(content_embeddings, axis=1) * np.linalg.norm(user_embedding))
+        
+        # Recommend top 3 most similar content items
+        top_indices = np.argsort(similarities)[-3:][::-1]
+        recommendations = [content_data[i] for i in top_indices]
+        return recommendations