Update function.py

function.py

@@ -1,60 +1,52 @@
 from langchain.prompts import PromptTemplate
-from langchain.llms import CTransformers
-from langchain.chains import LLMChain
-from langchain.chains import SequentialChain
 from langchain.llms import HuggingFaceHub
+from langchain.chains import LLMChain, SequentialChain
 from dotenv import load_dotenv
+import os
 
+# Load environment variables from .env file
+load_dotenv()
 
-# load_dotenv();
-config = {'max_new_tokens': 512, 'temperature': 0.6}
+# Hugging Face Hub API token
+huggingfacehub_api_token = os.getenv("HUGGINGFACEHUB_API_TOKEN")
 
-# Create function for app
-def GetLLMResponse(selected_topic_level, 
-                    selected_topic,
-                    num_quizzes):
-    
-    # Calling llama model
-    # llm = CTransformers(model="D:\Code Workspace\DL Model\llama-2-7b-chat.ggmlv3.q8_0.bin",
-    #                     model_type = 'llama',
-    #                     config = config)
-
-    # llm = CTransformers(model='TheBloke/Llama-2-7B-Chat-GGML',
-    #                     model_file = 'llama-2-7b-chat.ggmlv3.q8_0.bin',
-    #                     model_type = 'llama',
-    #                     config = config)
+# Configuration for language model
+config = {'max_new_tokens': 512, 'temperature': 0.6}
 
+def GetLLMResponse(selected_topic_level, selected_topic, num_quizzes):
+    # Initialize Hugging Face Hub with API token
     llm = HuggingFaceHub(
-        repo_id = "mistralai/Mixtral-8x7B-Instruct-v0.1",
-        model_kwargs = config
+        repo_id="mistralai/Mixtral-8x7B-Instruct-v0.1",
+        model_kwargs=config,
+        huggingfacehub_api_token=huggingfacehub_api_token
     )
-    
-    ## Create LLM Chaining
-    questions_template = "I want you to just generate question with this specification: Generate a {selected_topic_level} math quiz on the topic of {selected_topic}. Generate only {num_quizzes} questions not more and without providing answers. The Question should not in image format/link"
+
+    # Create LLM Chaining for generating questions
+    questions_template = "Generate a {selected_topic_level} math quiz on the topic of {selected_topic}. Generate only {num_quizzes} questions not more and without providing answers. The Question should not be in image format/link"
     questions_prompt = PromptTemplate(input_variables=["selected_topic_level", "selected_topic", "num_quizzes"],
                                       template=questions_template)
-    questions_chain = LLMChain(llm= llm,
-                               prompt = questions_prompt,
-                               output_key = "questions")
-
-
-    answer_template = "I want you to become a teacher answer this specific Question:\n {questions}\n\n. You should gave me a straightforward and consise explanation and answer to each one of them"
-    answer_prompt = PromptTemplate(input_variables = ["questions"],
-                                   template = answer_template)
-    answer_chain = LLMChain(llm = llm,
-                            prompt = answer_prompt,
-                            output_key = "answer")
-    
-    ## Create Sequential Chaining
-    seq_chain = SequentialChain(chains = [questions_chain, answer_chain],
-                                input_variables = ['selected_topic_level', 'selected_topic', 'num_quizzes'],
-                                output_variables = ['questions', 'answer'])
-    
-    response = seq_chain({'selected_topic_level': selected_topic_level, 
-                            'selected_topic': selected_topic, 
-                            'num_quizzes' : num_quizzes})
-    
-    ## Generate the response from the llama 2 model
+    questions_chain = LLMChain(llm=llm, prompt=questions_prompt, output_key="questions")
+
+    # Create LLM Chaining for generating answers
+    answer_template = "I want you to become a teacher and answer this specific Question:\n{questions}\n\nYou should give me a straightforward and concise explanation and answer to each one of them."
+    answer_prompt = PromptTemplate(input_variables=["questions"], template=answer_template)
+    answer_chain = LLMChain(llm=llm, prompt=answer_prompt, output_key="answer")
+
+    # Create Sequential Chaining
+    seq_chain = SequentialChain(chains=[questions_chain, answer_chain],
+                                input_variables=['selected_topic_level', 'selected_topic', 'num_quizzes'],
+                                output_variables=['questions', 'answer'])
+
+    # Execute the chained prompts
+    response = seq_chain({
+        'selected_topic_level': selected_topic_level,
+        'selected_topic': selected_topic,
+        'num_quizzes': num_quizzes
+    })
+
+    # Print the response for debugging purposes
     print(response)
+
+    # Return the response
     return response
-                        
+