Update app.py

app.py

@@ -20,65 +20,82 @@ from langchain.llms import OpenAI
 from langchain.chains import RetrievalQA
 from langchain.document_loaders import TextLoader
 from langchain.prompts import PromptTemplate
+from langchain.callbacks.stdout import StdOutCallbackHandler
+from langchain.chat_models.openai import ChatOpenAI
+from langchain.prompts.prompt import PromptTemplate
+
+from langchain.llms import OpenAI
+from langchain.prompts import PromptTemplate
+from langchain.chains import LLMChain
+
 
 OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
 
 
-def predict(file_obj):
-    loader = UnstructuredPDFLoader(file_obj.orig_name)
-    data = loader.load()
-    text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
-    texts = text_splitter.split_documents(data)    
+def predict(text):
+    # loader = UnstructuredPDFLoader(file_obj.orig_name)
+    # data = loader.load()
+    # text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
+    # texts = text_splitter.split_documents(data)    
   
-    embeddings = OpenAIEmbeddings()
-    docsearch = Chroma.from_documents(texts, embeddings)
-    qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="map_reduce", retriever=docsearch.as_retriever())
+    # embeddings = OpenAIEmbeddings()
+    # docsearch = Chroma.from_documents(texts, embeddings)
+    # qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="map_reduce", retriever=docsearch.as_retriever())
     
-    prompt_template = """Ignore all previous instructions. You are the world's best interviewer now. I am going to give you a resume of a candidate. Analyze the resume in 4 categories: Education, Work Experience, Projects and Internships, Others including interests, skills etc. Be simple, direct and commanding. Start with greeting the candidate with a 2 line relatable introduction emphasizing your superiority. Ask the candidate if they have a particular company and a role that they want to apply for. 
-If the candidate mentions either the company or the role, then ensure all questions that would be asked will are related to it.
-If they don't mention either the company or role clearly, then ignore this and move to the next step. 
-Then, give a one line response acknowledging the candidate or if they are not clear about the company or the role then acknowledge positively that you would ask practice interview questions. Then ask the candidate topic would they like to start with. There are 4 categories of questions: educational background related, role related or technical questions, behavioral questions and HR or culture related questions. Here, the candidate will have to put an input. 
-Now you will have to ask interview questions. Ensure the questions are good have test the candidate's knowledge. You can choose between longer case based questions, hypothetical questions or academic questions etc. as you deem fit. 
-If the candidate types educational background related, ask it 3-4 most relevant questions related to their education based on their resume which are relevant for the role or the company. 
-If the candidate types role related or technical related then ask accordingly. Here you can even ask a coding question or test their technical understanding etc. 
-Similarly, do it for behavioral questions and HR or culture related questions. You can also be creative, funny, or show emotions at time.
+    prompt_template = """Ignore all previous instructions. You are the world's hearing aid company markerting agent.
+    I am going to give you a text of a customer. Analyze it and you have 4 products in list which you have to suggest to the customer: 
+    ampli-mini it is mainly works for Maximum comfort and discretion, ampli-connect it is mainly works for Connected to the things you love, 
+    ampli-energy it is mainly works for Full of energy, like you, ampli-easy it is mainly works for Allow yourself to hear well.
+    You can also be creative, funny, or show emotions at time.
+    also share the book a appointment link of your company https://www.amplifon.com/uk/book-an-appointment
 {context}
 Question: {question}
-Answer in possible questions for interview:"""
+Product details:"""
     PROMPT = PromptTemplate(
         template=prompt_template, input_variables=["context", "question"]
     )
     chain_type_kwargs = {"prompt": PROMPT}
-    qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=docsearch.as_retriever(), chain_type_kwargs=chain_type_kwargs)
-    response = []
-    category = ["Technical", "Education Background", "Behaviour", "Project Specific"]
-    for value in category:
-
-        response.append({value:ai(qa, value)})
-
-    html_output = ""
-    for obj in response:
-    # Loop through the key-value pairs in the object
-        for key, value in obj.items():
-            value = re.sub(r'[\d\.]+', '', value)
-            value_list = value.strip().split('\n')
-            value_html = "<ol>"
-            for item in value_list:
-                value_html += "<li>{}</li>".format(item.strip())
-            value_html += "</ol>"
-            html_output += "<h2>{}</h2>".format(key)
-            html_output += value_html
+    # qa = RetrievalQA.from_chain_type(llm=OpenAI(), chain_type="stuff", retriever=docsearch.as_retriever(), chain_type_kwargs=chain_type_kwargs)
+
+
+    llm = OpenAI()
+    # prompt = PromptTemplate(
+    #     input_variables=["product"],
+    #     template="What is a good name for a company that makes {product}?",
+    # )
+    chain = LLMChain(llm=llm, prompt=PROMPT)
+    resp = chain.run(context=text)
+    print(resp)
+    
+    # response = []
+    # category = ["ampli-mini", "ampli-connect", "ampli-energy", "ampli-easy"]
+    # for value in category:
+
+        # response.append({value:ai(qa, value)})
+
+    # html_output = ""
+    # for obj in response:
+    # # Loop through the key-value pairs in the object
+    #     for key, value in obj.items():
+    #         value = re.sub(r'[\d\.]+', '', value)
+    #         value_list = value.strip().split('\n')
+    #         value_html = "<ol>"
+    #         for item in value_list:
+    #             value_html += "<li>{}</li>".format(item.strip())
+    #         value_html += "</ol>"
+    #         html_output += "<h2>{}</h2>".format(key)
+    #         html_output += value_html
 
     
-    return html_output
+    return "<p>resp</p>"
     
-def ai(qa,category):
-    query = "please suggest "+ category +" interview questions"
-    data = list(filter(None, qa.run(query).split('\n')))
-    results = list(filter(lambda x: x != ' ', data))
-    results = "\n".join(results)
+# def ai(qa,category):
+#     query = "please suggest "+ category +" interview questions"
+#     data = list(filter(None, qa.run(query).split('\n')))
+#     results = list(filter(lambda x: x != ' ', data))
+#     results = "\n".join(results)
     
-    return results
+#     return results
 
 model = whisper.load_model("base")
 sentiment_analysis = pipeline("sentiment-analysis", framework="pt", model="SamLowe/roberta-base-go_emotions")
@@ -146,6 +163,7 @@ def inference(audio, sentiment_option):
 
     sentiment_results = analyze_sentiment(result.text)
     print(result.text)
+    print(predict(result.text))
     sentiment_output = display_sentiment_results(sentiment_results, sentiment_option)
 
     return lang.upper(), result.text, sentiment_output