update app.py

app.py

@@ -3,8 +3,8 @@ import gradio as gr
 from langchain.chat_models import ChatOpenAI
 from kor import create_extraction_chain, Object, Text 
 from langchain.prompts.prompt import PromptTemplate
-from langchain.chains import LLMChain
-from langchain.llms import OpenAI
+# from langchain.chains import LLMChain
+# from langchain.llms import OpenAI
 
 from dotenv import load_dotenv
 
@@ -21,29 +21,29 @@ def gen_text(pdf_file):
     
 
     
-def generate_questions(resume,role='',experience=''):
-    _PROMPT_TEMPLATE = """
-    this is the resume of user:
-    {resume_details}
+# def generate_questions(resume,role='',experience=''):
+#     _PROMPT_TEMPLATE = """
+#     this is the resume of user:
+#     {resume_details}
 
-    here is the role he want to join in :
-    {role}
+#     here is the role he want to join in :
+#     {role}
 
-    Based on the following experience:
-    {experience}
+#     Based on the following experience:
+#     {experience}
 
-    What are your interview  questions for the given user resume and role he want to join in with that experience?
-    generate no of  questions = {questions}!
-    """
-    PROMPT = PromptTemplate(input_variables=["resume_details", "role", "experience",'questions'], template=_PROMPT_TEMPLATE)
+#     What are your interview  questions for the given user resume and role he want to join in with that experience?
+#     generate no of  questions = {questions}!
+#     """
+#     PROMPT = PromptTemplate(input_variables=["resume_details", "role", "experience",'questions'], template=_PROMPT_TEMPLATE)
   
-    llm1 = OpenAI(model_name="text-davinci-003", temperature=0)
-    chain = LLMChain(llm=llm1, prompt=PROMPT)
-    prompt = chain.predict_and_parse(resume_details= gen_text(resume),
-    role= role,
-    experience= experience,
-      questions=10)
-    return prompt.split('\n')
+#     llm1 = OpenAI(model_name="text-davinci-003", temperature=0)
+#     chain = LLMChain(llm=llm1, prompt=PROMPT)
+#     prompt = chain.predict_and_parse(resume_details= gen_text(resume),
+#     role= role,
+#     experience= experience,
+#       questions=10)
+#     return prompt.split('\n')
 def context_extracter(text):
       
       llm = ChatOpenAI(
@@ -115,10 +115,11 @@ def context_extracter(text):
       # chain = LLMChain(llm=llm1, prompt=PROMPT)
       chain = create_extraction_chain(llm, schema, encoder_or_encoder_class='json')
       return chain.predict_and_parse(text=text)['data']
+
 k=gr.Interface(
-    fn=generate_questions,
-    inputs=['file','text','text'],
-    outputs=['text']
+    fn=gen_text,
+    inputs=['file'],
+    outputs=['json']
 )
 k.launch()