Update app.py

app.py

@@ -7,9 +7,12 @@ import re
 import json
 from auditqa.sample_questions import QUESTIONS
 from auditqa.reports import POSSIBLE_REPORTS, files
-from auditqa.engine.prompts import audience_prompts, answer_prompt_template, llama_propmt
 from auditqa.doc_process import process_pdf
-from langchain_core.prompts import ChatPromptTemplate
+from langchain_core.messages import (
+    HumanMessage,
+    SystemMessage,
+)
+from langchain_huggingface import ChatHuggingFace
 from langchain_core.output_parsers import StrOutputParser
 from langchain.llms import HuggingFaceEndpoint
 from dotenv import load_dotenv
@@ -70,29 +73,32 @@ async def chat(query,history,sources,reports):
     
     
 # get prompt
+    SYSTEM_PROMPT = """
+        You are AuditQ&A, an AI Assistant created by Auditors and Data Scientist. You are given a question and extracted passages of the consolidated/departmental/thematic focus audit reports. Provide a clear and structured answer based on the passages provided, the context and the guidelines.
+        Guidelines:
+        - If the passages have useful facts or numbers, use them in your answer.
+        - When you use information from a passage, mention where it came from by using [Doc i] at the end of the sentence. i stands for the number of the document.
+        - Do not use the sentence 'Doc i says ...' to say where information came from.
+        - If the same thing is said in more than one document, you can mention all of them like this: [Doc i, Doc j, Doc k]
+        - Do not just summarize each passage one by one. Group your summaries to highlight the key parts in the explanation.
+        - If it makes sense, use bullet points and lists to make your answers easier to understand.
+        - You do not need to use every passage. Only use the ones that help answer the question.
+        - If the documents do not have the information needed to answer the question, just say you do not have enough information.
+        """
+    
+    USER_PROMPT = """Passages:
+        {context}
+        -----------------------
+        Question: {question}  - Explained to audit expert
+        Answer in english with the passages citations:
+        """.format(context = context_retrieved_lst, question=query)
+    
+    messages = [
+    SystemMessage(content=SYSTEM_PROMPT),
+    HumanMessage(
+        content=USER_PROMPT
+    ),]
     
-    #prompt = ChatPromptTemplate.from_template(answer_prompt_template)
-    prompt = ChatPromptTemplate.from_messages([
-        (
-            "system",
-            """You are AuditQ&A, an AI Assistant created by Auditors and Data Scientist. You are given a question and extracted passages of the consolidated/departmental/thematic focus audit reports. Provide a clear and structured answer based on the passages provided, the context and the guidelines.
-Guidelines:
-- If the passages have useful facts or numbers, use them in your answer.
-- When you use information from a passage, mention where it came from by using [Doc i] at the end of the sentence. i stands for the number of the document.
-- Do not use the sentence 'Doc i says ...' to say where information came from.
-- If the same thing is said in more than one document, you can mention all of them like this: [Doc i, Doc j, Doc k]
-- Do not just summarize each passage one by one. Group your summaries to highlight the key parts in the explanation.
-- If it makes sense, use bullet points and lists to make your answers easier to understand.
-- You do not need to use every passage. Only use the ones that help answer the question.
-- If the documents do not have the information needed to answer the question, just say you do not have enough information.""",
-        ),
-        ("user", 
-        """Passages:
-{context}
------------------------
-Question: {question} - Explained to {audience}
-Answer in {language} with the passages citations:"""),
-    ])
 
 # get llm_qa
  #   llm_qa = HuggingFaceEndpoint(
@@ -113,12 +119,13 @@ Answer in {language} with the passages citations:"""),
 
     
 # create rag chain
-    chain = prompt | llm_qa | StrOutputParser()
+    chat_model = ChatHuggingFace(llm=llm_qa)
+    chain = chat_model| StrOutputParser()
 # get answers
     answer_lst = []
     for question, context in zip(question_lst , context_retrieved_lst):
-        answer = chain.invoke({"context": context, "question": question,'audience':audience_prompt, 'language':'english'})
-        answer_lst.append(answer)
+        answer = chain.invoke(messages)
+        answer_lst.append(answer.content)
     docs_html = []
     for i, d in enumerate(context_retrieved, 1):
         docs_html.append(make_html_source(d, i))