Update app.py

app.py

@@ -5,8 +5,8 @@ import pdfplumber
 from langchain.chains.mapreduce import MapReduceChain
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.chains.summarize import load_summarize_chain
-from langchain.chat_models import ChatOpenAI
-from langchain.document_loaders import UnstructuredFileLoader
+
+from langchain_community.document_loaders import UnstructuredFileLoader
 from langchain.prompts import PromptTemplate
 import logging
 import json
@@ -21,17 +21,24 @@ import pandas as pd
 import requests
 import gradio as gr
 import re
-from langchain.document_loaders import WebBaseLoader
+from langchain_community.document_loaders import WebBaseLoader
 from langchain.chains.combine_documents.stuff import StuffDocumentsChain
 from transformers import pipeline
 import plotly.express as px
-from langchain.document_loaders.csv_loader import CSVLoader
+from langchain_community.document_loaders import CSVLoader
+from langchain_community.chat_models import ChatOpenAI
 from langchain.chains.llm import LLMChain
 import yfinance as yf
 import pandas as pd
 import nltk
 from nltk.tokenize import sent_tokenize
 from openai import AzureOpenAI
+from langchain.prompts import PromptTemplate
+from langchain.chains import load_summarize_chain
+from langchain.chat_models import AzureChatOpenAI
+
+
+
 
 
 class KeyValueExtractor:
@@ -183,8 +190,8 @@ class KeyValueExtractor:
     def analyze_sentiment_for_graph(self, text):
 
         pipe = pipeline("zero-shot-classification", model=self.model)
-        label=["Positive", "Negative", "Neutral"]
-        result = pipe(text, label)
+        labels=["Positive", "Negative", "Neutral"]
+        result = pipe(text, labels)
         sentiment_scores = {
             result['labels'][0]: result['scores'][0],
             result['labels'][1]: result['scores'][1],
@@ -288,37 +295,52 @@ class KeyValueExtractor:
 
         return bullet_string
 
-    def one_year_summary(self,keyword):
-
+    def one_year_summary(self, keyword):
+      try:
+        # Step 1: Get the finance data and convert to DataFrame
         csv_path = self.get_finance_data(keyword)
+        print(f"CSV path: {csv_path}")  # For debugging, ensure it's correct.
         df = self.csv_to_dataframe(csv_path)
+        if df is None or df.empty:
+            raise ValueError("The DataFrame is empty. Please check the CSV content.")
+
+        # Step 2: Save the DataFrame to a text file
         output_file_path = self.save_dataframe_in_text_file(df)
+        print(f"Output file saved at: {output_file_path}")
+
+        # Step 3: Load and split the document data
         docs = self.csv_loader(output_file_path)
+        if not docs:
+            raise ValueError("No content was loaded from the CSV file.")
+        
         split_docs = self.document_text_spilliter(docs)
+        if not split_docs:
+            raise ValueError("Document splitting failed. No valid chunks were created.")
         
-        prompt_template = """Analyze the Financial Details and Write a abractive quick short summary how the company perform up and down,Bullish/Bearish of the following:
+        # Step 4: Prepare the summarization prompt
+        prompt_template = """Analyze the Financial Details and Write a brief and concise summary of how the company performed:
                 {text}
                 CONCISE SUMMARY:"""
         prompt = PromptTemplate.from_template(prompt_template)
 
-        # Prepare the template for refining the summary with additional context
+        # Step 5: Prepare the refine prompt for summarization chain
         refine_template = (
             "Your job is to produce a final summary\n"
             "We have provided an existing summary up to a certain point: {existing_answer}\n"
-            "We have the opportunity to refine the existing summary"
+            "We have the opportunity to refine the existing summary "
             "(only if needed) with some more context below.\n"
             "------------\n"
             "{text}\n"
             "------------\n"
-            "Given the new context, refine the original summary"
+            "Given the new context, refine the original summary. "
             "If the context isn't useful, return the original summary."
-            "10 line summary is enough"
+            "10 lines of summary are enough."
         )
         refine_prompt = PromptTemplate.from_template(refine_template)
 
-        # Load the summarization chain using the ChatOpenAI language model
+        # Step 6: Load the summarization chain with Azure ChatGPT
         chain = load_summarize_chain(
-            llm = AzureChatOpenAI(azure_deployment = "GPT-3"),
+            llm=AzureChatOpenAI(azure_deployment="GPT-3"),
             chain_type="refine",
             question_prompt=prompt,
             refine_prompt=refine_prompt,
@@ -327,11 +349,19 @@ class KeyValueExtractor:
             output_key="output_text",
         )
 
-        # Generate the refined summary using the loaded summarization chain
+        # Step 7: Generate the summary
         result = chain({"input_documents": split_docs}, return_only_outputs=True)
+        
+        # Step 8: Process and return the summary
         one_year_perfomance_summary = self.change_bullet_points(result["output_text"])
-        # Return the refined summary
+        
+        # Log final summary
+        print(f"Generated Summary: {one_year_perfomance_summary}")
+
         return one_year_perfomance_summary
+      except Exception as e:
+         print(f"Error during one_year_summary processing: {str(e)}")
+         return None
 
     def main(self,keyword):
 
@@ -381,19 +411,24 @@ class KeyValueExtractor:
                   key_value_pair_result = gr.Textbox(label="Discussed Topics", lines = 12)
               with gr.Row(elem_id="col-container"):
                   with gr.Column(scale=1.0, min_width=0):
-                      plot_for_day =gr.Plot(label="Sentiment for Last Day", size=(500, 600))
+                      plot_for_day =gr.Plot(label="Sentiment for Last Day")
+                      
+                      plot_for_day.width = 500
+                      plot_for_day.height = 600
               with gr.Row(elem_id="col-container"):
                 with gr.Column(scale=1.0, min_width=150):
                   analyse_sentiment = gr.Button("Analyse Sentiment For Last Day")
               with gr.Row(elem_id="col-container"):
                 with gr.Column(scale=1.0, min_width=150, ):
-                  one_year_summary = gr.Textbox(label="Summary For One Year Perfomance",lines = 12)
+                  one_year_summary = gr.Textbox(label="Summary For One Year Performance",lines = 12)
               with gr.Row(elem_id="col-container"):
                 with gr.Column(scale=1.0, min_width=150):
                   one_year = gr.Button("Analyse One Year Summary")
               with gr.Row(elem_id="col-container"):
                   with gr.Column(scale=1.0, min_width=0):
-                      plot_for_year =gr.Plot(label="Sentiment for One Year", size=(500, 600))
+                      plot_for_year =gr.Plot(label="Sentiment for One Year")
+                      plot_for_day.width = 500
+                      plot_for_day.height = 600
               with gr.Row(elem_id="col-container"):
                 with gr.Column(scale=1.0, min_width=150):
                   analyse_sentiment_for_year = gr.Button("Analyse Sentiment For One Year")