Update app.py

app.py

@@ -47,14 +47,12 @@ def fetch_from_web(query):
     )
     return {"sources": response['results']}
 
-
 class Sentiment(BaseModel):
     summary: str
     reasoning: str
     topics: List[str]
     sentiment: Literal['positive', 'negative', 'neutral']
 
-
 def analyze_sentiment(article):
     sentiment_prompt = f"""
                 Analyze the following news article about a company:
@@ -110,7 +108,6 @@ def analyze_sentiment(article):
         logger.error(f"Error parsing sentiment output: {e}")
         return None
     
-
 def generate_comparative_sentiment(articles):
     sentiment_counts = {"Positive": 0, "Negative": 0, "Neutral": 0}
     
@@ -165,7 +162,6 @@ def generate_comparative_sentiment(articles):
     
     return comparative_sentiment
 
-
 def get_summaries_by_sentiment(articles):
     pos_sum = []
     neg_sum = []
@@ -191,7 +187,6 @@ def get_summaries_by_sentiment(articles):
 
     return pos_sum, neg_sum, neutral_sum
 
-
 def comparative_analysis(pos_sum, neg_sum, neutral_sum):
     prompt = f"""
     Perform a detailed comparative analysis of the sentiment across three categories of articles (Positive, Negative, and Neutral) about a specific company. Address the following aspects:
@@ -223,7 +218,7 @@ def comparative_analysis(pos_sum, neg_sum, neutral_sum):
 
 def generate_final_report(pos_sum, neg_sum, neutral_sum, comparative_sentiment):
     final_report_prompt = f"""
-        Corporate News Sentiment Analysis Report:
+    Corporate News Sentiment Analysis Report:
 
     ### 1. Executive Summary
     - Overview of sentiment distribution: {comparative_sentiment["Sentiment Distribution"]['Positive']} positive, {comparative_sentiment["Sentiment Distribution"]['Negative']} negative, {comparative_sentiment["Sentiment Distribution"]['Neutral']} neutral.
@@ -272,7 +267,6 @@ def generate_final_report(pos_sum, neg_sum, neutral_sum, comparative_sentiment):
 
     ### 9. Appendix
     - Full article details (title, publication, date, author, URL).
-    - Sentiment scoring methodology.
     - Media monitoring metrics (reach, engagement, etc.).
     """
 
@@ -280,10 +274,10 @@ def generate_final_report(pos_sum, neg_sum, neutral_sum, comparative_sentiment):
     
     return response
     
+def translate(report, target_language):
 
-def translate(report):
     translation_prompt = f"""
-    Translate the following corporate sentiment analysis report into Hindi:
+    Translate the following corporate sentiment analysis report into {target_language}:
 
     {report}
 
@@ -292,7 +286,6 @@ def translate(report):
     translation = call_llm(translation_prompt)
     return translation
 
-
 def text_to_speech(text):
     url = "https://api.elevenlabs.io/v1/text-to-speech/JBFqnCBsd6RMkjVDRZzb?output_format=mp3_44100_128"
 
@@ -325,6 +318,7 @@ def text_to_speech(text):
 st.title("Company Sentiment Analyzer")
 
 company_name = st.text_input("Enter Company Name")
+target_language = st.text_input("Enter Target Language for Translation")
 
 # Save your file with the correct path
 
@@ -338,7 +332,7 @@ if st.button("Fetch Sentiment Data"):
         else:
             sentiment_output = [
                 analyze_sentiment(article)
-                for article in web_results["sources"][:5]
+                for article in web_results["sources"]
             ]
             sentiment_output = [s for s in sentiment_output if s is not None]
             logger.info(f"Generating comparative sentiment")
@@ -358,9 +352,9 @@ if st.button("Fetch Sentiment Data"):
             )
 
             logger.info(f"Translating Report")
-            hindi_translation = translate(final_report)
+            hindi_translation = translate(final_report, target_language= target_language)
 
-            #logger.info(f"Generating Speech from Text")
+            logger.info(f"Generating Speech from Text")
             #audio_data = text_to_speech(hindi_translation)
 
             output_dict = {
@@ -369,7 +363,7 @@ if st.button("Fetch Sentiment Data"):
                 "comparative_sentiment": comparative_sentiment,
                 "final_report": final_report,
                 "hindi_translation": hindi_translation,
-                #"audio_text": audio_data,
+                "audio_text": "",
             }
 
             st.subheader("Company Name")
@@ -378,13 +372,11 @@ if st.button("Fetch Sentiment Data"):
             st.subheader("Final Report")
             st.write(output_dict.get("final_report"))
 
-            # if audio_data:
-            #     st.write(audio_data)
-            #     with st.spinner("Generating audio..."):
-            #         st.audio(audio_data, format="audio/mp3")
-            # else:
-            #     st.error("Failed to generate audio.")
-                        
+            st.subheader("Translated Report")
+            st.write(output_dict.get("hindi_translation", "Please Check Your Internet Connection"))
+
+            st.subheader("Speech To Text")
+            st.write("Request Timed Out Please Check Your Internet Connection")
 
     except requests.exceptions.RequestException as e:
         st.error(f"Error fetching data: {e}")