Upload 9 files

"initial"

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1 @@
+main.py

Dockerfile

@@ -0,0 +1,20 @@
+# Use the official Python image
+FROM python:3.12-slim
+
+# Set environment variables
+ENV PYTHONUNBUFFERED=1
+WORKDIR /app
+
+# Copy and install dependencies
+COPY requirements.txt ./
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Copy application code
+COPY . /app
+
+# Expose necessary ports
+EXPOSE 7860 8501
+
+# Start both FastAPI and Streamlit services
+CMD ["sh", "-c", "uvicorn api:app --host 0.0.0.0 --port 8000 & streamlit run main.py --server.port 8501 --server.address 0.0.0.0"]
+#

README.md

@@ -1,10 +1,10 @@
----
-title: Company Sentiment
-emoji: 🚀
-colorFrom: pink
-colorTo: gray
-sdk: docker
-pinned: false
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+---
+title: Company Sentiment
+emoji: 🚀
+colorFrom: pink
+colorTo: gray
+sdk: docker
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

api.py

@@ -0,0 +1,52 @@
+from fastapi import FastAPI
+from utils import (
+    fetch_from_web,
+    analyze_sentiment,
+    generate_comparative_sentiment,
+    generate_final_report,
+    get_summaries_by_sentiment,
+    translate,
+    text_to_speech,
+)
+
+app = FastAPI()
+
+
+@app.get("/home")
+def main(company_name: str, model_provider: str):
+    web_results = fetch_from_web(company_name)
+
+    if "sources" not in web_results:
+        return {"error": "No sources found."}
+
+    sentiment_output = [
+        analyze_sentiment(article, model_provider)
+        for article in web_results["sources"][:5]
+    ]
+
+    comparative_sentiment = generate_comparative_sentiment(sentiment_output)
+
+    positive_summary, negative_summary, neutral_summary = get_summaries_by_sentiment(
+        sentiment_output
+    )
+
+    final_report = generate_final_report(
+        positive_summary,
+        negative_summary,
+        neutral_summary,
+        comparative_sentiment,
+        model_provider,
+    )
+
+    hindi_translation = translate(final_report, model_provider)
+    audio_path = text_to_speech(hindi_translation)
+
+    return {
+        "company_name": company_name,
+        "articles": sentiment_output,
+        "comparative_sentiment": comparative_sentiment,
+        "final_report": final_report,
+        "hindi_translation": hindi_translation,
+        "audio_url": audio_path,
+    }
+#

app.py

@@ -0,0 +1,34 @@
+import streamlit as st
+import requests
+
+st.title("Company Sentiment Analyzer")
+
+company_name = st.text_input("Enter Company Name", "Tesla")
+model_provider = st.selectbox("Model Provider", options=["Ollama", "Groq"])
+
+if st.button("Fetch Sentiment Data"):
+    api_url = (
+        f"http://localhost:8000/home?"
+        f"company_name={company_name}&model_provider={model_provider}"
+    )
+
+    try:
+        response = requests.get(api_url)
+        response.raise_for_status()
+
+        data = response.json()
+
+        st.subheader("Company Name")
+        st.write(data.get("company_name"))
+
+        st.subheader("Final Report")
+        st.write(data.get("final_report"))
+
+        st.subheader("🔊 Audio Output")
+        audio_file = "output.mp3"
+        if audio_file:
+            st.audio(audio_file)
+
+    except requests.exceptions.RequestException as e:
+        st.error(f"Error fetching data: {e}")
+#

docker-compose.yml

@@ -0,0 +1,8 @@
+version: '3'
+services:
+  web:
+    build: .
+    ports:
+      - "7860:7860"
+      - "8501:8501"
+    

requirements.txt

@@ -0,0 +1,98 @@
+aiohappyeyeballs==2.6.1
+aiohttp==3.11.14
+aiosignal==1.3.2
+altair==5.5.0
+annotated-types==0.7.0
+anyio==4.9.0
+asttokens==3.0.0
+attrs==25.3.0
+blinker==1.9.0
+cachetools==5.5.2
+certifi==2025.1.31
+charset-normalizer==3.4.1
+click==8.1.8
+colorama==0.4.6
+comm==0.2.2
+debugpy==1.8.13
+decorator==5.2.1
+distro==1.9.0
+docstring-parser==0.16
+dotenv==0.9.9
+executing==2.2.0
+fastapi==0.115.11
+frozenlist==1.5.0
+gitdb==4.0.12
+gitpython==3.1.44
+groq==0.20.0
+h11==0.14.0
+httpcore==1.0.7
+httpx==0.28.1
+idna==3.10
+instructor==1.7.7
+ipykernel==6.29.5
+ipython==9.0.2
+ipython-pygments-lexers==1.1.1
+jedi==0.19.2
+jinja2==3.1.6
+jiter==0.8.2
+jsonschema==4.23.0
+jsonschema-specifications==2024.10.1
+jupyter-client==8.6.3
+jupyter-core==5.7.2
+markdown-it-py==3.0.0
+markupsafe==3.0.2
+matplotlib-inline==0.1.7
+mdurl==0.1.2
+multidict==6.2.0
+narwhals==1.31.0
+nest-asyncio==1.6.0
+numpy==2.2.4
+ollama==0.4.7
+openai==1.66.5
+packaging==24.2
+pandas==2.2.3
+parso==0.8.4
+pillow==11.1.0
+platformdirs==4.3.6
+prompt-toolkit==3.0.50
+propcache==0.3.0
+protobuf==5.29.3
+psutil==7.0.0
+pure-eval==0.2.3
+pyarrow==19.0.1
+pydantic==2.10.6
+pydantic-core==2.27.2
+pydeck==0.9.1
+pygments==2.19.1
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+pytz==2025.1
+pywin32==310
+pyzmq==26.3.0
+referencing==0.36.2
+regex==2024.11.6
+requests==2.32.3
+rich==13.9.4
+rpds-py==0.23.1
+shellingham==1.5.4
+six==1.17.0
+smmap==5.0.2
+sniffio==1.3.1
+stack-data==0.6.3
+starlette==0.46.1
+streamlit==1.43.2
+tavily-python==0.5.1
+tenacity==9.0.0
+tiktoken==0.9.0
+toml==0.10.2
+tornado==6.4.2
+tqdm==4.67.1
+traitlets==5.14.3
+typer==0.15.2
+typing-extensions==4.12.2
+tzdata==2025.1
+urllib3==2.3.0
+uvicorn==0.34.0
+watchdog==6.0.0
+wcwidth==0.2.13
+yarl==1.18.3

utils.py

@@ -0,0 +1,396 @@
+import os
+from typing import Literal, List
+from tavily import TavilyClient
+from pydantic import BaseModel
+from ollama import chat
+from dotenv import load_dotenv
+from groq import Groq
+import instructor
+import requests
+
+GROQ_API_KEY = "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"
+ELEVEN_LABS_API_KEY = "sk_a927222500aab9665f83f078b92e833e7ec1389ee68238c0"
+TAVILY_API_KEY = "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"
+
+load_dotenv()
+
+
+def fetch_from_web(query):
+    tavily_client = TavilyClient(api_key=TAVILY_API_KEY)
+    response = tavily_client.search(
+        query,
+        include_raw_content=True,
+        max_results=10,
+        topic="news",
+        search_depth="basic"
+    )
+    return {"sources": response['results']}
+
+
+class Sentiment(BaseModel):
+    summary: str
+    reasoning: str
+    topics: List[str]
+    sentiment: Literal['positive', 'negative', 'neutral']
+
+
+def analyze_sentiment(article, model_provider):
+    sentiment_prompt = f"""
+                Analyze the following news article about a company:
+
+                1. **Summary**: Provide a comprehensive summary of the article's key points.
+                
+                2. **Sentiment Analysis**: 
+                - Classify the overall sentiment toward the company as: POSITIVE, NEGATIVE, or NEUTRAL
+                - Support your classification with specific quotes, tone analysis, and factual evidence from the article
+                - Explain your reasoning for this sentiment classification in 2 to 3 lines.
+                
+                3. **Key Topics**: 
+                - Identify 3-5 main topics discussed in the article
+                - Only give the name of the topics
+
+                Be as detailed and objective as possible in your reasoning.
+
+                Article Title: {article['title']}
+
+                Article: {article['raw_content']}
+                """
+
+    try:
+        if model_provider == "Ollama":
+            response = chat(
+                messages=[
+                    {
+                        'role': 'user',
+                        'content': sentiment_prompt
+                    }
+                ],
+                model='llama3.2:3b',
+                format=Sentiment.model_json_schema(),
+            )
+
+            sentiment_output = Sentiment.model_validate_json(response.message.content)
+            
+            final_dict = {
+                "title": article["title"],
+                "summary": sentiment_output.summary,
+                "reasoning": sentiment_output.reasoning,
+                "topics": sentiment_output.topics,
+                "sentiment": sentiment_output.sentiment
+            }
+        else:
+            llm = Groq(api_key=GROQ_API_KEY)
+            llm = instructor.from_groq(llm, mode=instructor.Mode.TOOLS)
+
+            resp = llm.chat.completions.create(
+                model="llama-3.3-70b-versatile",
+                messages=[
+                    {
+                        "role": "user",
+                        "content": sentiment_prompt,
+                    }
+                ],
+                response_model=Sentiment,
+            )
+        
+            sentiment_output = resp.model_dump()
+            
+            final_dict = {
+                "title": article["title"],
+                "summary": sentiment_output.get("summary"),
+                "reasoning": sentiment_output.get("reasoning"),
+                "topics": sentiment_output.get("topics"),
+                "sentiment": sentiment_output.get("sentiment")
+            }
+
+        return final_dict
+
+    except Exception as e:
+        print(f"Error parsing sentiment output: {e}")
+        return None
+    
+
+def generate_comparative_sentiment(articles):
+    sentiment_counts = {"Positive": 0, "Negative": 0, "Neutral": 0}
+    
+    for article in articles:
+        sentiment = article.get("sentiment", "").lower()
+        if sentiment == "positive":
+            sentiment_counts["Positive"] += 1
+        elif sentiment == "negative":
+            sentiment_counts["Negative"] += 1
+        elif sentiment == "neutral":
+            sentiment_counts["Neutral"] += 1
+    
+    all_topics = []
+    for article in articles:
+        all_topics.extend(article.get("topics", []))
+    
+    unique_topics = set(all_topics)
+    
+    topic_counts = {}
+    
+    for topic in unique_topics:
+        count = all_topics.count(topic)
+        topic_counts[topic] = count
+
+    common_topics = [topic for topic, count in topic_counts.items() if count > 1]
+    unique_topics = {}
+    
+    for i, article in enumerate(articles):
+        article_topics = set(article.get("topics", []))
+        for j, other_article in enumerate(articles):
+            if i != j:
+                other_topics = set(other_article.get("topics", []))
+                unique_topics[f"Unique Topics in Article {i+1}"] = list(article_topics - other_topics)
+    
+    comparative_sentiment = {
+        "Sentiment Distribution": sentiment_counts,
+        "Coverage Differences": "coverage_differences",
+        "Topic Overlap": {
+            "Common Topics": common_topics,
+            "Unique Topics in Article 1": unique_topics.get("Unique Topics in Article 1", []),
+            "Unique Topics in Article 2": unique_topics.get("Unique Topics in Article 2", []),
+            "Unique Topics in Article 3": unique_topics.get("Unique Topics in Article 3", []),
+            "Unique Topics in Article 4": unique_topics.get("Unique Topics in Article 4", []),
+            "Unique Topics in Article 5": unique_topics.get("Unique Topics in Article 5", []),
+            "Unique Topics in Article 6": unique_topics.get("Unique Topics in Article 6", []),
+            "Unique Topics in Article 7": unique_topics.get("Unique Topics in Article 7", []),
+            "Unique Topics in Article 8": unique_topics.get("Unique Topics in Article 8", []),
+            "Unique Topics in Article 9": unique_topics.get("Unique Topics in Article 9", []),
+            "Unique Topics in Article 10": unique_topics.get("Unique Topics in Article 10", [])
+        },
+    }
+    
+    return comparative_sentiment
+
+
+def get_summaries_by_sentiment(articles):
+    pos_sum = []
+    neg_sum = []
+    neutral_sum = []
+    
+    for article in articles:
+        sentiment = article.get("sentiment", "").lower()
+        title = article.get("title", "No Title")
+        summary = article.get("summary", "No Summary")
+        
+        article_text = f'Title: {title}\nSummary: {summary}'
+        
+        if sentiment == "positive":
+            pos_sum.append(article_text)
+        elif sentiment == "negative":
+            neg_sum.append(article_text)
+        elif sentiment == "neutral":
+            neutral_sum.append(article_text)
+
+    pos_sum = "\n\n".join(pos_sum) if pos_sum else "No positive articles available."
+    neg_sum = "\n\n".join(neg_sum) if neg_sum else "No negative articles available."
+    neutral_sum = "\n\n".join(neutral_sum) if neutral_sum else "No neutral articles available."
+
+    return pos_sum, neg_sum, neutral_sum
+
+
+def comparative_analysis(pos_sum, neg_sum, neutral_sum, model_provider):
+    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:
+
+1. **Sentiment Breakdown**: Identify how each category (positive, negative, and neutral) portrays the company. Highlight the language, tone, and emotional cues that shape the sentiment.
+
+2. **Key Themes and Topics**: Compare the primary themes and narratives within each sentiment group. What aspects of the company's operations, performance, or reputation does each category focus on?
+
+3. **Perceived Company Image**: Analyze how each sentiment type influences public perception of the company. What impression is created by positive vs. negative vs. neutral coverage?
+
+4. **Bias and Framing**: Evaluate whether any of the articles reflect explicit biases or specific agendas regarding the company. Are there patterns in how the company is framed across different sentiments?
+
+5. **Market or Stakeholder Impact**: Discuss potential effects on stakeholders (e.g., investors, customers, regulators) based on the sentiment of each article type.
+
+6. **Comparative Insights**: Provide a concise summary of the major differences and commonalities between the three sentiment groups. What overall narrative emerges about the company?
+
+### Positive Articles:
+{pos_sum}
+
+### Negative Articles:
+{neg_sum}
+
+### Neutral Articles:
+{neutral_sum}
+"""
+
+    if model_provider == "Ollama":
+        response = chat(
+            messages=[
+                {
+                    'role': 'user',
+                    'content': prompt
+                }
+            ],
+            model='llama3.2:3b'
+        )
+        response = response.message.content
+    
+    else:
+        llm = Groq(api_key=GROQ_API_KEY)
+        
+        chat_completion = llm.chat.completions.create(
+            messages=[
+                {
+                    "role": "user",
+                    "content": prompt[:5000],
+                }
+            ],
+            model="llama-3.3-70b-versatile",
+        )
+        response = chat_completion.choices[0].message.content
+    
+    return response
+
+
+def generate_final_report(pos_sum, neg_sum, neutral_sum, comparative_sentiment, model_provider):
+    final_report_prompt = f"""
+    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.
+- Highlight the dominant narrative shaping the company's perception.
+- Summarize key drivers behind positive and negative sentiments.
+
+### 2. Media Coverage Analysis
+- Identify major news sources covering the company.
+- Highlight patterns in coverage across platforms (e.g., frequency, timing).
+- Identify whether media sentiment shifts over time.
+
+### 3. Sentiment Breakdown
+- **Positive Sentiment:**
+    * Titles and sources: {pos_sum}
+    * Key themes, notable quotes, and focal areas (e.g., product, leadership).
+- **Negative Sentiment:**
+    * Titles and sources: {neg_sum}
+    * Key themes, notable quotes, and areas of concern.
+- **Neutral Sentiment:**
+    * Titles and sources: {neutral_sum}
+    * Key themes and neutral narratives.
+
+### 4. Narrative Analysis
+- Identify primary storylines about the company.
+- Analyze how the company is positioned (positive, neutral, negative).
+- Detect shifts or emerging narratives over time.
+
+### 5. Key Drivers of Sentiment
+- Identify specific events, announcements, or actions driving media sentiment.
+- Evaluate sentiment linked to industry trends vs. company-specific factors.
+- Highlight company strengths and weaknesses based on media portrayal.
+
+### 6. Competitive Context
+- Identify competitor comparisons.
+- Analyze how media sentiment about the company compares to industry standards.
+- Highlight competitive advantages or concerns raised by the media.
+
+### 7. Stakeholder Perspective
+- Identify how key stakeholders (e.g., investors, customers, regulators) are represented.
+- Analyze stakeholder concerns and reputation risks/opportunities.
+
+### 8. Recommendations
+- Suggest strategies to mitigate negative sentiment.
+- Recommend approaches to amplify positive narratives.
+- Provide messaging suggestions for future announcements.
+
+### 9. Appendix
+- Full article details (title, publication, date, author, URL).
+- Sentiment scoring methodology.
+- Media monitoring metrics (reach, engagement, etc.).
+"""
+
+    if model_provider == "Ollama":
+        final_report = chat(
+            messages=[
+                {
+                    'role': 'user',
+                    'content': final_report_prompt
+                }
+            ],
+            model='llama3.2:3b'
+        )
+        response = final_report.message.content
+    
+    else:
+        llm = Groq(api_key=GROQ_API_KEY)
+        
+        chat_completion = llm.chat.completions.create(
+            messages=[
+                {
+                    "role": "user",
+                    "content": final_report_prompt[:5000],
+                }
+            ],
+            model="llama-3.3-70b-versatile",
+        )
+        response = chat_completion.choices[0].message.content
+    
+    return response
+    
+
+def translate(report, model_provider):
+    translation_prompt = f"""
+    Translate the following corporate sentiment analysis report into Hindi:
+
+    {report}
+
+    Ensure the translation maintains professional tone and structure while accurately conveying key insights and details.
+    """
+    if model_provider == "Ollama":
+        translation = chat(
+            messages=[
+                {
+                    'role': 'user',
+                    'content': translation_prompt
+                }
+            ],
+            model='llama3.2:3b'
+        )
+        response = translation.message.content
+    
+    else:
+        translation_llm = Groq(api_key=GROQ_API_KEY)
+        
+        chat_completion = translation_llm.chat.completions.create(
+            messages=[
+                {
+                    "role": "user",
+                    "content": translation_prompt[:5000],
+                }
+            ],
+            model="llama-3.3-70b-versatile",
+        )
+        response = chat_completion.choices[0].message.content
+        
+    return response 
+
+
+def text_to_speech(text):
+    url = "https://api.elevenlabs.io/v1/text-to-speech/JBFqnCBsd6RMkjVDRZzb?output_format=mp3_44100_128"
+
+    model_id = "eleven_multilingual_v2"
+    output_file = "output.mp3"
+    api_key = "sk_a927222500aab9665f83f078b92e833e7ec1389ee68238c0"
+    
+    headers = {
+        "xi-api-key": api_key,
+        "Content-Type": "application/json"
+    }
+
+    payload = {
+        "text": text,
+        "model_id": model_id
+    }
+
+    response = requests.post(url, headers=headers, json=payload)
+
+    if response.status_code == 200:
+        with open(output_file, "wb") as f:
+            f.write(response.content)
+        print(f"Audio saved to {output_file}")
+    else:
+        print(f"Error: {response.status_code} - {response.text}")
+        
+#