Upload 3 files

README.md

@@ -1,13 +1,86 @@
----
-title: Sales Email Generator
-emoji: 💬
-colorFrom: yellow
-colorTo: purple
-sdk: gradio
-sdk_version: 5.0.1
-app_file: app.py
-pinned: false
-license: mit
----
-
-An example chatbot using [Gradio](https://gradio.app), [`huggingface_hub`](https://huggingface.co/docs/huggingface_hub/v0.22.2/en/index), and the [Hugging Face Inference API](https://huggingface.co/docs/api-inference/index).
+# Smart Sales Email Generator
+
+An AI-powered tool that generates contextual and professional follow-up emails based on previous customer interactions, using RAG, sentiment analysis and quality scoring.
+
+## AI Tools & Technologies
+- RAG (Retrieval Augmented Generation) Implementation:
+  * Vector Store: ChromaDB for email template storage
+  * Embeddings: HuggingFace Sentence Transformers
+  * Similarity Search for context retrieval
+- LangChain for orchestrating the RAG pipeline
+- Hugging Face Transformers for sentiment analysis
+- DeepSeek model for email generation
+- Gradio for the interactive web interface
+- Transformers pipeline for NLP tasks
+
+## Key Features
+- RAG-powered contextual email generation
+- Retrieval of similar past interactions
+- Automated sentiment analysis for tone detection
+- Customizable urgency levels and situation types
+- Real-time email quality scoring
+- Multiple pre-built templates for common scenarios
+- Context-aware response generation
+
+## Technical Skills Demonstrated
+- RAG System Implementation
+- Vector Database Management
+- Embedding Generation
+- Natural Language Processing (NLP)
+- Large Language Model (LLM) integration
+- Prompt engineering
+- API integration (Hugging Face Hub)
+- Web application development
+- Machine Learning model deployment
+- GPU acceleration support
+- Error handling and input validation
+
+## Architecture
+- RAG Components:
+  * Vector Store for template storage
+  * Embedding model for text vectorization
+  * Similarity search for context retrieval
+- Language Models:
+  * DeepSeek for generation
+  * BERT-based model for sentiment analysis
+- Interface:
+  * Gradio for web UI
+  * Real-time processing
+
+## Use Cases
+- Customer Service Follow-ups
+- Complaint Resolution
+- Service Issue Communication
+- Payment Dispute Handling
+- Product Query Responses
+- General Business Communication
+
+## How to Use
+1. Enter the previous customer interaction
+2. Select the situation type from available options
+3. Choose tone (optional - will be automatically detected)
+4. Set urgency level (High/Medium/Low)
+5. Submit to generate a professional follow-up email with quality score
+
+
+## Development Stack
+- Python 3.x
+- LangChain Framework
+- ChromaDB
+- HuggingFace Transformers
+- Gradio UI Framework
+- CUDA support for GPU acceleration
+
+## Future Enhancements
+- Enhanced RAG capabilities
+- Expanded template database
+- Response time optimization
+- Direct email system integration
+- Analytics and tracking capabilities
+- Enhanced scoring system
+
+## License
+MIT License
+
+## Author
+[Tobi Ajibola]

app .py

@@ -0,0 +1,169 @@
+import os
+import torch
+import gradio as gr
+from langchain import HuggingFaceHub
+from langchain.chains import LLMChain
+from langchain.prompts import PromptTemplate
+from transformers import pipeline
+
+# 
+
+# 2. Model Initialization
+# Initialize sentiment analyzer
+sentiment_analyzer = pipeline(
+    "sentiment-analysis",
+    model="finiteautomata/bertweet-base-sentiment-analysis",
+    device=0 if torch.cuda.is_available() else -1
+)
+
+# Initialize LLM
+llm = HuggingFaceHub(
+    repo_id="deepseek-ai/deepseek-coder-33b-instruct",
+    model_kwargs={"temperature": 0.7}
+)
+
+# 3. Templates
+email_template = PromptTemplate(
+    input_variables=["previous_interaction", "situation_type", "tone", "urgency"],
+    template="""Based on these details, generate a professional follow-up email:
+
+Previous Interaction: {previous_interaction}
+Situation Type: {situation_type}
+Tone: {tone}
+Urgency Level: {urgency}
+
+Generate a personalized email that:
+1. Maintains {tone} tone
+2. Addresses the specific situation
+3. Provides clear next steps
+4. Is appropriate for {urgency} urgency level
+"""
+)
+
+scoring_template = """
+Analyze this follow-up email carefully and provide scores on a scale of 1-10 for each category:
+
+Email to analyze:
+{email_text}
+
+Please provide numerical scores and explanations in this exact format:
+
+CLARITY SCORE: [1-10]
+Explanation: [Why this score]
+
+PROFESSIONALISM SCORE: [1-10]
+Explanation: [Why this score]
+
+ACTION ITEMS SCORE: [1-10]
+Explanation: [Why this score]
+
+PERSONALIZATION SCORE: [1-10]
+Explanation: [Why this score]
+
+OVERALL EFFECTIVENESS SCORE: [1-10]
+Explanation: [Why this score]
+
+IMPROVEMENT SUGGESTIONS:
+1. [First suggestion]
+2. [Second suggestion]
+3. [Third suggestion]
+"""
+
+# 4. Create LangChain
+email_chain = LLMChain(llm=llm, prompt=email_template)
+
+# 5. Helper Functions
+def analyze_sentiment(text):
+    try:
+        result = sentiment_analyzer(text)[0]
+        sentiment_to_tone = {
+            'POS': 'Friendly',
+            'NEU': 'Professional',
+            'NEG': 'Apologetic'
+        }
+        return sentiment_to_tone.get(result['label'], 'Professional')
+    except Exception as e:
+        return 'Professional'
+
+# 6. Main Generation Function
+def generate_followup_email(previous_interaction, situation_type, tone, urgency):
+    try:
+        if not tone:
+            tone = analyze_sentiment(previous_interaction)
+            
+        # Generate email
+        email_result = email_chain.run({
+            "previous_interaction": previous_interaction,
+            "situation_type": situation_type,
+            "tone": tone,
+            "urgency": urgency
+        })
+        
+        # Generate score
+        score_result = llm(scoring_template.format(email_text=email_result))
+        return email_result, score_result
+    except Exception as e:
+        return f"Error generating email: {str(e)}", "Scoring unavailable"
+
+# 7. Gradio Interface
+demo = gr.Interface(
+    fn=generate_followup_email,
+    inputs=[
+        gr.Textbox(
+            label="Previous Interaction",
+            lines=5,
+            placeholder="Describe the previous interaction with the customer..."
+        ),
+        gr.Dropdown(
+            label="Situation Type",
+            choices=[
+                "Complaint Resolution",
+                "Service Issue",
+                "Payment Dispute",
+                "Product Query",
+                "General Follow-up"
+            ]
+        ),
+        gr.Dropdown(
+            label="Tone (Optional - will be automatically detected if not specified)",
+            choices=[
+                "",
+                "Professional",
+                "Apologetic",
+                "Friendly",
+                "Formal",
+                "Empathetic"
+            ]
+        ),
+        gr.Dropdown(
+            label="Urgency",
+            choices=["High", "Medium", "Low"]
+        )
+    ],
+    outputs=[
+        gr.Textbox(label="Generated Email"),
+        gr.Textbox(label="Email Score and Suggestions")
+    ],
+    title="Smart Sales Email Generator with Quality Scoring",
+    description="Generate and evaluate follow-up emails based on previous interactions",
+    examples=[
+        [
+            "Customer complained about slow website loading times and threatened to cancel subscription",
+            "Complaint Resolution",
+            "Apologetic",
+            "High"
+        ],
+        [
+            "Client requested information about premium features and pricing",
+            "Product Query",
+            "Professional",
+            "Medium"
+        ]
+    ]
+)
+
+# 8. Launch App
+if __name__ == "__main__":
+    demo.launch()
+
+

requirements.txt

@@ -1 +1,6 @@
-huggingface_hub==0.25.2
+gradio
+langchain
+transformers
+torch
+emoji
+huggingface_hub