Upload 7 files

.env

@@ -0,0 +1 @@
+GOOGLE_API_KEY=AIzaSyAe9c-4S0loskd55jVnJoXK8s2HfRUOj4Y

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+IMDB_Dataset.csv filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -0,0 +1,20 @@
+# Use an official Python runtime as a parent image
+FROM python:3.8-slim
+
+# Set the working directory in the container
+WORKDIR /app
+
+# Copy the current directory contents into the container at /app
+COPY . /app
+
+# Install any needed packages specified in requirements.txt
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Make port 80 available to the world outside this container
+EXPOSE 80
+
+# Define environment variable
+ENV NAME World
+
+# Run main.py when the container launches
+CMD ["python", "main.py"]

IMDB_Dataset.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfc447764f82be365fa9c2beef4e8df89d3919e3da95f5088004797d79695aa2
+size 66212309

main.py

@@ -0,0 +1,73 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from dotenv import load_dotenv
+import os
+import google.generativeai as genai
+import joblib
+
+# Load environment variables
+load_dotenv()
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+
+# Load the machine learning model
+try:
+    model = joblib.load('./movie_review_classifier.joblib')
+except Exception as e:
+    raise ImportError(f"Failed to load model: {e}")
+
+app = FastAPI()
+
+# Define models for requests
+class QueryRequest(BaseModel):
+    question: str
+
+class Review(BaseModel):
+    text: str
+
+# Initialize the Gemini chat model
+gemini_model = genai.GenerativeModel("gemini-pro")
+chat = gemini_model.start_chat(history=[])
+
+mental_health_prompt = """
+You are an expert in providing mental health support. When a user describes their mental health issues,
+you should provide relevant articles or blog posts to assist them.
+"""
+
+# Gemini response function
+def get_gemini_response(question, prompt):
+    response = chat.send_message(f"{prompt} {question}", stream=True)
+    return [chunk.text for chunk in response]
+
+# Function to retrieve articles from a database or external source
+def get_articles(query):
+    return [
+        {"title": "Understanding Anxiety", "url": "https://newsinhealth.nih.gov/2016/03/understanding-anxiety-disorders", "summary": "A comprehensive guide on anxiety disorders."},
+        {"title": "Coping with Depression", "url": "https://www.helpguide.org/articles/depression/coping-with-depression.htm", "summary": "Effective strategies for dealing with depression."}
+    ]
+
+# Mental health support endpoint
+@app.post("/rag")
+async def mental_health_support(request: QueryRequest):
+    try:
+        responses = get_gemini_response(request.question, mental_health_prompt)
+        articles = get_articles(request.question)
+        result = {"responses": responses, "articles": articles}
+        return result
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+# Classification endpoint
+@app.post("/classification")
+async def classify_review(review: Review):
+    try:
+        prediction = model.predict([review.text])
+        return {"predicted_sentiment": prediction[0]}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+# Main function to run the server
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)
+
+

model.py

@@ -0,0 +1,36 @@
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from sklearn.feature_extraction.text import CountVectorizer
+from sklearn.naive_bayes import MultinomialNB
+from sklearn.pipeline import make_pipeline
+import joblib
+
+def load_data():
+    # Load dataset
+    data = pd.read_csv('./IMDB_Dataset.csv')
+    data['review'] = data['review'].apply(lambda x: x.lower())  # convert to lowercase
+    return data
+
+def train_model(data):
+    # Split data into train and test sets
+    train_data, _, train_labels, _ = train_test_split(data['review'], data['sentiment'], test_size=0.2, random_state=42)
+    
+    # Create a text processing and classification pipeline
+    model = make_pipeline(CountVectorizer(), MultinomialNB())
+    
+    # Train the model
+    model.fit(train_data, train_labels)
+    return model
+
+def save_model(model):
+    # Save the model
+    joblib.dump(model, './movie_review_classifier.joblib')
+
+def main():
+    data = load_data()
+    model = train_model(data)
+    save_model(model)
+    print("Model trained and saved successfully.")
+
+if __name__ == "__main__":
+    main()

movie_review_classifier.joblib

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc6b14f6e523184f23ad8650bf4bb6461c82d8c8c528f582f086754928d18b4
+size 4291770

requirements.txt

@@ -0,0 +1,8 @@
+numpy
+scikit-learn 
+fastapi 
+joblib 
+python-dotenv 
+uvicorn
+pandas
+google-generativeai