Create app.py

app.py

@@ -0,0 +1,72 @@
+import os
+import requests
+from sentence_transformers import SentenceTransformer
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+import pandas as pd
+import gradio as gr
+
+# Load pre-trained Sentence Transformer model
+model = SentenceTransformer('LaBSE')
+
+# Load questions and answers from the CSV file
+df = pd.read_csv('combined_questions_and_answers.csv')
+
+# Encode all questions in the dataset
+question_embeddings = model.encode(df['Question'].tolist())
+
+# Hugging Face API details for Meta-Llama 70B
+API_URL = "https://api-inference.huggingface.co/models/meta-llama/Meta-Llama-3-70B"
+headers = {"Authorization": f"Bearer {os.getenv('HUGGINGFACE_API_KEY')}"}
+
+# Function to call Hugging Face API to refine and translate text
+def refine_text(prompt):
+    payload = {
+        "inputs": prompt,
+        "parameters": {
+            "max_new_tokens": 800,
+            "temperature": 0.7
+        }
+    }
+    response = requests.post(API_URL, headers=headers, json=payload)
+    response_json = response.json()
+    if isinstance(response_json, list) and len(response_json) > 0:
+        return response_json[0].get('generated_text', '')
+    return "Error in refining text."
+
+# Function to find the most similar question and provide the answer
+def get_answer(user_question, threshold=0.30):
+    # Encode the user question
+    user_embedding = model.encode(user_question)
+
+    # Calculate cosine similarities
+    similarities = cosine_similarity([user_embedding], question_embeddings)
+
+    # Find the most similar question
+    max_similarity = np.max(similarities)
+    if max_similarity > threshold:
+        # Get the index of the most similar question
+        similar_question_idx = np.argmax(similarities)
+        # Retrieve the corresponding answer
+        answer = df.iloc[similar_question_idx]['Answer']
+        # Refine the answer using Meta-Llama 70B
+        refined_answer = refine_text(f"Refine this answer: {answer}")
+        return refined_answer, max_similarity
+    else:
+        return "The question appears to be out of domain. Kindly ask questions related to blood donations.", max_similarity
+
+# Gradio app
+def gradio_app(user_question):
+    answer, similarity = get_answer(user_question)
+    return f"Similarity: {similarity}\nAnswer: {answer}"
+
+# Launch the Gradio app
+iface = gr.Interface(
+    fn=gradio_app,
+    inputs=gr.Textbox(label="Enter your question"),
+    outputs=gr.Textbox(label="Answer"),
+    title="Blood Donation Q&A",
+    description="Ask questions related to blood donation and get answers.",
+)
+
+iface.launch()