Create app.py

app.py

@@ -0,0 +1,82 @@
+import streamlit as st
+import os
+import requests
+
+# Ensure that the Groq API key is set
+os.environ["GROQ_API_KEY"] = "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"
+
+# Groq API endpoint
+GROQ_API_URL = "https://api.groq.com/v1/inference"
+
+# Function to perform embedding retrieval using MiniLM via Groq API
+def retrieve_embedding(user_query):
+    payload = {
+        "model": "microsoft/MiniLM-L6-H384-uncased",
+        "input_text": user_query
+    }
+    headers = {
+        "Authorization": f"Bearer {os.getenv('GROQ_API_KEY')}"
+    }
+    response = requests.post(f"{GROQ_API_URL}/embedding", json=payload, headers=headers)
+    return response.json()["embedding"]
+
+# Function to perform response generation using FLAN-T5 via Groq API
+def generate_response(context):
+    payload = {
+        "model": "google/flan-t5-small",
+        "input_text": f"Given the following context, provide a supportive response: {context}"
+    }
+    headers = {
+        "Authorization": f"Bearer {os.getenv('GROQ_API_KEY')}"
+    }
+    response = requests.post(f"{GROQ_API_URL}/generate", json=payload, headers=headers)
+    return response.json()["text"]
+
+# Load the counseling conversations dataset
+from datasets import load_dataset
+dataset = load_dataset("Amod/mental_health_counseling_conversations")["train"]
+
+# Precompute embeddings for the dataset responses using Groq API
+@st.cache(allow_output_mutation=True)
+def embed_dataset(dataset):
+    embeddings = []
+    for entry in dataset:
+        embedding = retrieve_embedding(entry["response"])
+        embeddings.append(embedding)
+    return embeddings
+
+dataset_embeddings = embed_dataset(dataset)
+
+# Function to retrieve closest responses from the dataset using cosine similarity
+from sklearn.metrics.pairwise import cosine_similarity
+import numpy as np
+
+def retrieve_response(user_query, dataset, dataset_embeddings, k=5):
+    query_embedding = retrieve_embedding(user_query)
+    cos_scores = cosine_similarity([query_embedding], dataset_embeddings)[0]
+    top_indices = np.argsort(cos_scores)[-k:][::-1]
+
+    retrieved_responses = []
+    for idx in top_indices:
+        retrieved_responses.append(dataset[idx]["response"])
+    return retrieved_responses
+
+# Streamlit app UI
+st.title("Emotional Support Buddy")
+st.write("Enter your thoughts or concerns, and I'll provide some comforting words.")
+
+# User input
+user_query = st.text_input("How are you feeling today?")
+
+if user_query:
+    # Retrieve similar responses from the dataset
+    retrieved_responses = retrieve_response(user_query, dataset, dataset_embeddings)
+    
+    # Join retrieved responses to create a supportive context
+    context = " ".join(retrieved_responses)
+    
+    # Generate a supportive response using FLAN-T5 via Groq API
+    supportive_response = generate_response(context)
+    
+    st.write("Here's some advice or support for you:")
+    st.write(supportive_response)