Update app.py

app.py

@@ -1,11 +1,20 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
-
+from sentence_transformers import SentenceTransformer
+import torch
+import numpy as np 
 client = InferenceClient("Qwen/Qwen2.5-7B-Instruct-1M")
 
+# Open the ECOsphere.txt file in read mode with UTF-8 encoding
+with open("ECOsphere.txt", "r", encoding="utf-8") as file:
+  # Read the entire contents of the file and store it in a variable
+  ECOsphere_text = file.read()
+
 def respond(message, history):
-    
-    messages = [{"role": "system", "content": "You are an annoying chatbot who forces me to study"}]
+    top_results = get_top_chunks( message , chunk_embeddings, cleaned_chunks) # Complete this line
+    # Print the top results
+    print(top_results)
+    messages = [{"role": "system", "content": "You are a chatbot that encourage people to live more sustainably. Base your response on the following action {top_results}"}]
     
     if history:
         messages.extend(history)
@@ -22,4 +31,78 @@ def respond(message, history):
 
 chatbot = gr.ChatInterface(respond, type="messages")
 
+def preprocess_text(text):
+  # Strip extra whitespace from the beginning and the end of the text
+  cleaned_text = text.strip()
+
+  # Split the cleaned_text by every newline character (\n)
+  chunks = cleaned_text.split("\n")
+
+  # Create an empty list to store cleaned chunks
+  cleaned_chunks = []
+
+  # Write your for-in loop below to clean each chunk and add it to the cleaned_chunks list
+  for chunk in chunks:
+    stripped_chunk = chunk.strip()
+    cleaned_chunks.append(stripped_chunk)
+
+
+  # Print cleaned_chunks
+  print(cleaned_chunks)
+
+  # Print the length of cleaned_chunks
+  print(len(cleaned_chunks))
+
+  # Return the cleaned_chunks
+  return cleaned_chunks
+
+# Load the pre-trained embedding model that converts text to vectors
+model = SentenceTransformer('all-MiniLM-L6-v2')
+
+def create_embeddings(text_chunks):
+  # Convert each text chunk into a vector embedding and store as a tensor
+  chunk_embeddings = model.encode(text_chunks, convert_to_tensor=True) # Replace ... with the text_chunks list
+
+  # Print the chunk embeddings
+  print(chunk_embeddings)
+
+  # Print the shape of chunk_embeddings
+  print(chunk_embeddings.shape)
+
+  # Return the chunk_embeddings
+  return chunk_embeddings
+
+# Define a function to find the most relevant text chunks for a given query, chunk_embeddings, and text_chunks
+def get_top_chunks(query, chunk_embeddings, text_chunks):
+  # Convert the query text into a vector embedding
+  query_embedding = model.encode(query, convert_to_tensor=True) # Complete this line
+
+  # Normalize the query embedding to unit length for accurate similarity comparison
+  query_embedding_normalized = query_embedding / query_embedding.norm()
+
+  # Normalize all chunk embeddings to unit length for consistent comparison
+  chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)
+
+  # Calculate cosine similarity between query and all chunks using matrix multiplication
+  similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized ) # Complete this line
+
+  # Print the similarities
+  print(similarities)
+
+  # Find the indices of the 3 chunks with highest similarity scores
+  top_indices = torch.topk(similarities, k=3).indices
+
+  # Print the top indices
+  print(top_indices)
+
+  # Create an empty list to store the most relevant chunks
+  top_chunks = []
+
+  # Loop through the top indices and retrieve the corresponding text chunks
+  for indices in top_indices:
+    relevant_info = cleaned_chunks
+    top_chunks.append(relevant_info)
+
+
+
 chatbot.launch()