Added Colab Stuff

app.py

@@ -1,8 +1,113 @@
 import gradio as gr
 import random
+from huggingface_hub import InferenceClient
+# SEMANTIC SEARCH STEP 1
+from sentence_transformers import SentenceTransformer
+import torch
 #import lines go at the top!
 
-from huggingface_hub import InferenceClient
+# SEMANTIC SEARCH STEP 2 --> EDIT WITH YOUR OWN KNOWLEDGE BASE WHEN READY
+with open("water_cycle.txt", "r", encoding="utf-8") as file:
+  # Read the entire contents of the file and store it in a variable
+  water_cycle_text = file.read()
+print(water_cycle_text)
+
+# SEMANTIC SEARCH STEP 3
+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
+
+# Call the preprocess_text function and store the result in a cleaned_chunks variable
+cleaned_chunks = preprocess_text(water_cycle_text) # Complete this line; edit with my knowledgebase when ready
+
+# SEMANTIC SEARCH STEP 4
+# 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
+
+# Call the create_embeddings function and store the result in a new chunk_embeddings variable
+chunk_embeddings = create_embeddings(cleaned_chunks) # Complete this line
+
+# SEMANTIC SEARCH STEP 5
+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; bring it to the length of 1
+  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 i in top_indices:
+    relevant_info = cleaned_chunks[i]
+    top_chunks.append(relevant_info)
+
+  # Return the list of most relevant chunks
+  return top_chunks
+
+
+# SEMANTIC SEARCH STEP 6
+
+# Call the get_top_chunks function with the original query
+top_results = get_top_chunks('Is water good?',chunk_embeddings, cleaned_chunks) # Complete this line
+
+print(top_results)# Print the top results
+
 
 client = InferenceClient("microsoft/phi-4")
 # name of llm chatbot accessed ^^ or can use ' microsoft/phi-4 that's connected to the microsoft phi gen model