First trial code written through - mostly drawn straight from lessons

app.py

@@ -0,0 +1,105 @@
+import gradio as gr
+!pip install -q sentence-transformers
+#this line is unneccesary in HF
+from sentence_transformers import SentenceTransformer
+import torch
+from huggingface_hub import InferenceClient
+
+client = InferenceClient("google/gemma-3-27b-it")
+
+with open("knowledge.txt", "r", encoding="utf-8") as file:
+  knowledge = file.read()
+cleaned_text = knowledge.strip()
+# cleaning up the text
+chunks = cleaned_text.split("\n")
+# separating the text into one sentence chunks
+cleaned_chunks = []
+# creating a empty list called cleaned_chunks
+
+for chunk in chunks:
+  # for every chunk in the chunks list,
+  stripped_chunk = chunk.strip()
+  # the chunk is getting stripped
+  if stripped_chunk:
+    #if the chunk is not empty then it is being appended to the cleaned chunk list.
+    cleaned_chunks.append(stripped_chunk)
+print(cleaned_chunks)
+model = SentenceTransformer('all-MiniLM-L6-v2')
+chunk_embeddings = model.encode(cleaned_chunks, convert_to_tensor=True)
+# encode the model, pass through my clean chunks and convert to vector embeddings (not arrays)
+print(chunk_embeddings
+
+
+
+def get_top_chunks(query): # store a function that gets the most relevant_info and make it return a variable “relevant_info”  then 
+  # create my function taking query as my parameter
+  query_embedding = model.encode(query, convert_to_tensor=True)
+  # turning my query to a vector embedding for comparison
+  query_embedding_normalized = query_embedding / query_embedding.norm()
+  # normlaize my query to 1: allows for comparison of meaning
+  chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)
+  # normalizing chunks for comparison of meaning
+
+  similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized)
+  print(similarities)
+# using my matmul(matrix multiplication method to compare query to chunks)
+
+  top_indices = torch.topk(similarities, k=3).indices
+  print(top_indices)
+  # get the indices of the chunks that are most similar to my query
+
+  top_chunks = []
+
+
+  for i in top_indices:
+    chunk = chunks[i]
+    # for each index number in top_indices, get back the text
+    top_chunks.append(chunk) # adding the sentences that are associated with the top indices to the list
+
+  return top_chunks
+
+
+
+
+def respond(message, history):
+#use created variable for relevant info
+
+info = pull_relevant_info(message, top_k=3)
+    system_message = (f"You are a helpful and kind teacher.  You respond clearly in no more than three complete sentences. Use the following information to help answer the user's question:\n\n{info}\n\n")
+
+
+    
+#change HOW the bot responds
+      
+    if history:
+        messages.extend(history)
+    messages.append({"role": "user", "content": message})
+
+    response = ""
+    for messages in client.chat_completion(
+        messages,
+        max_tokens = 100,#change the length of the messages
+        stream = True
+
+
+):
+
+
+
+
+    token = messages.choices[0].delta.content
+
+
+    response += token
+
+
+    yield response
+
+
+
+
+
+
+
+
+