Update app.py

app.py

@@ -2,83 +2,49 @@ import gradio as gr
 from sentence_transformers import SentenceTransformer
 import torch
 from huggingface_hub import InferenceClient
-#import os
-
-#HF_TOKEN = os.environ.get("HF_TOKEN")
 
+# Load and process knowledge base
 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)
+    knowledge = file.read()
+
+cleaned_chunks = [chunk.strip() for chunk in knowledge.strip().split("\n") if chunk.strip()]
 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)
-
-
-
-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)
-# using my matmul(matrix multiplication method to compare query to chunks)
-
-  top_indices = torch.topk(similarities, k=3).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
 
+# Function to retrieve most relevant info
+def get_top_chunks(query):
+    query_embedding = model.encode(query, convert_to_tensor=True)
+    query_embedding_normalized = query_embedding / query_embedding.norm()
+    chunk_embeddings_normalized = chunk_embeddings / chunk_embeddings.norm(dim=1, keepdim=True)
+    similarities = torch.matmul(chunk_embeddings_normalized, query_embedding_normalized)
+    top_indices = torch.topk(similarities, k=3).indices
+    return [cleaned_chunks[i] for i in top_indices]
 
+# Connect to HF inference client
 client = InferenceClient("google/gemma-3-27b-it")
 
-
+# Chatbot function
 def respond(message, history):
     knowledge_base = get_top_chunks(message)
-    system_message = f"You are a helpful chatbot named scooby, kinda like the cartoon character but not too much like it, who knows alot about pets and their diets and loves helping pet owners, and can only answer questions about pets:{knowledge_base}"
-    messages = [{"role":  "system", "content": system_message}]
-
+    system_message = f"You are a helpful chatbot named Scooby, kind of like the cartoon character but not too much like it. You know a lot about pets and their diets and can only answer questions about pets. Here is what you know: {knowledge_base}"
     
-      
+    messages = [{"role": "system", "content": system_message}]
     if history:
-        messages.extend(history)
-        
+        messages += history
     messages.append({"role": "user", "content": message})
+
     response = ""
-    for messages in client.chat_completion(messages,max_tokens = 2500, stream = True):
-        token = messages.choices[0].delta.content
+    for delta in client.chat_completion(messages=messages, max_tokens=2500, stream=True):
+        token = delta.choices[0].delta.get("content", "")
         response += token
         yield response
 
+# Recipe chatbot (simple placeholder)
+def respond_recipe(message, history):
+    return f"Here's a custom recipe idea for your pet based on: '{message}'. 🐾"
 
-
-
-theme = gr.themes.Monochrome(primary_hue="teal",secondary_hue="orange")
+# Theme, welcome, topics
+theme = gr.themes.Monochrome(primary_hue="teal", secondary_hue="orange")
 
 welcome_message = """
 # Welcome to ScoobyAI
@@ -92,11 +58,7 @@ topics = """
 - Creating recipes for pets based on dietary needs
 """
 
-    
-#chatbot = gr.ChatInterface(respond, type = "messages", theme)
-
-import gradio as gr
-
+# Gradio UI
 with gr.Blocks(theme=theme) as demo:
     gr.Image(
         value="scooby.png",
@@ -107,18 +69,17 @@ with gr.Blocks(theme=theme) as demo:
         show_download_button=False,
         container=False
     )
-    
+
     gr.Markdown(welcome_message)
-    
+
     with gr.Row():
         with gr.Column():
             gr.Markdown(topics)
-    
+
     with gr.Tabs():
         with gr.Tab("Main Page"):
             with gr.Row():
                 text_input = gr.Textbox(label="Ask Scooby a question about your pet")
-                # image_input = gr.Image(type="pil", label="Upload an image of your pet (optional)")
                 output = gr.Textbox(label="Scooby's Answer")
             submit_btn = gr.Button("Ask Scooby")
             submit_btn.click(fn=respond, inputs=text_input, outputs=output)
@@ -136,21 +97,9 @@ with gr.Blocks(theme=theme) as demo:
                 clear_btn="🧹 Clear Chat"
             )
 
-
-
-
-
 demo.launch(debug=True)
 
 
 
 
 
-
-
-
-
-
-
-
-