Refactored to model, view, data

app.py

@@ -1,67 +1,7 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-from langchain_community.document_loaders import UnstructuredURLLoader
-
-import os
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("meta-llama/Llama-3.2-1B-Instruct", token=os.getenv("HUGGINGFACEHUB_API_TOKEN"))
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    url,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    urls = [
-        url,
-    ]
-    loader = UnstructuredURLLoader(urls=urls)
-    data = loader.load()
-
-    context = data[0].page_content # will come from 'url'
-
-    prompt = f"""
-Use the following piece of context to answer the question asked.
-Please try to provide the answer only based on the context
-{context}
-Question:{message}
-Helpful Answers:
-"""
-
-    messages = [{"role": "system", "content": url}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": prompt})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
+from model import model
 
+import gradio as gr
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 with gr.Blocks() as demo:
     with gr.Row(equal_height=True):
         with gr.Column(min_width=200, scale=0):
@@ -78,7 +18,7 @@ with gr.Blocks() as demo:
         with gr.Column():
             url = gr.Textbox(value="https://www.gradio.app/docs/gradio/chatinterface", label="Docs URL", render=True)
             chat = gr.ChatInterface(
-                respond,
+                model.respond,
                 additional_inputs=[
                     url,
                     max_tokens,

data.py

@@ -0,0 +1,26 @@
+from langchain_community.document_loaders import UnstructuredURLLoader
+
+class Data:
+    def __init__(self, url):
+        self.url = url
+
+    def get_context(self):
+        urls = [
+            self.url,
+        ]
+        loader = UnstructuredURLLoader(urls=urls)
+        data = loader.load()
+    
+        context = data[0].page_content # will come from 'url'
+
+        return context
+
+    def build_prompt(self, question):
+        prompt = f"""
+        Use the following piece of context to answer the question asked.
+        Please try to provide the answer only based on the context
+        {self.get_context()}
+        Question:{question}
+        Helpful Answers:
+        """
+        return prompt

model.py

@@ -0,0 +1,48 @@
+import os
+
+from huggingface_hub import InferenceClient
+
+from data import Data
+
+class Model:
+    def __init__(self, model_id="meta-llama/Llama-3.2-1B-Instruct"):
+        self.client = InferenceClient(model_id, token=os.getenv("HUGGINGFACEHUB_API_TOKEN"))
+
+    def respond(
+        self,
+        message,
+        history: list[tuple[str, str]],
+        url,
+        max_tokens,
+        temperature,
+        top_p,
+    ):
+    
+        data = Data(url)
+    
+        messages = [{"role": "system", "content": url}]
+    
+        for val in history:
+            if val[0]:
+                messages.append({"role": "user", "content": val[0]})
+            if val[1]:
+                messages.append({"role": "assistant", "content": val[1]})
+    
+        messages.append({"role": "user", "content": data.build_prompt(message)})
+    
+        response = ""
+    
+        for message in self.client.chat_completion(
+            messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = message.choices[0].delta.content
+    
+            response += token
+            yield response
+    
+
+model = Model()