uploaded

app.py

@@ -1,70 +1,38 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    """
-    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(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
-
-if __name__ == "__main__":
-    demo.launch()
+import gradio as gr
+import joblib
+import numpy as np
+
+# --- Load chatbot data ---
+data = joblib.load("chatbot.pkl")
+questions = data["questions"]
+answers = data["answers"]
+embeddings = np.array(data["embeddings"])
+model = data["model"]
+
+def chatbot_reply(user_input, threshold=0.4):
+    if not user_input.strip():
+        return "Please ask a question."
+
+    # Encode user input
+    user_emb = model.encode([user_input])[0]
+    # Compute cosine similarity
+    cos_scores = np.dot(embeddings, user_emb) / (np.linalg.norm(embeddings, axis=1) * np.linalg.norm(user_emb))
+    idx = np.argmax(cos_scores)
+    score = cos_scores[idx]
+
+    if score < threshold:
+        return "Sorry, I am not able to answer that."
+    
+    return answers[idx]
+
+# --- Gradio UI ---
+chatbot = gr.ChatInterface(
+    fn=lambda msg, hist: (hist + [(msg, chatbot_reply(msg))], hist + [(msg, chatbot_reply(msg))]),
+    title="Sajid's FAQ Chatbot 🤖",
+    description="A chatbot trained on my custom FAQ data using embeddings.",
+    theme="soft"
+)
+
+if __name__ == "__main__":
+    chatbot.launch()
+

chatbot.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddbd04f2ce3492b01ad090c0d680612ebf4b3bf66a7a2105d5150bdb2c51c5f5
+size 1182871