UMAR798 commited on
Commit
633826a
·
verified ·
1 Parent(s): 92552c5

Update app.py

Browse files
Files changed (1) hide show
  1. app.py +108 -65
app.py CHANGED
@@ -1,69 +1,112 @@
 
 
1
  import gradio as gr
2
- from huggingface_hub import InferenceClient
3
-
4
-
5
- def respond(
6
- message,
7
- history: list[dict[str, str]],
8
- system_message,
9
- max_tokens,
10
- temperature,
11
- top_p,
12
- hf_token: gr.OAuthToken,
13
- ):
14
- """
15
- 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
16
- """
17
- client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
18
-
19
- messages = [{"role": "system", "content": system_message}]
20
-
21
- messages.extend(history)
22
-
23
- messages.append({"role": "user", "content": message})
24
-
25
- response = ""
26
-
27
- for message in client.chat_completion(
28
- messages,
29
- max_tokens=max_tokens,
30
- stream=True,
31
- temperature=temperature,
32
- top_p=top_p,
33
- ):
34
- choices = message.choices
35
- token = ""
36
- if len(choices) and choices[0].delta.content:
37
- token = choices[0].delta.content
38
-
39
- response += token
40
- yield response
41
-
42
-
43
- """
44
- For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
45
- """
46
- chatbot = gr.ChatInterface(
47
- respond,
48
- additional_inputs=[
49
- gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
50
- gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
51
- gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
52
- gr.Slider(
53
- minimum=0.1,
54
- maximum=1.0,
55
- value=0.95,
56
- step=0.05,
57
- label="Top-p (nucleus sampling)",
58
- ),
59
- ],
60
- )
61
 
62
- with gr.Blocks() as demo:
63
- with gr.Sidebar():
64
- gr.LoginButton()
65
- chatbot.render()
66
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
 
68
- if __name__ == "__main__":
69
- demo.launch()
 
1
+ import re
2
+ import nltk
3
  import gradio as gr
4
+ from nltk.corpus import stopwords
5
+ from nltk.tokenize import word_tokenize
6
+ from sklearn.feature_extraction.text import TfidfVectorizer
7
+ from sklearn.metrics.pairwise import cosine_similarity
8
+
9
+ # Download NLTK data
10
+ nltk.download("punkt")
11
+ nltk.download("stopwords")
12
+
13
+ # -------------------------------
14
+ # FAQ Dataset
15
+ # -------------------------------
16
+
17
+ faq_data = {
18
+ "What is AI?":
19
+ "Artificial Intelligence is the simulation of human intelligence by machines.",
20
+
21
+ "What is Machine Learning?":
22
+ "Machine Learning is a subset of AI that allows systems to learn from data.",
23
+
24
+ "What is Deep Learning?":
25
+ "Deep Learning is a branch of Machine Learning that uses neural networks.",
26
+
27
+ "Who developed Python?":
28
+ "Python was created by Guido van Rossum.",
29
+
30
+ "What is Hugging Face?":
31
+ "Hugging Face is a platform for Machine Learning models and datasets.",
32
+
33
+ "What is Google Colab?":
34
+ "Google Colab is a free cloud-based Jupyter Notebook service.",
35
+
36
+ "What is NLP?":
37
+ "Natural Language Processing enables computers to understand human language.",
38
+
39
+ "What is Streamlit?":
40
+ "Streamlit is a Python framework used to build data apps.",
41
+
42
+ "What is Gradio?":
43
+ "Gradio is a Python library for creating web interfaces for ML models.",
44
+
45
+ "What is cosine similarity?":
46
+ "Cosine similarity measures how similar two text vectors are."
47
+ }
48
+
49
+ # -------------------------------
50
+ # Text Preprocessing
51
+ # -------------------------------
52
+
53
+ stop_words = set(stopwords.words("english"))
54
+
55
+ def preprocess(text):
56
+ text = text.lower()
57
+ text = re.sub(r'[^a-zA-Z ]', '', text)
58
+
59
+ tokens = word_tokenize(text)
 
 
 
60
 
61
+ tokens = [word for word in tokens if word not in stop_words]
 
 
 
62
 
63
+ return " ".join(tokens)
64
+
65
+ # Preprocess Questions
66
+ questions = list(faq_data.keys())
67
+ answers = list(faq_data.values())
68
+
69
+ processed_questions = [preprocess(q) for q in questions]
70
+
71
+ # TF-IDF Vectorizer
72
+ vectorizer = TfidfVectorizer()
73
+
74
+ question_vectors = vectorizer.fit_transform(processed_questions)
75
+
76
+ # -------------------------------
77
+ # Chatbot Function
78
+ # -------------------------------
79
+
80
+ def chatbot(user_input):
81
+
82
+ processed_input = preprocess(user_input)
83
+
84
+ input_vector = vectorizer.transform([processed_input])
85
+
86
+ similarities = cosine_similarity(input_vector, question_vectors)
87
+
88
+ best_match = similarities.argmax()
89
+
90
+ score = similarities[0][best_match]
91
+
92
+ if score < 0.25:
93
+ return "Sorry, I couldn't find a relevant answer."
94
+
95
+ return answers[best_match]
96
+
97
+ # -------------------------------
98
+ # Gradio UI
99
+ # -------------------------------
100
+
101
+ demo = gr.Interface(
102
+ fn=chatbot,
103
+ inputs=gr.Textbox(
104
+ lines=2,
105
+ placeholder="Ask a question..."
106
+ ),
107
+ outputs="text",
108
+ title="🤖 FAQ Chatbot",
109
+ description="FAQ Chatbot using NLP, TF-IDF and Cosine Similarity"
110
+ )
111
 
112
+ demo.launch()