Sg-at-srijan-us-kg
commited on
Commit
•
46dbbda
1
Parent(s):
2df1006
Update app.py
Browse files
app.py
CHANGED
@@ -1,49 +1,32 @@
|
|
1 |
import gradio as gr
|
2 |
from huggingface_hub import InferenceClient
|
3 |
|
|
|
|
|
|
|
4 |
client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
|
5 |
|
|
|
6 |
def respond(
|
7 |
message,
|
8 |
-
history,
|
9 |
system_message,
|
10 |
max_tokens,
|
11 |
temperature,
|
12 |
top_p,
|
13 |
-
file=None
|
14 |
):
|
15 |
-
# Initialize messages with the system message
|
16 |
messages = [{"role": "system", "content": system_message}]
|
17 |
|
18 |
-
# Handle file content if a file is uploaded
|
19 |
-
if file:
|
20 |
-
try:
|
21 |
-
if hasattr(file, 'read'): # If file-like object, read it
|
22 |
-
file_content = file.read().decode('utf-8')
|
23 |
-
elif hasattr(file, 'value'): # If NamedString or similar, access `value`
|
24 |
-
file_content = file.value
|
25 |
-
else:
|
26 |
-
file_content = str(file) # Fallback to str conversion if neither works
|
27 |
-
|
28 |
-
print("File content:", file_content) # Debug print
|
29 |
-
message = f"{file_content}\n\n{message}" # Append file content to message
|
30 |
-
except Exception as e:
|
31 |
-
print("Error reading file:", e)
|
32 |
-
message = f"(Error reading file: {e})\n\n{message}"
|
33 |
-
|
34 |
-
# Append conversation history
|
35 |
for val in history:
|
36 |
if val[0]:
|
37 |
messages.append({"role": "user", "content": val[0]})
|
38 |
if val[1]:
|
39 |
messages.append({"role": "assistant", "content": val[1]})
|
40 |
|
41 |
-
# Append the latest user message
|
42 |
messages.append({"role": "user", "content": message})
|
43 |
|
44 |
response = ""
|
45 |
|
46 |
-
# Stream response from the model
|
47 |
for message in client.chat_completion(
|
48 |
messages,
|
49 |
max_tokens=max_tokens,
|
@@ -52,11 +35,16 @@ def respond(
|
|
52 |
top_p=top_p,
|
53 |
):
|
54 |
token = message.choices[0].delta.content
|
|
|
55 |
response += token
|
56 |
yield response
|
57 |
|
|
|
|
|
|
|
|
|
58 |
demo = gr.ChatInterface(
|
59 |
-
|
60 |
additional_inputs=[
|
61 |
gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
|
62 |
gr.Slider(minimum=1, maximum=32000, value=2048, step=1, label="Max new tokens"),
|
@@ -66,12 +54,11 @@ demo = gr.ChatInterface(
|
|
66 |
maximum=1.0,
|
67 |
value=0.95,
|
68 |
step=0.05,
|
69 |
-
label="Top-p (nucleus sampling)"
|
70 |
),
|
71 |
-
gr.File(label="Upload a text file", file_types=[".txt"])
|
72 |
],
|
73 |
)
|
74 |
|
|
|
75 |
if __name__ == "__main__":
|
76 |
-
demo.launch()
|
77 |
-
|
|
|
1 |
import gradio as gr
|
2 |
from huggingface_hub import InferenceClient
|
3 |
|
4 |
+
"""
|
5 |
+
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
|
6 |
+
"""
|
7 |
client = InferenceClient("Qwen/Qwen2.5-Coder-32B-Instruct")
|
8 |
|
9 |
+
|
10 |
def respond(
|
11 |
message,
|
12 |
+
history: list[tuple[str, str]],
|
13 |
system_message,
|
14 |
max_tokens,
|
15 |
temperature,
|
16 |
top_p,
|
|
|
17 |
):
|
|
|
18 |
messages = [{"role": "system", "content": system_message}]
|
19 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
20 |
for val in history:
|
21 |
if val[0]:
|
22 |
messages.append({"role": "user", "content": val[0]})
|
23 |
if val[1]:
|
24 |
messages.append({"role": "assistant", "content": val[1]})
|
25 |
|
|
|
26 |
messages.append({"role": "user", "content": message})
|
27 |
|
28 |
response = ""
|
29 |
|
|
|
30 |
for message in client.chat_completion(
|
31 |
messages,
|
32 |
max_tokens=max_tokens,
|
|
|
35 |
top_p=top_p,
|
36 |
):
|
37 |
token = message.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 |
demo = 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=32000, value=2048, step=1, label="Max new tokens"),
|
|
|
54 |
maximum=1.0,
|
55 |
value=0.95,
|
56 |
step=0.05,
|
57 |
+
label="Top-p (nucleus sampling)",
|
58 |
),
|
|
|
59 |
],
|
60 |
)
|
61 |
|
62 |
+
|
63 |
if __name__ == "__main__":
|
64 |
+
demo.launch()
|
|