Update app.py
Browse files
app.py
CHANGED
@@ -1,64 +1,82 @@
|
|
1 |
import gradio as gr
|
2 |
-
|
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("HuggingFaceH4/zephyr-7b-beta")
|
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,
|
33 |
-
stream=True,
|
34 |
-
temperature=temperature,
|
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=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 |
|
63 |
if __name__ == "__main__":
|
64 |
demo.launch()
|
|
|
1 |
import gradio as gr
|
2 |
+
import requests
|
3 |
+
import json
|
4 |
+
import os
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
|
6 |
+
# Set OpenRouter API key in the Space's secrets as "OPENROUTER_API_KEY"
|
7 |
+
OPENROUTER_API_KEY = os.getenv("OPENROUTER_API_KEY")
|
8 |
+
HEADERS = {
|
9 |
+
"Authorization": f"Bearer {OPENROUTER_API_KEY}",
|
10 |
+
"HTTP-Referer": "https://huggingface.co/spaces/YOUR_SPACE", # Optional
|
11 |
+
"X-Title": "CrispChat" # Optional
|
12 |
+
}
|
13 |
+
|
14 |
+
# List of free OpenRouter models
|
15 |
+
FREE_MODELS = {
|
16 |
+
"Google: Gemini Pro 2.5 Experimental (free)": ("google/gemini-2.5-pro-exp-03-25:free", 1000000),
|
17 |
+
"DeepSeek: DeepSeek V3 (free)": ("deepseek/deepseek-chat:free", 131072),
|
18 |
+
"Meta: Llama 3.2 11B Vision Instruct (free)": ("meta-llama/llama-3.2-11b-vision-instruct:free", 131072),
|
19 |
+
"Qwen: Qwen2.5 VL 72B Instruct (free)": ("qwen/qwen2.5-vl-72b-instruct:free", 131072),
|
20 |
+
}
|
21 |
+
|
22 |
+
|
23 |
+
def query_openrouter_model(model_id, prompt, image=None):
|
24 |
+
messages = [{"role": "user", "content": prompt}]
|
25 |
+
|
26 |
+
# If image is included, add it to the message content as a dict
|
27 |
+
if image is not None:
|
28 |
+
with open(image, "rb") as f:
|
29 |
+
image_bytes = f.read()
|
30 |
+
base64_image = base64.b64encode(image_bytes).decode("utf-8")
|
31 |
+
messages[0]["content"] = [
|
32 |
+
{"type": "text", "text": prompt},
|
33 |
+
{"type": "image_url", "image_url": {"url": f"data:image/png;base64,{base64_image}"}}
|
34 |
+
]
|
35 |
+
|
36 |
+
payload = {
|
37 |
+
"model": model_id,
|
38 |
+
"messages": messages
|
39 |
+
}
|
40 |
+
|
41 |
+
response = requests.post(
|
42 |
+
url="https://openrouter.ai/api/v1/chat/completions",
|
43 |
+
headers=HEADERS,
|
44 |
+
data=json.dumps(payload)
|
45 |
+
)
|
46 |
+
|
47 |
+
try:
|
48 |
+
response.raise_for_status()
|
49 |
+
data = response.json()
|
50 |
+
return data["choices"][0]["message"]["content"]
|
51 |
+
except Exception as e:
|
52 |
+
return f"Error: {str(e)}\n{response.text}"
|
53 |
+
|
54 |
+
|
55 |
+
def chat_interface(prompt, image, model_label):
|
56 |
+
model_id, _ = FREE_MODELS[model_label]
|
57 |
+
return query_openrouter_model(model_id, prompt, image)
|
58 |
+
|
59 |
+
|
60 |
+
with gr.Blocks(title="CrispChat") as demo:
|
61 |
+
gr.Markdown("""
|
62 |
+
# 🌟 CrispChat
|
63 |
+
Multi-modal chat with free OpenRouter models
|
64 |
+
""")
|
65 |
+
|
66 |
+
with gr.Row():
|
67 |
+
prompt = gr.Textbox(label="Enter your message", lines=4, placeholder="Ask me anything...")
|
68 |
+
image = gr.Image(type="filepath", label="Optional image input")
|
69 |
+
|
70 |
+
model_choice = gr.Dropdown(
|
71 |
+
choices=list(FREE_MODELS.keys()),
|
72 |
+
value="Google: Gemini Pro 2.5 Experimental (free)",
|
73 |
+
label="Select model"
|
74 |
+
)
|
75 |
+
|
76 |
+
output = gr.Textbox(label="Response", lines=6)
|
77 |
+
|
78 |
+
submit = gr.Button("Submit")
|
79 |
+
submit.click(fn=chat_interface, inputs=[prompt, image, model_choice], outputs=output)
|
80 |
|
81 |
if __name__ == "__main__":
|
82 |
demo.launch()
|