Spaces:
Running
Running
Update app.py
Browse files
app.py
CHANGED
|
@@ -1,11 +1,11 @@
|
|
| 1 |
import gradio as gr
|
| 2 |
-
from
|
| 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,
|
|
@@ -17,32 +17,35 @@ def respond(
|
|
| 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 |
-
|
| 31 |
-
|
|
|
|
|
|
|
| 32 |
max_tokens=max_tokens,
|
| 33 |
-
stream=True,
|
| 34 |
temperature=temperature,
|
| 35 |
top_p=top_p,
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 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=[
|
|
@@ -59,6 +62,5 @@ demo = gr.ChatInterface(
|
|
| 59 |
],
|
| 60 |
)
|
| 61 |
|
| 62 |
-
|
| 63 |
if __name__ == "__main__":
|
| 64 |
demo.launch()
|
|
|
|
| 1 |
import gradio as gr
|
| 2 |
+
from openai import OpenAI
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
|
| 4 |
+
# API istemcisini başlatıyoruz
|
| 5 |
+
client = OpenAI(
|
| 6 |
+
base_url="https://integrate.api.nvidia.com/v1",
|
| 7 |
+
api_key="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" # Geçerli API anahtarını kullan
|
| 8 |
+
)
|
| 9 |
|
| 10 |
def respond(
|
| 11 |
message,
|
|
|
|
| 17 |
):
|
| 18 |
messages = [{"role": "system", "content": system_message}]
|
| 19 |
|
| 20 |
+
# Geçmiş mesajları ekliyoruz
|
| 21 |
for val in history:
|
| 22 |
if val[0]:
|
| 23 |
messages.append({"role": "user", "content": val[0]})
|
| 24 |
if val[1]:
|
| 25 |
messages.append({"role": "assistant", "content": val[1]})
|
| 26 |
|
| 27 |
+
# Kullanıcı mesajını ekliyoruz
|
| 28 |
messages.append({"role": "user", "content": message})
|
| 29 |
|
| 30 |
response = ""
|
| 31 |
|
| 32 |
+
# API'den gelen yanıtı işliyoruz
|
| 33 |
+
completion = client.chat.completions.create(
|
| 34 |
+
model="nvidia/nemotron-4-340b-instruct",
|
| 35 |
+
messages=messages,
|
| 36 |
max_tokens=max_tokens,
|
|
|
|
| 37 |
temperature=temperature,
|
| 38 |
top_p=top_p,
|
| 39 |
+
stream=True,
|
| 40 |
+
)
|
| 41 |
+
|
| 42 |
+
for chunk in completion:
|
| 43 |
+
if chunk.choices[0].delta.content is not None:
|
| 44 |
+
token = chunk.choices[0].delta.content
|
| 45 |
+
response += token
|
| 46 |
+
yield response
|
| 47 |
|
| 48 |
+
# Gradio arayüzünü tanımlıyoruz
|
|
|
|
|
|
|
| 49 |
demo = gr.ChatInterface(
|
| 50 |
respond,
|
| 51 |
additional_inputs=[
|
|
|
|
| 62 |
],
|
| 63 |
)
|
| 64 |
|
|
|
|
| 65 |
if __name__ == "__main__":
|
| 66 |
demo.launch()
|