deepgeek/gradio-webrtc
2
0
Fork 0
mirror of https://github.com/HumanAIGC-Engineering/gradio-webrtc.git synced 2026-02-05 18:09:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

Use huggingface_hub.InferenceClient instead of openai for Sambanova client (#79)

Browse Source
This commit is contained in:
Lucain
2025-02-26 16:06:17 +01:00
committed by GitHub
parent bb85e894be
commit c6769fe33f
4 changed files with 10 additions and 13 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
demo/hello_computer/app.py
View File

@@ -4,8 +4,8 @@ import os
from pathlib import Path from pathlib import Path
import gradio as gr import gradio as gr
import huggingface_hub
import numpy as np import numpy as np
import openai
from dotenv import load_dotenv from dotenv import load_dotenv
from fastapi import FastAPI from fastapi import FastAPI
from fastapi.responses import HTMLResponse, StreamingResponse from fastapi.responses import HTMLResponse, StreamingResponse
@@ -24,9 +24,9 @@ load_dotenv()
curr_dir = Path(__file__).parent curr_dir = Path(__file__).parent
client = openai.OpenAI( client = huggingface_hub.InferenceClient(
api_key=os.environ.get("SAMBANOVA_API_KEY"), api_key=os.environ.get("SAMBANOVA_API_KEY"),
base_url="https://api.sambanova.ai/v1", provider="sambanova",
) )
model = get_stt_model() model = get_stt_model()
@@ -49,7 +49,7 @@ def response(
conversation_state.append({"role": "user", "content": text}) conversation_state.append({"role": "user", "content": text})
request = client.chat.completions.create( request = client.chat.completions.create(
model="Meta-Llama-3.2-3B-Instruct", model="meta-llama/Llama-3.2-3B-Instruct",
messages=conversation_state, # type: ignore messages=conversation_state, # type: ignore
temperature=0.1, temperature=0.1,
top_p=0.1, top_p=0.1,

2
demo/hello_computer/requirements.txt
View File

@@ -1,4 +1,4 @@
fastrtc[stopword] fastrtc[stopword]
python-dotenv python-dotenv
openai huggingface_hub>=0.29.0
twilio twilio

11
demo/talk_to_sambanova/app.py
View File

@@ -4,8 +4,8 @@ import os
from pathlib import Path from pathlib import Path
import gradio as gr import gradio as gr
import huggingface_hub
import numpy as np import numpy as np
import openai
from dotenv import load_dotenv from dotenv import load_dotenv
from fastapi import FastAPI from fastapi import FastAPI
from fastapi.responses import HTMLResponse, StreamingResponse from fastapi.responses import HTMLResponse, StreamingResponse
@@ -13,7 +13,6 @@ from fastrtc import (
AdditionalOutputs, AdditionalOutputs,
ReplyOnPause, ReplyOnPause,
Stream, Stream,
WebRTCError,
get_stt_model, get_stt_model,
get_twilio_turn_credentials, get_twilio_turn_credentials,
) )
@@ -25,9 +24,9 @@ load_dotenv()
curr_dir = Path(__file__).parent curr_dir = Path(__file__).parent
client = openai.OpenAI( client = huggingface_hub.InferenceClient(
api_key=os.environ.get("SAMBANOVA_API_KEY"), api_key=os.environ.get("SAMBANOVA_API_KEY"),
base_url="https://api.sambanova.ai/v1", provider="sambanova",
) )
stt_model = get_stt_model() stt_model = get_stt_model()
@@ -49,10 +48,8 @@ def response(
conversation_state.append({"role": "user", "content": text}) conversation_state.append({"role": "user", "content": text})
raise WebRTCError("test")
request = client.chat.completions.create( request = client.chat.completions.create(
model="Meta-Llama-3.2-3B-Instruct", model="meta-llama/Llama-3.2-3B-Instruct",
messages=conversation_state, # type: ignore messages=conversation_state, # type: ignore
temperature=0.1, temperature=0.1,
top_p=0.1, top_p=0.1,

2
demo/talk_to_sambanova/requirements.txt
View File

@@ -1,4 +1,4 @@
fastrtc[vad, stt] fastrtc[vad, stt]
python-dotenv python-dotenv
openai huggingface_hub>=0.29.0
twilio twilio