Spaces:
Running
Running
File size: 5,109 Bytes
21cbcb5 5daf42e 21cbcb5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 |
import streamlit as st
from huggingface_hub import InferenceClient
import os
from typing import Iterator
API_KEY = os.getenv("TOGETHER_API_KEY")
if not API_KEY:
raise ValueError("API key is missing! Make sure TOGETHER_API_KEY is set in the Secrets.")
# Initialize the client with Together AI provider
@st.cache_resource
def get_client():
return InferenceClient(
provider="together",
api_key=API_KEY
)
def process_file(file) -> str:
"""Process uploaded file and return its content"""
if file is None:
return ""
try:
content = file.getvalue().decode('utf-8')
return content
except Exception as e:
return f"Error reading file: {str(e)}"
def generate_response(
message: str,
history: list[tuple[str, str]],
system_message: str,
max_tokens: int,
temperature: float,
top_p: float,
file=None
) -> Iterator[str]:
"""Generate streaming response from the model"""
client = get_client()
# Process file if uploaded
file_content = process_file(file) if file else ""
# If there's file content, append it to the message
if file_content:
message = f"File content:\n{file_content}\n\nUser message:\n{message}"
messages = [{"role": "system", "content": system_message}]
# Add conversation history
for user_msg, assistant_msg in history:
if user_msg:
messages.append({"role": "user", "content": user_msg})
if assistant_msg:
messages.append({"role": "assistant", "content": assistant_msg})
# Add current message
messages.append({"role": "user", "content": message})
try:
stream = client.chat.completions.create(
model="deepseek-ai/DeepSeek-R1",
messages=messages,
max_tokens=max_tokens,
stream=True,
temperature=temperature,
top_p=top_p,
)
for chunk in stream:
if chunk.choices and chunk.choices[0].delta and chunk.choices[0].delta.content:
yield chunk.choices[0].delta.content
except Exception as e:
yield f"Error: {str(e)}"
def main():
st.set_page_config(page_title="DeepSeek Chat", page_icon="💭", layout="wide")
# Initialize session state for chat history
if "messages" not in st.session_state:
st.session_state.messages = []
st.title("DeepSeek Chat with File Upload")
st.markdown("Chat with DeepSeek AI model. You can optionally upload files for the model to analyze.")
# Sidebar for parameters
with st.sidebar:
st.header("Settings")
system_message = st.text_area(
"System Message",
value="You are a friendly Chatbot.",
height=100
)
max_tokens = st.slider(
"Max Tokens",
min_value=1,
max_value=8192,
value=8192,
step=1
)
temperature = st.slider(
"Temperature",
min_value=0.1,
max_value=4.0,
value=0.0,
step=0.1
)
top_p = st.slider(
"Top-p (nucleus sampling)",
min_value=0.1,
max_value=1.0,
value=0.95,
step=0.05
)
uploaded_file = st.file_uploader(
"Upload File (optional)",
type=['txt', 'py', 'md', 'swift', 'java', 'js', 'ts', 'rb', 'go',
'php', 'c', 'cpp', 'h', 'hpp', 'cs', 'html', 'css', 'kt']
)
# Display chat messages
for message in st.session_state.messages:
with st.chat_message(message["role"]):
st.write(message["content"])
# Chat input
if prompt := st.chat_input("What would you like to know?"):
# Display user message
st.session_state.messages.append({"role": "user", "content": prompt})
with st.chat_message("user"):
st.write(prompt)
# Generate and display assistant response
with st.chat_message("assistant"):
response_placeholder = st.empty()
full_response = ""
# Get message history for context
history = [(msg["content"], next_msg["content"])
for msg, next_msg in zip(st.session_state.messages[::2], st.session_state.messages[1::2])]
# Stream the response
for response_chunk in generate_response(
prompt,
history,
system_message,
max_tokens,
temperature,
top_p,
uploaded_file
):
full_response += response_chunk
print(full_response)
response_placeholder.markdown(full_response + "▌")
response_placeholder.markdown(full_response)
# Add assistant response to chat history
st.session_state.messages.append({"role": "assistant", "content": full_response})
if __name__ == "__main__":
main() |