Upload 3 files

Dockerfile

@@ -0,0 +1,16 @@
+# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
+# you will also find guides on how best to write your Dockerfile
+
+FROM python:3.9
+
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+WORKDIR /app
+
+COPY --chown=user ./requirements.txt requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt
+
+COPY --chown=user . /app
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -0,0 +1,97 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from huggingface_hub import InferenceClient
+import os
+
+app = FastAPI()
+
+# Get the token from the environment variable
+hf_token = os.environ.get("HF_TOKEN")
+
+if hf_token:
+    client = InferenceClient("meta-llama/Meta-Llama-3-8B-Instruct", token=hf_token)
+else:
+    raise ValueError("HF_TOKEN environment variable not set. Please add it as a secret in your Hugging Face Space.")
+
+class ChatRequest(BaseModel):
+    message: str
+    system_message: str = "You are a friendly Chatbot."
+    max_tokens: int = 512
+    temperature: float = 0.7
+    top_p: float = 0.95
+
+class ChatResponse(BaseModel):
+    response: str
+
+@app.post("/chat", response_model=ChatResponse)
+async def chat(request: ChatRequest):
+    try:
+        messages = [
+            {"role": "system", "content": request.system_message},
+            {"role": "user", "content": request.message},
+        ]
+
+        response = client.chat_completion(
+            messages=messages,
+            max_tokens=request.max_tokens,
+            temperature=request.temperature,
+            top_p=request.top_p,
+        )
+
+        return {"response": response.choices[0].message.content}
+    except Exception as e:
+        raise HTTPException(status_code=500, detail=str(e))
+
+# from fastapi import FastAPI, HTTPException
+# from pydantic import BaseModel
+# from huggingface_hub import InferenceClient
+# import os
+
+# app = FastAPI()
+
+# # Get the token from the environment variable
+# hf_token = os.environ.get("HF_TOKEN")
+
+# if hf_token:
+#     client = InferenceClient("HuggingFaceH4/zephyr-7b-beta", token=hf_token)
+# else:
+#     raise ValueError("HF_TOKEN environment variable not set. Please add it as a secret in your Hugging Face Space.")
+
+# # Rest of your code...
+
+# class ChatRequest(BaseModel):
+#     message: str
+#     history: list[tuple[str, str]] = []
+#     system_message: str = "You are a friendly Chatbot."
+#     max_tokens: int = 512
+#     temperature: float = 0.7
+#     top_p: float = 0.95
+
+# class ChatResponse(BaseModel):
+#     response: str
+
+# @app.post("/chat", response_model=ChatResponse)
+# async def chat(request: ChatRequest):
+#     try:
+#         messages = [{"role": "system", "content": request.system_message}]
+#         for val in request.history:
+#             if val[0]:
+#                 messages.append({"role": "user", "content": val[0]})
+#             if val[1]:
+#                 messages.append({"role": "assistant", "content": val[1]})
+#         messages.append({"role": "user", "content": request.message})
+
+#         response = ""
+#         for message in client.chat_completion(
+#             messages,
+#             max_tokens=request.max_tokens,
+#             stream=True,
+#             temperature=request.temperature,
+#             top_p=request.top_p,
+#         ):
+#             token = message.choices[0].delta.content
+#             response += token
+
+#         return {"response": response}
+#     except Exception as e:
+#         raise HTTPException(status_code=500, detail=str(e))

requirements.txt

@@ -0,0 +1,4 @@
+fastapi
+uvicorn
+huggingface_hub
+datasets