Upload 3 files

Dockerfile

@@ -0,0 +1,14 @@
+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", "api:app", "--host", "0.0.0.0", "--port", "7860"]
+

api.py

@@ -0,0 +1,50 @@
+from fastapi import FastAPI
+from pydantic import BaseModel
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
+
+# Definição do modelo de dados de entrada
+class Question(BaseModel):
+    text: str
+
+# Inicializando o FastAPI
+app = FastAPI()
+
+
+llm = Llama.from_pretrained(
+	repo_id="FabioSantos/curso_llama3.2_Finetune",
+	filename="unsloth.Q8_0.gguf",
+)
+
+
+def get_response(text: str) -> str:
+
+    response = llm.create_chat_completion(
+        messages=[
+            {
+                "role": "user",
+                "content": text  # Correção: Remover as chaves {} que estavam criando um set
+            }
+        ]
+    )
+    
+    response_text = response['choices'][0]['text']
+    
+    # Extrair a resposta após "### Response:"
+    if "### Response:" in response_text:
+        answer = response_text.split("### Response:")[1].strip()
+    else:
+        answer = response_text.strip()
+
+    print(f"Final Answer: {answer}")
+    return answer
+
+
+# Endpoint para receber uma questão e retornar a resposta
+@app.post("/ask")
+def ask_question(question: Question):
+    response = get_response(question.text)
+    return {"response": response}
+
+
+