v0.2.0

- откат 3

Dockerfile

@@ -1,22 +1,17 @@
 # Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
 # you will also find guides on how best to write your Dockerfile
-FROM ghcr.io/ggerganov/llama.cpp:server
-ENV LLAMA_ARG_MODEL_URL=https://huggingface.co/Vikhrmodels/Vikhr-Qwen-2.5-1.5B-Instruct-GGUF/resolve/main/Vikhr-Qwen-2.5-1.5b-Instruct-Q8_0.gguf \
-    LLAMA_ARG_CTX_SIZE=4096 \
-    LLAMA_ARG_N_PARALLEL=2 \
-    LLAMA_ARG_ENDPOINT_METRICS=1 \
-    LLAMA_ARG_PORT=8080
-RUN ./llama-server --host 0.0.0.0
 
-WORKDIR /app
-FROM python:3.11-slim as builder
+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
+RUN pip install llama-cpp-python --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 
 COPY --chown=user . /app
-
-CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]

app.py

@@ -113,3 +113,12 @@ async def predict(text: str):
     prompt = create_prompt(text)
     response = generate_response(prompt)
     return {"response": response}
+
+@app.post("/webhook")
+async def predict(response):
+    # Генерация ответа с помощью модели
+    logger.info('post/webhook -> response:')
+    logger.info(response)
+    # prompt = create_prompt(text)
+    # response = generate_response(prompt)
+    return {"response": response}