update

Dockerfile

@@ -10,12 +10,13 @@ RUN apt-get update && \
 
 # Install Python dependencies
 COPY requirements.txt .
-RUN pip install --no-cache-dir --upgrade -r requirements.txt
+RUN pip install --no-cache-dir --upgrade -r requirements.txt && \
+    pip install --no-cache-dir llama-cpp-python==0.3.8 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
 
 # Pre-download the model
 ENV HF_HOME=/code/.cache/huggingface
 RUN mkdir -p /code/.cache/huggingface && \
-    pip install huggingface_hub && \
+    pip install --no-cache-dir huggingface_hub && \
     python -c "from huggingface_hub import hf_hub_download; hf_hub_download(repo_id='muhammadnoman76/cortex_q4', filename='unsloth.Q4_K_M.gguf', local_dir='/code', local_dir_use_symlinks=False)"
 
 # Copy application code

README.md

@@ -15,6 +15,4 @@ Check out the configuration reference at https://huggingface.co/docs/hub/spaces-
 This Space provides a FastAPI application that streams responses from the Cortex LLM model.
 
 - Send GET requests to `/stream?task=<your_task>` to receive a streamed response from the model.
-- Example: `/stream?task=make an agent which send mail by searching top 5 website from google`
-
-**Note**: The `/ui` endpoint is not implemented in the current version.
+- Example: `/stream?task=make an agent which send mail by searching top 5 website from google`

requirements.txt

@@ -1,5 +1,4 @@
-fastapi>=0.115.12
-uvicorn>=0.34.2
-pydantic>=2.11.4
-llama-cpp-python>=0.3.8
-huggingface_hub>=0.25.0
+fastapi==0.115.12
+uvicorn==0.34.2
+pydantic==2.11.4
+huggingface_hub==0.30.2