Upload 2 files

Dockerfile

@@ -31,12 +31,11 @@ COPY . .
 EXPOSE 7860
 
 # Start vLLM in the background and then the Gradio app
-CMD bash -c "wget -O /tmp/tool_chat_template_llama3.1_json.jinja https://github.com/vllm-project/vllm/raw/refs/heads/main/examples/tool_chat_template_llama3.1_json.jinja && \
-    vllm.entrypoints.openai.api_server \
+CMD bash -c "vllm.entrypoints.openai.api_server \
     --model unsloth/llama-3-8b-Instruct-bnb-4bit \
     --enable-auto-tool-choice \
     --tool-call-parser llama3_json \
-    --chat-template /tmp/tool_chat_template_llama3.1_json.jinja \
+    --chat-template examples/tool_chat_template_llama3.1_json.jinja \
     --quantization bitsandbytes \
     --load-format bitsandbytes \
     --dtype half \

app.py

@@ -31,7 +31,7 @@ from docling.chunking import HybridChunker
 from langchain_community.document_loaders import WebBaseLoader
 from urllib.parse import urlparse
 
-from langchain_groq import ChatGroq
+#from langchain_groq import ChatGroq
 from langchain_openai import ChatOpenAI
 from langgraph.prebuilt import InjectedStore
 from langgraph.store.base import BaseStore