fix non root docker image (#6744)

Signed-off-by: Rajat Vig <rvig@etsy.com>

.dockerignore

@@ -9,3 +9,4 @@ tests
 .devcontainer
 *.tgz
 log.txt
+docker/Dockerfile.*

docker/Dockerfile.non_root

@@ -9,13 +9,16 @@ FROM $LITELLM_BUILD_IMAGE AS builder
 # Set the working directory to /app
 WORKDIR /app
 
+# Set the shell to bash
+SHELL ["/bin/bash", "-o", "pipefail", "-c"]
+
 # Install build dependencies
 RUN apt-get clean && apt-get update && \
     apt-get install -y gcc python3-dev && \
     rm -rf /var/lib/apt/lists/*
 
-RUN pip install --upgrade pip && \
-    pip install build
+RUN pip install --no-cache-dir --upgrade pip && \
+    pip install --no-cache-dir build
 
 # Copy the current directory contents into the container at /app
 COPY . .
@@ -39,7 +42,7 @@ RUN pip wheel --no-cache-dir --wheel-dir=/wheels/ -r requirements.txt
 FROM $LITELLM_RUNTIME_IMAGE AS runtime
 
 # Update dependencies and clean up - handles debian security issue
-RUN apt-get update && apt-get upgrade -y && rm -rf /var/lib/apt/lists/* 
+RUN apt-get update && apt-get upgrade -y && rm -rf /var/lib/apt/lists/*
 
 WORKDIR /app
 # Copy the current directory contents into the container at /app
@@ -53,32 +56,45 @@ COPY --from=builder /wheels/ /wheels/
 # Install the built wheel using pip; again using a wildcard if it's the only file
 RUN pip install *.whl /wheels/* --no-index --find-links=/wheels/ && rm -f *.whl && rm -rf /wheels
 
-# install semantic-cache [Experimental]- we need this here and not in requirements.txt because redisvl pins to pydantic 1.0 
+# install semantic-cache [Experimental]- we need this here and not in requirements.txt because redisvl pins to pydantic 1.0
 RUN pip install redisvl==0.0.7 --no-deps
 
 # ensure pyjwt is used, not jwt
-RUN pip uninstall jwt -y
-RUN pip uninstall PyJWT -y
-RUN pip install PyJWT==2.9.0 --no-cache-dir
+RUN pip uninstall jwt -y && \
+    pip uninstall PyJWT -y && \
+    pip install PyJWT==2.9.0 --no-cache-dir
 
 # Build Admin UI
 RUN chmod +x docker/build_admin_ui.sh && ./docker/build_admin_ui.sh
 
-# Generate prisma client
-ENV PRISMA_BINARY_CACHE_DIR=/app/prisma
-RUN mkdir -p /.cache
-RUN chmod -R 777 /.cache
-RUN pip install nodejs-bin
-RUN pip install prisma
-RUN prisma generate
+### Prisma Handling for Non-Root #################################################
+# Prisma allows you to specify the binary cache directory to use
+ENV PRISMA_BINARY_CACHE_DIR=/nonexistent
+
+# Set the TMPDIR environment variable, when this does not exist prisma raises "Error: ENOENT: no such file or directory, lstat '/var/folders'""
+ENV TMPDIR=/tmp
+RUN mkdir -p /tmp && chmod 1777 /tmp
+
+# Make a /non-existent folder and assign chown to nobody
+RUN mkdir -p /nonexistent && \
+    chown -R nobody:nogroup /nonexistent && \
+    chown -R nobody:nogroup /usr/local/lib/python3.11/site-packages/prisma/
+
 RUN chmod +x docker/entrypoint.sh
 
+# Run Prisma generate as user = nobody
+USER nobody
+
+RUN pip install --no-cache-dir nodejs-bin prisma
+RUN prisma generate
+### End of Prisma Handling for Non-Root #########################################
+
 EXPOSE 4000/tcp
 
 # # Set your entrypoint and command
 
 ENTRYPOINT ["litellm"]
 
-# Append "--detailed_debug" to the end of CMD to view detailed debug logs 
+# Append "--detailed_debug" to the end of CMD to view detailed debug logs
 # CMD ["--port", "4000", "--detailed_debug"]
 CMD ["--port", "4000"]

litellm/model_prices_and_context_window_backup.json

@@ -108,7 +108,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "o1-mini-2024-09-12": {
@@ -122,7 +122,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "o1-preview": {
@@ -136,7 +136,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "o1-preview-2024-09-12": {
@@ -150,7 +150,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "chatgpt-4o-latest": {
@@ -190,6 +190,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
         "supports_vision": true,
         "supports_prompt_caching": true
     },
@@ -461,6 +462,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
         "supports_vision": true
     },
     "ft:gpt-4o-mini-2024-07-18": {
@@ -652,7 +654,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "azure/o1-mini-2024-09-12": {
@@ -666,7 +668,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "azure/o1-preview": {
@@ -680,7 +682,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "azure/o1-preview-2024-09-12": {
@@ -694,7 +696,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true,
+        "supports_vision": false,
         "supports_prompt_caching": true
     },
     "azure/gpt-4o": {
@@ -721,6 +723,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
         "supports_vision": true
     },
     "azure/gpt-4o-2024-05-13": {
@@ -746,6 +749,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
+        "supports_response_schema": true,
         "supports_vision": true
     },
     "azure/global-standard/gpt-4o-mini": {
@@ -3790,7 +3794,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true
+        "supports_vision": false
     },
     "openrouter/openai/o1-mini-2024-09-12": {
         "max_tokens": 65536,
@@ -3802,7 +3806,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true
+        "supports_vision": false
     },
     "openrouter/openai/o1-preview": {
         "max_tokens": 32768,
@@ -3814,7 +3818,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true
+        "supports_vision": false
     },
     "openrouter/openai/o1-preview-2024-09-12": {
         "max_tokens": 32768,
@@ -3826,7 +3830,7 @@
         "mode": "chat",
         "supports_function_calling": true,
         "supports_parallel_function_calling": true,
-        "supports_vision": true
+        "supports_vision": false
     },
     "openrouter/openai/gpt-4o": {
         "max_tokens": 4096,