Clean up Dockerfile and prod environment config

Dockerfile

@@ -19,16 +19,9 @@ WORKDIR /app
 # add a .env.local if the user doesn't bind a volume to it
 RUN touch /app/.env.local
 
-
-
 USER root
-
-RUN mkdir -p /data/models
-RUN chown -R 1000:1000 /data/models
-
 RUN apt-get update
-RUN apt-get install gnupg curl git cmake clang libgomp1 -y
-
+RUN apt-get install -y libgomp1
 
 # ensure npm cache dir exists before adjusting ownership
 RUN mkdir -p /home/user/.npm && chown -R 1000:1000 /home/user/.npm
@@ -38,7 +31,6 @@ USER user
 
 COPY --chown=1000 .env /app/.env
 COPY --chown=1000 entrypoint.sh /app/entrypoint.sh
-COPY --chown=1000 gcp-*.json /app/
 COPY --chown=1000 package.json /app/package.json
 COPY --chown=1000 package-lock.json /app/package-lock.json
 
@@ -94,7 +86,6 @@ ARG PUBLIC_APP_COLOR=blue
 ARG PUBLIC_COMMIT_SHA=
 ENV PUBLIC_COMMIT_SHA=${PUBLIC_COMMIT_SHA}
 ENV BODY_SIZE_LIMIT=15728640
-ENV MODELS_STORAGE_PATH=/data/models
 
 #import the build & dependencies
 COPY --from=builder --chown=1000 /app/build /app/build

chart/env/prod.yaml

@@ -42,7 +42,6 @@ ingressInternal:
     kubernetes.io/ingress.class: "alb"
 
 envVars:
-  ADDRESS_HEADER: 'X-Forwarded-For'
   ADMIN_CLI_LOGIN: "false"
   ALTERNATIVE_REDIRECT_URLS: '["huggingchat://login/callback"]'
   APP_BASE: "/chat"
@@ -53,408 +52,6 @@ envVars:
   ENABLE_ASSISTANTS: "true"
   ENABLE_CONFIG_MANAGER: "false"
   LOG_LEVEL: "debug"
-  MODELS: >
-    [
-      {
-        "name": "meta-llama/Llama-3.3-70B-Instruct",
-        "id": "meta-llama/Llama-3.3-70B-Instruct",
-        "description": "Ideal for everyday use. A fast and extremely capable model matching closed source models' capabilities. Now with the latest Llama 3.3 weights!",
-        "modelUrl": "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct",
-        "websiteUrl": "https://llama.meta.com/",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/meta-logo.png",
-        "tools": true,
-        "preprompt": "",
-        "parameters": {
-          "stop": ["<|endoftext|>", "<|eot_id|>"],
-          "temperature": 0.6,
-          "max_new_tokens": 1024,
-          "truncate": 7167
-        },
-        "endpoints": [{"type" : "inference-client"}],
-        "promptExamples": [
-          {
-            "title": "Write an email",
-            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
-          },
-          {
-            "title": "Code a game",
-            "prompt": "Code a basic snake game in python, give explanations for each step."
-          },
-          {
-            "title": "Recipe help",
-            "prompt": "How do I make a delicious lemon cheesecake?"
-          }
-        ]
-      },
-      {
-        "name": "Qwen/Qwen3-235B-A22B",
-        "description": "Qwen's flagship model featuring optional reasoning. Exceptional performance with benchmarks rivaling R1 and o1.",
-        "modelUrl": "https://huggingface.co/Qwen/Qwen3-235B-A22B",
-        "websiteUrl": "https://qwenlm.github.io/blog/qwen3/",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
-        "preprompt": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant.",
-        "reasoning": {
-          "type": "tokens",
-          "beginToken": "<think>",
-          "endToken": "</think>"
-        },
-        "parameters": {
-          "stop": ["<|endoftext|>", "<|im_end|>"],
-          "temperature": 0.6,
-        },
-        "tools": true,
-        "promptExamples": [
-          {
-            "title": "Write an email",
-            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12) /nothink"
-          },
-          {
-            "title": "Build a website",
-            "prompt": "Generate a snazzy static landing page for a local coffee shop using HTML and CSS. You can use tailwind using <script src='https://cdn.tailwindcss.com'></script>."
-          },
-          {
-            "title": "Larger number",
-            "prompt": "9.11 or 9.9 which number is larger?"
-          },
-        ],
-        "endpoints": [
-          {
-            "type": "inference-client",
-            "baseURL": "https://api-inference.endpoints.huggingface.tech/models/Qwen/Qwen3-235B-A22B/v1"
-          }
-        ]
-      },
-      {
-        "name": "Qwen/Qwen2.5-72B-Instruct",
-        "description": "The latest Qwen open model with improved role-playing, long text generation and structured data understanding.",
-        "modelUrl": "https://huggingface.co/Qwen/Qwen2.5-72B-Instruct",
-        "websiteUrl": "https://qwenlm.github.io/blog/qwen2.5/",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
-        "preprompt": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant.",
-        "parameters": {
-          "stop": ["<|endoftext|>", "<|im_end|>"],
-          "temperature": 0.6,
-          "truncate": 28672,
-          "max_new_tokens": 3072
-        },
-        "tools": true,
-        "endpoints": [{"type" : "inference-client"}],
-        "promptExamples": [
-          {
-            "title": "Write an email",
-            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
-          },
-          {
-            "title": "Code a game",
-            "prompt": "Code a basic snake game in python, give explanations for each step."
-          },
-          {
-            "title": "Recipe help",
-            "prompt": "How do I make a delicious lemon cheesecake?"
-          }
-        ]
-      },
-      {
-        "name": "CohereLabs/c4ai-command-r-plus-08-2024",
-        "description": "Cohere's largest language model, optimized for conversational interaction and tool use. Now with the 2024 update!",
-        "modelUrl": "https://huggingface.co/CohereLabs/c4ai-command-r-plus-08-2024",
-        "websiteUrl": "https://docs.cohere.com/docs/command-r-plus",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/cohere-logo.png",
-        "tools": true,
-        "systemRoleSupported": false,
-        "parameters": {
-          "stop": ["<|END_OF_TURN_TOKEN|>", "<|im_end|>"],
-          "truncate": 28672,
-          "max_new_tokens": 2048,
-          "temperature": 0.3
-        },
-        "endpoints": [{"type" : "inference-client"}],
-        "promptExamples": [
-          {
-            "title": "Generate image",
-            "prompt": "Generate the portrait of a scientific mouse in its laboratory."
-          },
-          {
-            "title": "Review code",
-            "prompt": "Review this pull request: https://github.com/huggingface/chat-ui/pull/1131/files"
-          },
-          {
-            "title": "Code a game",
-            "prompt": "Code a basic snake game in python, give explanations for each step."
-          }
-        ]
-      },
-      {
-        "name": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
-        "modelUrl": "https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
-        "websiteUrl": "https://deepseek.com/",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/deepseek-logo.png",
-        "description": "The first reasoning model from DeepSeek, distilled into a 32B dense model. Outperforms o1-mini on multiple benchmarks.",
-        "reasoning": {
-          "type": "tokens",
-          "beginToken": "",
-          "endToken": "</think>"
-        },
-        "tools": true,
-        "promptExamples": [
-          {
-            "title": "Rs in strawberry",
-            "prompt": "how many R in strawberry?"
-          },
-          {
-            "title": "Larger number",
-            "prompt": "9.11 or 9.9 which number is larger?"
-          },
-          {
-            "title": "Measuring 6 liters",
-            "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
-          }
-        ],
-        "endpoints": [
-          {
-            "type": "inference-client",
-            "baseURL": "https://b8xf586h164t4vk7.us-east-1.aws.endpoints.huggingface.cloud/v1"
-          }
-        ]
-      },
-      {
-        "name": "nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
-        "modelUrl": "https://huggingface.co/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF",
-        "websiteUrl": "https://www.nvidia.com/",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nvidia-logo.png",
-        "description": "Nvidia's latest Llama fine-tune, topping alignment benchmarks and optimized for instruction following.",
-        "parameters": {
-          "stop": ["<|eot_id|>", "<|im_end|>"],
-          "temperature": 0.5,
-          "truncate": 28672,
-          "max_new_tokens": 2048
-        },
-        "promptExamples": [
-          {
-            "title": "Rs in strawberry",
-            "prompt": "how many R in strawberry?"
-          },
-          {
-            "title": "Larger number",
-            "prompt": "9.11 or 9.9 which number is larger?"
-          },
-          {
-            "title": "Measuring 6 liters",
-            "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
-          }
-        ],
-        "endpoints": [
-          {
-            "type": "inference-client",
-            "baseURL": "https://api-inference.endpoints.huggingface.tech/models/nvidia/Llama-3.1-Nemotron-70B-Instruct-HF/v1"
-          }
-        ]
-      },
-      {
-        "name": "Qwen/QwQ-32B",
-        "tools": true,
-        "preprompt": "You are a helpful and harmless assistant. You are Qwen developed by Alibaba. You should think step-by-step.",
-        "modelUrl": "https://huggingface.co/Qwen/QwQ-32B",
-        "websiteUrl": "https://qwenlm.github.io/blog/qwq-32b/",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
-        "description": "QwQ is the latest reasoning model released by the Qwen team, approaching the capabilities of R1 in benchmarks.",
-        "reasoning": {
-          "type": "tokens",
-          "beginToken": "",
-          "endToken": "</think>"
-        },
-        "promptExamples": [
-          {
-            "title": "Rs in strawberry",
-            "prompt": "how many R in strawberry?"
-          },
-          {
-            "title": "Larger number",
-            "prompt": "9.11 or 9.9 which number is larger?"
-          },
-          {
-            "title": "Measuring 6 liters",
-            "prompt": "I have a 6- and a 12-liter jug. I want to measure exactly 6 liters."
-          }
-        ],
-        "endpoints": [
-          {
-            "type": "inference-client",
-          }
-        ]
-      },
-      {
-        "name": "google/gemma-3-27b-it",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/google-logo.png",
-        "multimodal": true,
-        "tools": true,
-        "systemRoleSupported" : false,
-        "description": "Google's latest open model with great multilingual performance, supports image inputs natively.",
-        "websiteUrl": "https://blog.google/technology/developers/gemma-3/",
-        "promptExamples": [
-          {
-            "title": "Write an email",
-            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
-          },
-          {
-            "title": "Code a game",
-            "prompt": "Code a basic snake game in python, give explanations for each step."
-          },
-          {
-            "title": "Recipe help",
-            "prompt": "How do I make a delicious lemon cheesecake?"
-          }
-        ],
-        "endpoints": [
-          {
-            "type": "inference-client",
-            "baseURL": "https://wp0d3hn6s3k8jk22.us-east-1.aws.endpoints.huggingface.cloud/v1",
-            "multimodal": {
-              "image": {
-                "maxSizeInMB": 10,
-                "maxWidth": 560,
-                "maxHeight": 560,
-                "supportedMimeTypes": ["image/jpeg", "image/png", "image/webp"],
-                "preferredMimeType": "image/webp"
-              }
-            }
-          }
-        ]
-      },
-      {
-        "name": "mistralai/Mistral-Small-3.1-24B-Instruct-2503",
-        "tools": true,
-        "displayName": "mistralai/Mistral-Small-3.1-24B-Instruct-2503",
-        "description": "A small model with good capabilities in language understanding and commonsense reasoning.",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/mistral-logo.png",
-        "websiteUrl": "https://mistral.ai/news/mistral-nemo/",
-        "modelUrl": "https://huggingface.co/mistralai/Mistral-Small-3.1-24B-Instruct-2503",
-        "preprompt": "",
-        "promptExamples": [
-          {
-            "title": "Write an email",
-            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
-          },
-          {
-            "title": "Code a game",
-            "prompt": "Code a basic snake game in python, give explanations for each step."
-          },
-          {
-            "title": "Recipe help",
-            "prompt": "How do I make a delicious lemon cheesecake?"
-          }
-        ],
-
-        "endpoints": [
-          {
-            "type": "inference-client",
-              "baseURL": "https://hkjfqcryevvq9cie.us-east-1.aws.endpoints.huggingface.cloud/v1"
-          }
-        ]
-      },
-      {
-        "name": "Qwen/Qwen2.5-VL-32B-Instruct",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/qwen-logo.png",
-        "description": "The latest multimodal model from Qwen! Supports image inputs natively.",
-        "websiteUrl": "https://qwenlm.github.io/blog/qwen2.5-vl/",
-        "modelUrl": "https://huggingface.co/Qwen/Qwen2.5-VL-32B-Instruct",
-        "multimodal": true,
-        "promptExamples": [
-          {
-            "title": "Write an email",
-            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
-          },
-          {
-            "title": "Code a game",
-            "prompt": "Code a basic snake game in python, give explanations for each step."
-          },
-          {
-            "title": "Recipe help",
-            "prompt": "How do I make a delicious lemon cheesecake?"
-          }
-        ],
-        "endpoints": [
-          {
-            "type": "inference-client",
-            "multimodal": {
-              "image": {
-                "maxSizeInMB": 10,
-                "maxWidth": 1024,
-                "maxHeight": 1024,
-                "supportedMimeTypes": ["image/png", "image/jpeg", "image/webp"],
-                "preferredMimeType": "image/webp"
-              }
-            }
-          }
-        ]
-      },
-      {
-        "name": "microsoft/Phi-4",
-        "tools": true,
-        "systemRoleSupported": false,
-        "description": "One of the best small models, super fast for simple tasks.",
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/microsoft-logo.png",
-        "modelUrl": "https://huggingface.co/microsoft/Phi-4",
-        "websiteUrl": "https://techcommunity.microsoft.com/blog/aiplatformblog/introducing-phi-4-microsoft%E2%80%99s-newest-small-language-model-specializing-in-comple/4357090",
-        "preprompt": "",
-        "parameters": {
-          "stop": ["<|end|>", "<|endoftext|>", "<|assistant|>"],
-          "temperature": 0.6,
-          "truncate": 28672,
-          "max_new_tokens": 3072
-        },
-        "promptExamples": [
-          {
-            "title": "Write an email",
-            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
-          },
-          {
-            "title": "Code a game",
-            "prompt": "Code a basic snake game in python, give explanations for each step."
-          },
-          {
-            "title": "Recipe help",
-            "prompt": "How do I make a delicious lemon cheesecake?"
-          }
-        ],
-        "endpoints": [
-          {
-            "type": "inference-client",
-            "baseURL": "https://up5ijetg6a2e9zlb.us-east-1.aws.endpoints.huggingface.cloud/v1"
-          }
-        ]
-      },
-      {
-        "name": "NousResearch/Hermes-3-Llama-3.1-8B",
-        "description": "Nous Research's latest Hermes 3 release in 8B size. Follows instruction closely.",
-        "tools": true,
-        "logoUrl": "https://huggingface.co/datasets/huggingchat/models-logo/resolve/main/nous-logo.png",
-        "websiteUrl": "https://nousresearch.com/",
-        "modelUrl": "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-8B",
-        "promptExamples": [
-          {
-            "title": "Write an email",
-            "prompt": "As a restaurant owner, write a professional email to the supplier to get these products every week: \n\n- Wine (x10)\n- Eggs (x24)\n- Bread (x12)"
-          },
-          {
-            "title": "Code a game",
-            "prompt": "Code a basic snake game in python, give explanations for each step."
-          },
-          {
-            "title": "Recipe help",
-            "prompt": "How do I make a delicious lemon cheesecake?"
-          }
-        ],
-        "parameters": {
-          "stop": ["<|im_end|>"],
-          "temperature": 0.6,
-          "truncate": 14336,
-          "max_new_tokens": 1536
-        },
-        "endpoints": [{"type" : "inference-client"}]
-      }
-    ]
-
   NODE_ENV: "prod"
   NODE_LOG_STRUCTURED_DATA: true
   OLD_MODELS: >
@@ -542,7 +139,6 @@ envVars:
   PUBLIC_APP_GUEST_MESSAGE: "Sign in with a free Hugging Face account to continue using HuggingChat."
   PUBLIC_APP_DATA_SHARING: 0
   PUBLIC_PLAUSIBLE_SCRIPT_URL: "/js/script.js"
-  REQUIRE_FEATURED_ASSISTANTS: "true"
   TASK_MODEL: >
         {
         "name": "NousResearch/Hermes-3-Llama-3.1-8B",
@@ -555,147 +151,8 @@ envVars:
         }
 
 
-  TEXT_EMBEDDING_MODELS: >
-    [{
-      "name": "bge-base-en-v1-5-sxa",
-      "displayName": "bge-base-en-v1-5-sxa",
-      "chunkCharLength": 512,
-      "endpoints": [{
-        "type": "tei",
-        "url": "https://huggingchat-tei.hf.space/"
-      }]
-    }]
-  WEBSEARCH_BLOCKLIST: '["youtube.com", "twitter.com"]'
-  XFF_DEPTH: '2'
-  TOOLS: >
-    [
-      {
-        "_id": "000000000000000000000001",
-        "displayName": "Image Generation",
-        "description": "Use this tool to generate images based on a prompt.",
-        "color": "yellow",
-        "icon": "camera",
-        "baseUrl": "black-forest-labs/FLUX.1-schnell",
-        "name": "image_generation",
-        "endpoint": "/infer",
-        "inputs": [
-          {
-            "name": "prompt",
-            "description": "A prompt to generate an image from",
-            "paramType": "required",
-            "type": "str"
-          },
-          { "name": "seed", "paramType": "fixed", "value": "0", "type": "float" },
-          {
-            "name": "randomize_seed",
-            "paramType": "fixed",
-            "value": "true",
-            "type": "bool"
-          },
-          {
-            "name": "width",
-            "description": "numeric value between 256 and 2048",
-            "paramType": "optional",
-            "default": 1024,
-            "type": "float"
-          },
-          {
-            "name": "height",
-            "description": "numeric value between 256 and 2048",
-            "paramType": "optional",
-            "default": 1024,
-            "type": "float"
-          },
-          {
-            "name": "num_inference_steps",
-            "paramType": "fixed",
-            "value": "4",
-            "type": "float"
-          }
-        ],
-        "outputComponent": "image",
-        "outputComponentIdx": 0,
-        "showOutput": true
-      },
-      {
-        "_id": "000000000000000000000002",
-        "displayName": "Document Parser",
-        "description": "Use this tool to parse any document and get its content in markdown format.",
-        "color": "yellow",
-        "icon": "cloud",
-        "baseUrl": "huggingchat/document-parser",
-        "name": "document_parser",
-        "endpoint": "/predict",
-        "inputs": [
-          {
-            "name": "document",
-            "description": "Filename of the document to parse",
-            "paramType": "required",
-            "type": "file",
-            "mimeTypes": 'application/*'
-          },
-          {
-            "name": "filename",
-            "paramType": "fixed",
-            "value": "document.pdf",
-            "type": "str"
-          }
-        ],
-        "outputComponent": "textbox",
-        "outputComponentIdx": 0,
-        "showOutput": false,
-        "isHidden": true
-      },
-      {
-        "_id": "000000000000000000000003",
-        "name": "edit_image",
-        "baseUrl": "multimodalart/cosxl",
-        "endpoint": "/run_edit",
-        "inputs": [
-          {
-            "name": "image",
-            "description": "The image path to be edited",
-            "paramType": "required",
-            "type": "file",
-            "mimeTypes": 'image/*'
-          },
-          {
-            "name": "prompt",
-            "description": "The prompt with which to edit the image",
-            "paramType": "required",
-            "type": "str"
-          },
-          {
-            "name": "negative_prompt",
-            "paramType": "fixed",
-            "value": "",
-            "type": "str"
-          },
-          {
-            "name": "guidance_scale",
-            "paramType": "fixed",
-            "value": 6.5,
-            "type": "float"
-          },
-          {
-            "name": "steps",
-            "paramType": "fixed",
-            "value": 30,
-            "type": "float"
-          }
-        ],
-        "outputComponent": "image",
-        "showOutput": true,
-        "displayName": "Image Editor",
-        "color": "green",
-        "icon": "camera",
-        "description": "This tool lets you edit images",
-        "outputComponentIdx": 0
-      }
-    ]
   HF_ORG_ADMIN: '644171cfbd0c97265298aa99'
   HF_ORG_EARLY_ACCESS: '5e67bd5b1009063689407478'
-  HF_API_ROOT: 'https://api-inference.endpoints.huggingface.tech/models'
 infisical:
   enabled: true
   env: "prod-us-east-1"
@@ -714,6 +171,3 @@ resources:
   limits:
     cpu: 4
     memory: 8Gi
-
-monitoring:
-  enabled: true