sync: import fork main changes onto upstream base

Author: gary149

.env

@@ -10,58 +10,27 @@ MONGODB_DB_NAME=chat-ui
 MONGODB_DIRECT_CONNECTION=false
 
 ### Local Storage ###
-MODELS_STORAGE_PATH= # where are .gguf for model inference stored
 MONGO_STORAGE_PATH= # where is the db folder stored
 
-### Endpoints config ###
+### Endpoints config (OpenAI-compatible only) ###
 HF_API_ROOT=https://api-inference.huggingface.co/models
-# HF_TOKEN is used for a lot of things, not only for inference but also fetching tokenizers, etc.
-# We recommend using an HF_TOKEN even if you use a local endpoint.
-HF_TOKEN= #get it from https://huggingface.co/settings/token
-# API Keys for providers, you will need to specify models in the MODELS section but these keys can be kept secret
-OPENAI_API_KEY=#your openai api key here
-ANTHROPIC_API_KEY=#your anthropic api key here
-CLOUDFLARE_ACCOUNT_ID=#your cloudflare account id here
-CLOUDFLARE_API_TOKEN=#your cloudflare api token here
-COHERE_API_TOKEN=#your cohere api token here
-GOOGLE_GENAI_API_KEY=#your google genai api token here
+# Canonical auth token for any OpenAI-compatible provider
+OPENAI_API_KEY=#your provider API key (works for HF router, OpenAI, LM Studio, etc.)
+# Legacy alias (still supported): if set and OPENAI_API_KEY is empty, it will be used
+HF_TOKEN=
+
+# If set, Chat UI will pull models exclusively from an OpenAI-compatible API,
+# calling `${OPENAI_BASE_URL}/models` and ignoring MODELS and GGUF discovery.
+# Example: https://router.huggingface.co/v1
+OPENAI_BASE_URL=
+
+# OPENAI_MODEL_LIST_URL has been removed.
 
 
 ### Models ###
-## Models can support many different endpoints, check the documentation for more details
-MODELS=`[
-    {
-      "name": "NousResearch/Hermes-3-Llama-3.1-8B",
-      "description": "Nous Research's latest Hermes 3 release in 8B size.",
-      "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?"
-        }
-      ]
-    }
-]`
-
-LOAD_GGUF_MODELS=true
-## Text Embedding Models used for websearch
-# Default is a model that runs locally on CPU.
-TEXT_EMBEDDING_MODELS = `[
-  {
-    "name": "Xenova/gte-small",
-    "displayName": "Xenova/gte-small",
-    "description": "Local embedding model running on the server.",
-    "chunkCharLength": 512,
-    "endpoints": [
-      { "type": "transformersjs" }
-    ]
-  }
-]`
+# Models are sourced exclusively from an OpenAI-compatible base URL.
+# See OPENAI_BASE_URL above.
+## Text Embedding Models (removed in this build)
 
 
 REASONING_SUMMARY=true # Change this to false to disable reasoning summary
@@ -70,11 +39,11 @@ REASONING_SUMMARY=true # Change this to false to disable reasoning summary
 OLD_MODELS=`[]`
 
 ## Task model
-# name of the model used for tasks such as summarizing title, creating query, etc.
-# if not set, the first model in MODELS will be used
+# Optional: set to the model id/name from the `${OPENAI_BASE_URL}/models` list
+# to use for internal tasks (title summarization, etc). If not set, the first
+# listed model will be used.
 TASK_MODEL=
 
-
 ### Authentication ###
 # Parameters to enable open id login
 OPENID_CONFIG=
@@ -98,23 +67,8 @@ ADMIN_CLI_LOGIN=true # set to false to disable the CLI login
 ADMIN_TOKEN=#We recommend leaving this empty, you can get the token from the terminal.
 
 
-### Websearch ###
-## API Keys used to activate search with web functionality. websearch is disabled if none are defined. choose one of the following:
-YDC_API_KEY=#your docs.you.com api key here
-SERPER_API_KEY=#your serper.dev api key here
-SERPAPI_KEY=#your serpapi key here
-SERPSTACK_API_KEY=#your serpstack api key here
-SEARCHAPI_KEY=#your searchapi api key here
-USE_LOCAL_WEBSEARCH=#set to true to parse google results yourself, overrides other API keys
-SEARXNG_QUERY_URL=# where '<query>' will be replaced with query keywords see https://docs.searxng.org/dev/search_api.html eg https://searxng.yourdomain.com/search?q=<query>&engines=duckduckgo,google&format=json
-BING_SUBSCRIPTION_KEY=#your key
-## Websearch configuration
-PLAYWRIGHT_ADBLOCKER=true
-WEBSEARCH_ALLOWLIST=`[]` # if it's defined, allow websites from only this list.
-WEBSEARCH_BLOCKLIST=`[]` # if it's defined, block websites from this list.
-WEBSEARCH_JAVASCRIPT=true # CPU usage reduces by 60% on average by disabling javascript. Enable to improve website compatibility
-WEBSEARCH_TIMEOUT = 3500 # in milliseconds, determines how long to wait to load a page before timing out
-ENABLE_LOCAL_FETCH=false #set to true to allow fetches on the local network. /!\ Only enable this if you have the proper firewall rules to prevent SSRF attacks and understand the implications.
+### Websearch (removed in this build)
+
 
 
 ## Public app configuration ##
@@ -125,13 +79,13 @@ PUBLIC_APP_DESCRIPTION=# description used throughout the app
 PUBLIC_APP_DATA_SHARING=# Set to 1 to enable an option in the user settings to share conversations with model authors
 PUBLIC_APP_DISCLAIMER=# Set to 1 to show a disclaimer on login page
 PUBLIC_APP_DISCLAIMER_MESSAGE=# Message to show on the login page
-PUBLIC_ANNOUNCEMENT_BANNERS=`[
-    {
-    "title": "chat-ui is now open source!",
-    "linkTitle": "check it out",
-    "linkHref": "https://github.com/huggingface/chat-ui"
-  }
-]`
+# PUBLIC_ANNOUNCEMENT_BANNERS=`[
+#     {
+#     "title": "chat-ui is now open source!",
+#     "linkTitle": "check it out",
+#     "linkHref": "https://github.com/huggingface/chat-ui"
+#   }
+# ]`
 PUBLIC_SMOOTH_UPDATES=false # set to true to enable smoothing of messages client-side, can be CPU intensive
 PUBLIC_ORIGIN=#https://huggingface.co
 PUBLIC_SHARE_PREFIX=#https://hf.co/chat
@@ -145,16 +99,12 @@ PUBLIC_APPLE_APP_ID=#1234567890 / Leave empty to disable
 ### Feature Flags ###
 LLM_SUMMARIZATION=true # generate conversation titles with LLMs
 ENABLE_ASSISTANTS=false #set to true to enable assistants feature
-ENABLE_ASSISTANTS_RAG=false # /!\ This will let users specify arbitrary URLs that the server will then request. Make sure you have the proper firewall rules in place. 
+ 
 REQUIRE_FEATURED_ASSISTANTS=false # require featured assistants to show in the list
 COMMUNITY_TOOLS=false # set to true to enable community tools
 ALLOW_IFRAME=true # Allow the app to be embedded in an iframe
 ENABLE_DATA_EXPORT=true
 
-### Tools ###
-# Check out public config in `chart/env/prod.yaml` for more details
-TOOLS=`[]` 
-
 ### Rate limits ### 
 # See `src/lib/server/usageLimits.ts`
 # {
@@ -169,19 +119,14 @@ USAGE_LIMITS=`{}`
 
 
 ### HuggingFace specific ###
-# Let user authenticate with their HF token in the /api routes. This is only useful if you have OAuth configured with huggingface.
-USE_HF_TOKEN_IN_API=false
 ## Feature flag & admin settings
 # Used for setting early access & admin flags to users
 HF_ORG_ADMIN=
 HF_ORG_EARLY_ACCESS=
 WEBHOOK_URL_REPORT_ASSISTANT=#provide slack webhook url to get notified for reports/feature requests
-IP_TOKEN_SECRET=
 
 
 ### Metrics ###
-METRICS_ENABLED=false
-METRICS_PORT=5565
 LOG_LEVEL=info
 
 
@@ -203,7 +148,6 @@ BODY_SIZE_LIMIT=15728640
 PUBLIC_COMMIT_SHA=
 
 ### LEGACY parameters
-HF_ACCESS_TOKEN=#LEGACY! Use HF_TOKEN instead
 ALLOW_INSECURE_COOKIES=false # LEGACY! Use COOKIE_SECURE and COOKIE_SAMESITE instead
 PARQUET_EXPORT_SECRET=#DEPRECATED, use ADMIN_API_SECRET instead
 RATE_LIMIT= # /!\ DEPRECATED definition of messages per minute. Use USAGE_LIMITS.messagesPerMinute instead

.gitattributes

@@ -0,0 +1,3 @@
+src/lib/server/fonts/*.ttf filter=lfs diff=lfs merge=lfs -text
+static/huggingchat/*.png filter=lfs diff=lfs merge=lfs -text
+static/fonts/*.ttf filter=lfs diff=lfs merge=lfs -text

Dockerfile

@@ -2,7 +2,6 @@
 ARG INCLUDE_DB=false
 
 FROM node:20-slim AS base
-ENV PLAYWRIGHT_SKIP_BROWSER_GC=1
 
 # install dotenv-cli
 RUN npm install -g dotenv-cli
@@ -21,7 +20,6 @@ WORKDIR /app
 RUN touch /app/.env.local
 
 
-RUN npm i --no-package-lock --no-save [email protected]
 
 USER root
 
@@ -31,9 +29,9 @@ RUN chown -R 1000:1000 /data/models
 RUN apt-get update
 RUN apt-get install gnupg curl git cmake clang libgomp1 -y
 
-RUN npx playwright install --with-deps chromium
 
-RUN chown -R 1000:1000 /home/user/.npm
+# ensure npm cache dir exists before adjusting ownership
+RUN mkdir -p /home/user/.npm && chown -R 1000:1000 /home/user/.npm
 
 USER user