resolved merge conflicts

.gitattributes

@@ -0,0 +1 @@
+*.sh text eol=lf

.github/workflows/docker-build.yaml

@@ -40,15 +40,21 @@ jobs:
           registry: ${{ env.REGISTRY }}
           username: ${{ github.actor }}
           password: ${{ secrets.GITHUB_TOKEN }}
-      # This step uses [docker/metadata-action](https://github.com/docker/metadata-action#about) to extract tags and labels that will be applied to the specified image. The `id` "meta" allows the output of this step to be referenced in a subsequent step. The `images` value provides the base name for the tags and labels.
-      - name: Extract metadata (tags, labels) for Docker
+
+      - name: Extract metadata for Docker images
         id: meta
         uses: docker/metadata-action@v5
         with:
           images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-      # This step uses the `docker/build-push-action` action to build the image, based on your repository's `Dockerfile`. If the build succeeds, it pushes the image to GitHub Packages.
-      # It uses the `context` parameter to define the build's context as the set of files located in the specified path. For more information, see "[Usage](https://github.com/docker/build-push-action#usage)" in the README of the `docker/build-push-action` repository.
-      # It uses the `tags` and `labels` parameters to tag and label the image with the output from the "meta" step.
+          # This configuration dynamically generates tags based on the branch, tag, commit, and custom suffix for lite version.
+          tags: |
+            type=ref,event=branch
+            type=ref,event=tag
+            type=sha,prefix=git-
+            type=semver,pattern={{version}}
+          flavor: |
+            latest=${{ github.ref == 'refs/heads/main' }}
+
       - name: Build and push Docker image
         uses: docker/build-push-action@v5
         with:

Dockerfile

@@ -25,7 +25,28 @@ ENV OLLAMA_API_BASE_URL "/ollama/api"
 ENV OPENAI_API_BASE_URL ""
 ENV OPENAI_API_KEY ""
 
-ENV WEBUI_JWT_SECRET_KEY "SECRET_KEY"
+ENV WEBUI_SECRET_KEY ""
+
+ENV SCARF_NO_ANALYTICS true
+ENV DO_NOT_TRACK true
+
+######## Preloaded models ########
+# whisper TTS Settings
+ENV WHISPER_MODEL="base"
+ENV WHISPER_MODEL_DIR="/app/backend/data/cache/whisper/models"
+
+# RAG Embedding Model Settings
+# any sentence transformer model; models to use can be found at https://huggingface.co/models?library=sentence-transformers
+# Leaderboard: https://huggingface.co/spaces/mteb/leaderboard 
+# for better persormance and multilangauge support use "intfloat/multilingual-e5-large" (~2.5GB) or "intfloat/multilingual-e5-base" (~1.5GB)
+# IMPORTANT: If you change the default model (all-MiniLM-L6-v2) and vice versa, you aren't able to use RAG Chat with your previous documents loaded in the WebUI! You need to re-embed them.
+ENV RAG_EMBEDDING_MODEL="all-MiniLM-L6-v2"
+# device type for whisper tts and ebbeding models - "cpu" (default), "cuda" (nvidia gpu and CUDA required) or "mps" (apple silicon) - choosing this right can lead to better performance
+ENV RAG_EMBEDDING_MODEL_DEVICE_TYPE="cpu"
+ENV RAG_EMBEDDING_MODEL_DIR="/app/backend/data/cache/embedding/models"
+ENV SENTENCE_TRANSFORMERS_HOME $RAG_EMBEDDING_MODEL_DIR
+
+######## Preloaded models ########
 
 WORKDIR /app/backend
 
@@ -41,7 +62,10 @@ RUN apt-get update \
     && apt-get install -y pandoc netcat-openbsd \
     && rm -rf /var/lib/apt/lists/*
 
-# RUN python -c "from sentence_transformers import SentenceTransformer; model = SentenceTransformer('all-MiniLM-L6-v2')"
+# preload embedding model
+RUN python -c "import os; from chromadb.utils import embedding_functions; sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name=os.environ['RAG_EMBEDDING_MODEL'], device=os.environ['RAG_EMBEDDING_MODEL_DEVICE_TYPE'])"
+# preload tts model
+RUN python -c "import os; from faster_whisper import WhisperModel; WhisperModel(os.environ['WHISPER_MODEL'], device='auto', compute_type='int8', download_root=os.environ['WHISPER_MODEL_DIR'])"
 
 # copy embedding weight from build
 RUN mkdir -p /root/.cache/chroma/onnx_models/all-MiniLM-L6-v2

INSTALLATION.md

@@ -1,4 +1,4 @@
-### Installing Both Ollama and Ollama Web UI Using Kustomize
+### Installing Both Ollama and Open WebUI Using Kustomize
 
 For cpu-only pod
 
@@ -12,7 +12,7 @@ For gpu-enabled pod
 kubectl apply -k ./kubernetes/manifest
 ```
 
-### Installing Both Ollama and Ollama Web UI Using Helm
+### Installing Both Ollama and Open WebUI Using Helm
 
 Package Helm file first
 

TROUBLESHOOTING.md

@@ -1,32 +1,32 @@
-# Ollama Web UI Troubleshooting Guide
+# Open WebUI Troubleshooting Guide
 
-## Understanding the Ollama WebUI Architecture
+## Understanding the Open WebUI Architecture
 
-The Ollama WebUI system is designed to streamline interactions between the client (your browser) and the Ollama API. At the heart of this design is a backend reverse proxy, enhancing security and resolving CORS issues.
+The Open WebUI system is designed to streamline interactions between the client (your browser) and the Ollama API. At the heart of this design is a backend reverse proxy, enhancing security and resolving CORS issues.
 
-- **How it Works**: The Ollama WebUI is designed to interact with the Ollama API through a specific route. When a request is made from the WebUI to Ollama, it is not directly sent to the Ollama API. Initially, the request is sent to the Ollama WebUI backend via `/ollama/api` route. From there, the backend is responsible for forwarding the request to the Ollama API. This forwarding is accomplished by using the route specified in the `OLLAMA_API_BASE_URL` environment variable. Therefore, a request made to `/ollama/api` in the WebUI is effectively the same as making a request to `OLLAMA_API_BASE_URL` in the backend. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend.
+- **How it Works**: The Open WebUI is designed to interact with the Ollama API through a specific route. When a request is made from the WebUI to Ollama, it is not directly sent to the Ollama API. Initially, the request is sent to the Open WebUI backend via `/ollama/api` route. From there, the backend is responsible for forwarding the request to the Ollama API. This forwarding is accomplished by using the route specified in the `OLLAMA_API_BASE_URL` environment variable. Therefore, a request made to `/ollama/api` in the WebUI is effectively the same as making a request to `OLLAMA_API_BASE_URL` in the backend. For instance, a request to `/ollama/api/tags` in the WebUI is equivalent to `OLLAMA_API_BASE_URL/tags` in the backend.
 
 - **Security Benefits**: This design prevents direct exposure of the Ollama API to the frontend, safeguarding against potential CORS (Cross-Origin Resource Sharing) issues and unauthorized access. Requiring authentication to access the Ollama API further enhances this security layer.
 
-## Ollama WebUI: Server Connection Error
+## Open WebUI: Server Connection Error
 
 If you're experiencing connection issues, it’s often due to the WebUI docker container not being able to reach the Ollama server at 127.0.0.1:11434 (host.docker.internal:11434) inside the container . Use the `--network=host` flag in your docker command to resolve this. Note that the port changes from 3000 to 8080, resulting in the link: `http://localhost:8080`.
 
 **Example Docker Command**:
 
 ```bash
-docker run -d --network=host -v ollama-webui:/app/backend/data -e OLLAMA_API_BASE_URL=http://127.0.0.1:11434/api --name ollama-webui --restart always ghcr.io/ollama-webui/ollama-webui:main
+docker run -d --network=host -v open-webui:/app/backend/data -e OLLAMA_API_BASE_URL=http://127.0.0.1:11434/api --name open-webui --restart always ghcr.io/open-webui/open-webui:main
 ```
 
 ### General Connection Errors
 
-**Ensure Ollama Version is Up-to-Date**: Always start by checking that you have the latest version of Ollama. Visit [Ollama's official site](https://ollama.ai/) for the latest updates.
+**Ensure Ollama Version is Up-to-Date**: Always start by checking that you have the latest version of Ollama. Visit [Ollama's official site](https://ollama.com/) for the latest updates.
 
 **Troubleshooting Steps**:
 
 1. **Verify Ollama URL Format**:
    - When running the Web UI container, ensure the `OLLAMA_API_BASE_URL` is correctly set, including the `/api` suffix. (e.g., `http://192.168.1.1:11434/api` for different host setups).
-   - In the Ollama WebUI, navigate to "Settings" > "General".
+   - In the Open WebUI, navigate to "Settings" > "General".
    - Confirm that the Ollama Server URL is correctly set to `[OLLAMA URL]/api` (e.g., `http://localhost:11434/api`), including the `/api` suffix.
 
 By following these enhanced troubleshooting steps, connection issues should be effectively resolved. For further assistance or queries, feel free to reach out to us on our community Discord.

backend/.gitignore

@@ -6,4 +6,6 @@ uploads
 *.db
 _test
 Pipfile
-data/*
+data/*
+!data/config.json
+.webui_secret_key

backend/apps/audio/main.py

@@ -0,0 +1,80 @@
+import os
+from fastapi import (
+    FastAPI,
+    Request,
+    Depends,
+    HTTPException,
+    status,
+    UploadFile,
+    File,
+    Form,
+)
+from fastapi.middleware.cors import CORSMiddleware
+from faster_whisper import WhisperModel
+
+from constants import ERROR_MESSAGES
+from utils.utils import (
+    decode_token,
+    get_current_user,
+    get_verified_user,
+    get_admin_user,
+)
+from utils.misc import calculate_sha256
+
+from config import CACHE_DIR, UPLOAD_DIR, WHISPER_MODEL, WHISPER_MODEL_DIR
+
+app = FastAPI()
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=["*"],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+
+@app.post("/transcribe")
+def transcribe(
+    file: UploadFile = File(...),
+    user=Depends(get_current_user),
+):
+    print(file.content_type)
+
+    if file.content_type not in ["audio/mpeg", "audio/wav"]:
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.FILE_NOT_SUPPORTED,
+        )
+
+    try:
+        filename = file.filename
+        file_path = f"{UPLOAD_DIR}/{filename}"
+        contents = file.file.read()
+        with open(file_path, "wb") as f:
+            f.write(contents)
+            f.close()
+
+        model = WhisperModel(
+            WHISPER_MODEL,
+            device="auto",
+            compute_type="int8",
+            download_root=WHISPER_MODEL_DIR,
+        )
+
+        segments, info = model.transcribe(file_path, beam_size=5)
+        print(
+            "Detected language '%s' with probability %f"
+            % (info.language, info.language_probability)
+        )
+
+        transcript = "".join([segment.text for segment in list(segments)])
+
+        return {"text": transcript.strip()}
+
+    except Exception as e:
+        print(e)
+
+        raise HTTPException(
+            status_code=status.HTTP_400_BAD_REQUEST,
+            detail=ERROR_MESSAGES.DEFAULT(e),
+        )

backend/apps/ollama/main.py

@@ -1,4 +1,4 @@
-from fastapi import FastAPI, Request, Response, HTTPException, Depends
+from fastapi import FastAPI, Request, Response, HTTPException, Depends, status
 from fastapi.middleware.cors import CORSMiddleware
 from fastapi.responses import StreamingResponse
 from fastapi.concurrency import run_in_threadpool
@@ -10,7 +10,7 @@
 
 from apps.web.models.users import Users
 from constants import ERROR_MESSAGES
-from utils.utils import decode_token, get_current_user
+from utils.utils import decode_token, get_current_user, get_admin_user
 from config import OLLAMA_API_BASE_URL, WEBUI_AUTH
 
 app = FastAPI()
@@ -31,26 +31,18 @@
 
 
 @app.get("/url")
-async def get_ollama_api_url(user=Depends(get_current_user)):
-    if user and user.role == "admin":
-        return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
-    else:
-        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+async def get_ollama_api_url(user=Depends(get_admin_user)):
+    return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
 
 
 class UrlUpdateForm(BaseModel):
     url: str
 
 
 @app.post("/url/update")
-async def update_ollama_api_url(
-    form_data: UrlUpdateForm, user=Depends(get_current_user)
-):
-    if user and user.role == "admin":
-        app.state.OLLAMA_API_BASE_URL = form_data.url
-        return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
-    else:
-        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+async def update_ollama_api_url(form_data: UrlUpdateForm, user=Depends(get_admin_user)):
+    app.state.OLLAMA_API_BASE_URL = form_data.url
+    return {"OLLAMA_API_BASE_URL": app.state.OLLAMA_API_BASE_URL}
 
 
 @app.get("/cancel/{request_id}")
@@ -74,10 +66,14 @@ async def proxy(path: str, request: Request, user=Depends(get_current_user)):
         if path in ["pull", "delete", "push", "copy", "create"]:
             if user.role != "admin":
                 raise HTTPException(
-                    status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED
+                    status_code=status.HTTP_401_UNAUTHORIZED,
+                    detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
                 )
     else:
-        raise HTTPException(status_code=401, detail=ERROR_MESSAGES.ACCESS_PROHIBITED)
+        raise HTTPException(
+            status_code=status.HTTP_401_UNAUTHORIZED,
+            detail=ERROR_MESSAGES.ACCESS_PROHIBITED,
+        )
 
     headers.pop("host", None)
     headers.pop("authorization", None)
@@ -132,7 +128,7 @@ def stream_content():
     try:
         return await run_in_threadpool(get_request)
     except Exception as e:
-        error_detail = "Ollama WebUI: Server Connection Error"
+        error_detail = "Open WebUI: Server Connection Error"
         if r is not None:
             try:
                 res = r.json()

backend/apps/ollama/old_main.py

@@ -61,7 +61,7 @@ async def update_ollama_api_url(
 #                     yield line
 #         except Exception as e:
 #             print(e)
-#             error_detail = "Ollama WebUI: Server Connection Error"
+#             error_detail = "Open WebUI: Server Connection Error"
 #             yield json.dumps({"error": error_detail, "message": str(e)}).encode()
 
 
@@ -110,7 +110,7 @@ async def generate():
 
     except Exception as e:
         print(e)
-        error_detail = "Ollama WebUI: Server Connection Error"
+        error_detail = "Open WebUI: Server Connection Error"
 
         if response is not None:
             try: