diff --git a/.docker/router.yml b/.docker/router.yml
new file mode 100644
index 00000000..3b55df9e
--- /dev/null
+++ b/.docker/router.yml
@@ -0,0 +1,16 @@
+http:
+  services:
+    ollama:
+      loadBalancer:
+        healthCheck:
+          interval: 5s
+          path: /
+        servers:
+          - url: http://ollama-cpu:11434
+          - url: http://ollama-cuda:11434
+          - url: http://host.docker.internal:11434
+
+  routers:
+    ollama-router:
+      rule: "PathPrefix(`/`)"
+      service: ollama
\ No newline at end of file
diff --git a/.github/release_please/.release-please-config.json b/.github/release_please/.release-please-config.json
new file mode 100644
index 00000000..97f31700
--- /dev/null
+++ b/.github/release_please/.release-please-config.json
@@ -0,0 +1,19 @@
+{
+    "$schema": "https://raw.githubusercontent.com/googleapis/release-please/main/schemas/config.json",
+    "release-type": "simple",
+    "version-file": "version.txt",
+    "extra-files": [
+      {
+        "type": "toml",
+        "path": "pyproject.toml",
+        "jsonpath": "$.tool.poetry.version"
+      },
+      {
+        "type": "generic",
+        "path": "docker-compose.yaml"
+      }
+    ],
+    "packages": {
+      ".": {}
+    }
+  }
\ No newline at end of file
diff --git a/.github/release_please/.release-please-manifest.json b/.github/release_please/.release-please-manifest.json
new file mode 100644
index 00000000..e3778b2c
--- /dev/null
+++ b/.github/release_please/.release-please-manifest.json
@@ -0,0 +1,3 @@
+{
+  ".": "0.6.2"
+}
\ No newline at end of file
diff --git a/.github/workflows/docker.yml b/.github/workflows/docker.yml
deleted file mode 100644
index 259cf5da..00000000
--- a/.github/workflows/docker.yml
+++ /dev/null
@@ -1,45 +0,0 @@
-name: docker
-
-on:
-  release:
-    types: [ published ]
-  workflow_dispatch:
-
-env:
-  REGISTRY: ghcr.io
-  IMAGE_NAME: ${{ github.repository }}
-
-jobs:
-  build-and-push-image:
-    runs-on: ubuntu-latest
-    permissions:
-      contents: read
-      packages: write
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@v4
-      - name: Log in to the Container registry
-        uses: docker/login-action@v3
-        with:
-          registry: ${{ env.REGISTRY }}
-          username: ${{ github.actor }}
-          password: ${{ secrets.GITHUB_TOKEN }}
-      - name: Extract metadata (tags, labels) for Docker
-        id: meta
-        uses: docker/metadata-action@v5
-        with:
-          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
-          tags: |
-            type=ref,event=branch
-            type=ref,event=pr
-            type=semver,pattern={{version}}
-            type=semver,pattern={{major}}.{{minor}}
-            type=sha
-      - name: Build and push Docker image
-        uses: docker/build-push-action@v5
-        with:
-          context: .
-          file: Dockerfile.external
-          push: true
-          tags: ${{ steps.meta.outputs.tags }}
-          labels: ${{ steps.meta.outputs.labels }}
diff --git a/.github/workflows/generate-release.yml b/.github/workflows/generate-release.yml
new file mode 100644
index 00000000..36a95add
--- /dev/null
+++ b/.github/workflows/generate-release.yml
@@ -0,0 +1,83 @@
+name: generate-release
+
+on:
+  release:
+    types: [ published ]
+  workflow_dispatch:
+
+env:
+  REGISTRY: docker.io
+  IMAGE_NAME: zylonai/private-gpt
+  platforms: linux/amd64,linux/arm64
+  DEFAULT_TYPE: "ollama"
+
+jobs:
+  build-and-push-image:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        type: [ llamacpp-cpu, ollama ]
+
+    permissions:
+      contents: read
+      packages: write
+
+    outputs:
+      version: ${{ steps.version.outputs.version }}
+
+    steps:
+      - name: Free Disk Space (Ubuntu)
+        uses: jlumbroso/free-disk-space@main
+        with:
+          tool-cache: false
+          android: true
+          dotnet: true
+          haskell: true
+          large-packages: true
+          docker-images: false
+          swap-storage: true
+
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to Docker Hub
+        uses: docker/login-action@v3
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ${{ env.REGISTRY }}/${{ env.IMAGE_NAME }}
+          tags: |
+            type=semver,pattern={{version}},enable=${{ matrix.type == env.DEFAULT_TYPE }}
+            type=semver,pattern={{version}}-${{ matrix.type }}
+            type=semver,pattern={{major}}.{{minor}},enable=${{ matrix.type == env.DEFAULT_TYPE }}
+            type=semver,pattern={{major}}.{{minor}}-${{ matrix.type }}
+            type=raw,value=latest,enable=${{ matrix.type == env.DEFAULT_TYPE }}
+            type=sha
+          flavor: |
+            latest=false
+
+      - name: Build and push Docker image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: Dockerfile.${{ matrix.type }}
+          platforms: ${{ env.platforms }}
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+
+      - name: Version output
+        id: version
+        run: echo "version=${{ steps.meta.outputs.version }}" >> "$GITHUB_OUTPUT"
\ No newline at end of file
diff --git a/.github/workflows/release-please.yml b/.github/workflows/release-please.yml
index b7b74e05..1e3f05c6 100644
--- a/.github/workflows/release-please.yml
+++ b/.github/workflows/release-please.yml
@@ -13,7 +13,8 @@ jobs:
   release-please:
     runs-on: ubuntu-latest
     steps:
-      - uses: google-github-actions/release-please-action@v3
+      - uses: google-github-actions/release-please-action@v4
+        id: release
         with:
-          release-type: simple
-          version-file: version.txt
\ No newline at end of file
+          config-file: .github/release_please/.release-please-config.json
+          manifest-file: .github/release_please/.release-please-manifest.json
diff --git a/.github/workflows/tests.yml b/.github/workflows/tests.yml
index 6a450cbe..ad8450de 100644
--- a/.github/workflows/tests.yml
+++ b/.github/workflows/tests.yml
@@ -14,7 +14,7 @@ jobs:
   setup:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: ./.github/workflows/actions/install_dependencies
 
   checks:
@@ -28,7 +28,7 @@ jobs:
           - ruff
           - mypy
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: ./.github/workflows/actions/install_dependencies
       - name: run ${{ matrix.quality-command }}
         run: make ${{ matrix.quality-command }}
@@ -38,7 +38,7 @@ jobs:
     runs-on: ubuntu-latest
     name: test
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
       - uses: ./.github/workflows/actions/install_dependencies
       - name: run test
         run: make test-coverage
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 4a9bbedc..e37d3413 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -1,5 +1,25 @@
 # Changelog
 
+## [0.6.2](https://github.com/zylon-ai/private-gpt/compare/v0.6.1...v0.6.2) (2024-08-08)
+
+
+### Bug Fixes
+
+* add numpy issue to troubleshooting ([#2048](https://github.com/zylon-ai/private-gpt/issues/2048)) ([4ca6d0c](https://github.com/zylon-ai/private-gpt/commit/4ca6d0cb556be7a598f7d3e3b00d2a29214ee1e8))
+* auto-update version ([#2052](https://github.com/zylon-ai/private-gpt/issues/2052)) ([7fefe40](https://github.com/zylon-ai/private-gpt/commit/7fefe408b4267684c6e3c1a43c5dc2b73ec61fe4))
+* publish image name ([#2043](https://github.com/zylon-ai/private-gpt/issues/2043)) ([b1acf9d](https://github.com/zylon-ai/private-gpt/commit/b1acf9dc2cbca2047cd0087f13254ff5cda6e570))
+* update matplotlib to 3.9.1-post1 to fix win install ([b16abbe](https://github.com/zylon-ai/private-gpt/commit/b16abbefe49527ac038d235659854b98345d5387))
+
+## [0.6.1](https://github.com/zylon-ai/private-gpt/compare/v0.6.0...v0.6.1) (2024-08-05)
+
+
+### Bug Fixes
+
+* add built image from DockerHub ([#2042](https://github.com/zylon-ai/private-gpt/issues/2042)) ([f09f6dd](https://github.com/zylon-ai/private-gpt/commit/f09f6dd2553077d4566dbe6b48a450e05c2f049e))
+* Adding azopenai to model list ([#2035](https://github.com/zylon-ai/private-gpt/issues/2035)) ([1c665f7](https://github.com/zylon-ai/private-gpt/commit/1c665f7900658144f62814b51f6e3434a6d7377f))
+* **deploy:** generate docker release when new version is released ([#2038](https://github.com/zylon-ai/private-gpt/issues/2038)) ([1d4c14d](https://github.com/zylon-ai/private-gpt/commit/1d4c14d7a3c383c874b323d934be01afbaca899e))
+* **deploy:** improve Docker-Compose and quickstart on Docker ([#2037](https://github.com/zylon-ai/private-gpt/issues/2037)) ([dae0727](https://github.com/zylon-ai/private-gpt/commit/dae0727a1b4abd35d2b0851fe30e0a4ed67e0fbb))
+
 ## [0.6.0](https://github.com/zylon-ai/private-gpt/compare/v0.5.0...v0.6.0) (2024-08-02)
 
 
diff --git a/Dockerfile.local b/Dockerfile.llamacpp-cpu
similarity index 100%
rename from Dockerfile.local
rename to Dockerfile.llamacpp-cpu
diff --git a/Dockerfile.external b/Dockerfile.ollama
similarity index 100%
rename from Dockerfile.external
rename to Dockerfile.ollama
diff --git a/docker-compose.yaml b/docker-compose.yaml
index 517af659..c2ef0f6d 100644
--- a/docker-compose.yaml
+++ b/docker-compose.yaml
@@ -1,19 +1,101 @@
 services:
-  private-gpt:
+
+  #-----------------------------------
+  #---- Private-GPT services ---------
+  #-----------------------------------
+
+  # Private-GPT service for the Ollama CPU and GPU modes
+  # This service builds from an external Dockerfile and runs the Ollama mode.
+  private-gpt-ollama:
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-ollama  # x-release-please-version
     build:
-      dockerfile: Dockerfile.external
+      context: .
+      dockerfile: Dockerfile.ollama
     volumes:
       - ./local_data/:/home/worker/app/local_data
     ports:
-      - 8001:8001
+      - "8001:8001"
     environment:
       PORT: 8001
       PGPT_PROFILES: docker
       PGPT_MODE: ollama
       PGPT_EMBED_MODE: ollama
-  ollama:
-    image: ollama/ollama:latest
+      PGPT_OLLAMA_API_BASE: http://ollama:11434
+      HF_TOKEN: ${HF_TOKEN:-}
+    profiles:
+      - ""
+      - ollama-cpu
+      - ollama-cuda
+      - ollama-api
+
+  # Private-GPT service for the local mode
+  # This service builds from a local Dockerfile and runs the application in local mode.
+  private-gpt-llamacpp-cpu:
+    image: ${PGPT_IMAGE:-zylonai/private-gpt}:${PGPT_TAG:-0.6.2}-llamacpp-cpu # x-release-please-version
+    build:
+      context: .
+      dockerfile: Dockerfile.llamacpp-cpu
+    volumes:
+      - ./local_data/:/home/worker/app/local_data
+      - ./models/:/home/worker/app/models
+    entrypoint: sh -c ".venv/bin/python scripts/setup && .venv/bin/python -m private_gpt"
     ports:
-      - 11434:11434
+      - "8001:8001"
+    environment:
+      PORT: 8001
+      PGPT_PROFILES: local
+      HF_TOKEN: ${HF_TOKEN}
+    profiles:
+      - llamacpp-cpu
+
+  #-----------------------------------
+  #---- Ollama services --------------
+  #-----------------------------------
+
+  # Traefik reverse proxy for the Ollama service
+  # This will route requests to the Ollama service based on the profile.
+  ollama:
+    image: traefik:v2.10
+    ports:
+      - "8081:8080"
+    command:
+      - "--providers.file.filename=/etc/router.yml"
+      - "--log.level=ERROR"
+      - "--api.insecure=true"
+      - "--providers.docker=true"
+      - "--providers.docker.exposedbydefault=false"
+      - "--entrypoints.web.address=:11434"
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:ro
+      - ./.docker/router.yml:/etc/router.yml:ro
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    profiles:
+      - ""
+      - ollama-cpu
+      - ollama-cuda
+      - ollama-api
+
+  # Ollama service for the CPU mode
+  ollama-cpu:
+    image: ollama/ollama:latest
     volumes:
       - ./models:/root/.ollama
+    profiles:
+      - ""
+      - ollama-cpu
+
+  # Ollama service for the CUDA mode
+  ollama-cuda:
+    image: ollama/ollama:latest
+    volumes:
+      - ./models:/root/.ollama
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    profiles:
+      - ollama-cuda
\ No newline at end of file
diff --git a/fern/docs.yml b/fern/docs.yml
index e0a5c423..d13822c8 100644
--- a/fern/docs.yml
+++ b/fern/docs.yml
@@ -10,6 +10,9 @@ tabs:
   overview:
     display-name: Overview
     icon: "fa-solid fa-home"
+  quickstart:
+    display-name: Quickstart
+    icon: "fa-solid fa-rocket"
   installation:
     display-name: Installation
     icon: "fa-solid fa-download"
@@ -32,6 +35,12 @@ navigation:
         contents:
           - page: Introduction
             path: ./docs/pages/overview/welcome.mdx
+  - tab: quickstart
+    layout:
+      - section: Getting started
+        contents:
+          - page: Quickstart
+            path: ./docs/pages/quickstart/quickstart.mdx
   # How to install PrivateGPT, with FAQ and troubleshooting
   - tab: installation
     layout:
diff --git a/fern/docs/pages/installation/installation.mdx b/fern/docs/pages/installation/installation.mdx
index f7457b34..e7f80c87 100644
--- a/fern/docs/pages/installation/installation.mdx
+++ b/fern/docs/pages/installation/installation.mdx
@@ -307,11 +307,12 @@ If you have all required dependencies properly configured running the
 following powershell command should succeed.
 
 ```powershell
-$env:CMAKE_ARGS='-DLLAMA_CUBLAS=on'; poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python
+$env:CMAKE_ARGS='-DLLAMA_CUBLAS=on'; poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python numpy==1.26.0
 ```
 
 If your installation was correct, you should see a message similar to the following next
-time you start the server `BLAS = 1`.
+time you start the server `BLAS = 1`. If there is some issue, please refer to the
+[troubleshooting](/installation/getting-started/troubleshooting#building-llama-cpp-with-nvidia-gpu-support) section.
 
 ```console
 llama_new_context_with_model: total VRAM used: 4857.93 MB (model: 4095.05 MB, context: 762.87 MB)
@@ -339,11 +340,12 @@ Some tips:
 After that running the following command in the repository will install llama.cpp with GPU support:
 
 ```bash
-CMAKE_ARGS='-DLLAMA_CUBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python
+CMAKE_ARGS='-DLLAMA_CUBLAS=on' poetry run pip install --force-reinstall --no-cache-dir llama-cpp-python numpy==1.26.0
 ```
 
 If your installation was correct, you should see a message similar to the following next
-time you start the server `BLAS = 1`.
+time you start the server `BLAS = 1`. If there is some issue, please refer to the
+[troubleshooting](/installation/getting-started/troubleshooting#building-llama-cpp-with-nvidia-gpu-support) section.
 
 ```
 llama_new_context_with_model: total VRAM used: 4857.93 MB (model: 4095.05 MB, context: 762.87 MB)
diff --git a/fern/docs/pages/installation/troubleshooting.mdx b/fern/docs/pages/installation/troubleshooting.mdx
index dc99d6cb..0b72526d 100644
--- a/fern/docs/pages/installation/troubleshooting.mdx
+++ b/fern/docs/pages/installation/troubleshooting.mdx
@@ -46,4 +46,19 @@ huggingface:
 embedding:
   embed_dim: 384
 ```
-</Callout>
\ No newline at end of file
+</Callout>
+
+# Building Llama-cpp with NVIDIA GPU support
+
+## Out-of-memory error
+
+If you encounter an out-of-memory error while running `llama-cpp` with CUDA, you can try the following steps to resolve the issue:
+1. **Set the next environment:**
+    ```bash
+    TOKENIZERS_PARALLELISM=true
+    ```
+2. **Run PrivateGPT:**
+    ```bash
+    poetry run python -m privategpt
+    ```
+Give thanks to [MarioRossiGithub](https://github.com/MarioRossiGithub) for providing the following solution.
\ No newline at end of file
diff --git a/fern/docs/pages/quickstart/quickstart.mdx b/fern/docs/pages/quickstart/quickstart.mdx
new file mode 100644
index 00000000..09877ce2
--- /dev/null
+++ b/fern/docs/pages/quickstart/quickstart.mdx
@@ -0,0 +1,105 @@
+This guide provides a quick start for running different profiles of PrivateGPT using Docker Compose.
+The profiles cater to various environments, including Ollama setups (CPU, CUDA, MacOS), and a fully local setup.
+
+By default, Docker Compose will download pre-built images from a remote registry when starting the services. However, you have the option to build the images locally if needed. Details on building Docker image locally are provided at the end of this guide.
+
+If you want to run PrivateGPT locally without Docker, refer to the [Local Installation Guide](/installation).
+
+## Prerequisites
+- **Docker and Docker Compose:** Ensure both are installed on your system.
+  [Installation Guide for Docker](https://docs.docker.com/get-docker/), [Installation Guide for Docker Compose](https://docs.docker.com/compose/install/).
+- **Clone PrivateGPT Repository:** Clone the PrivateGPT repository to your machine and navigate to the directory:
+  ```sh
+  git clone https://github.com/zylon-ai/private-gpt.git
+  cd private-gpt
+  ```
+
+## Setups
+
+### Ollama Setups (Recommended)
+
+#### 1. Default/Ollama CPU
+
+**Description:**
+This profile runs the Ollama service using CPU resources. It is the standard configuration for running Ollama-based Private-GPT services without GPU acceleration.
+
+**Run:**
+To start the services using pre-built images, run:
+```sh
+docker-compose up
+```
+or with a specific profile:
+```sh
+docker-compose --profile ollama-cpu up
+```
+
+#### 2. Ollama Nvidia CUDA
+
+**Description:**
+This profile leverages GPU acceleration with CUDA support, suitable for computationally intensive tasks that benefit from GPU resources.
+
+**Requirements:**
+Ensure that your system has compatible GPU hardware and the necessary NVIDIA drivers installed. The installation process is detailed [here](https://docs.nvidia.com/cuda/cuda-installation-guide-microsoft-windows/index.html).
+
+**Run:**
+To start the services with CUDA support using pre-built images, run:
+```sh
+docker-compose --profile ollama-cuda up
+```
+
+#### 3. Ollama External API
+
+**Description:**
+This profile is designed for running PrivateGPT using Ollama installed on the host machine. This setup is particularly useful for MacOS users, as Docker does not yet support Metal GPU.
+
+**Requirements:**
+Install Ollama on your machine by following the instructions at [ollama.ai](https://ollama.ai/).
+
+**Run:**
+To start the Ollama service, use:
+```sh
+OLLAMA_HOST=0.0.0.0 ollama serve
+```
+To start the services with the host configuration using pre-built images, run:
+```sh
+docker-compose --profile ollama-api up
+```
+
+### Fully Local Setups
+
+#### 1. LlamaCPP CPU
+
+**Description:**
+This profile runs the Private-GPT services locally using `llama-cpp` and Hugging Face models.
+
+**Requirements:**
+A **Hugging Face Token (HF_TOKEN)** is required for accessing Hugging Face models. Obtain your token following [this guide](/installation/getting-started/troubleshooting#downloading-gated-and-private-models).
+
+**Run:**
+Start the services with your Hugging Face token using pre-built images:
+```sh
+HF_TOKEN=<your_hf_token> docker-compose --profile llamacpp-cpu up
+```
+Replace `<your_hf_token>` with your actual Hugging Face token.
+
+## Building Locally
+
+If you prefer to build Docker images locally, which is useful when making changes to the codebase or the Dockerfiles, follow these steps:
+
+### Building Locally
+To build the Docker images locally, navigate to the cloned repository directory and run:
+```sh
+docker-compose build
+```
+This command compiles the necessary Docker images based on the current codebase and Dockerfile configurations.
+
+### Forcing a Rebuild with --build
+If you have made changes and need to ensure these changes are reflected in the Docker images, you can force a rebuild before starting the services:
+```sh
+docker-compose up --build
+```
+or with a specific profile:
+```sh
+docker-compose --profile <profile_name> up --build
+```
+Replace `<profile_name>` with the desired profile.
\ No newline at end of file
diff --git a/poetry.lock b/poetry.lock
index bb0a1ae6..ab83a150 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -1,4 +1,4 @@
-# This file is automatically @generated by Poetry 1.7.1 and should not be changed by hand.
+# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
 
 [[package]]
 name = "aiofiles"
@@ -1248,18 +1248,14 @@ standard = ["fastapi", "uvicorn[standard] (>=0.15.0)"]
 
 [[package]]
 name = "ffmpy"
-version = "0.3.2"
-description = "A simple Python wrapper for ffmpeg"
-optional = true
-python-versions = "*"
-files = []
-develop = false
-
-[package.source]
-type = "git"
-url = "https://github.com/EuDs63/ffmpy.git"
-reference = "333a19ee4d21f32537c0508aa1942ef1aa7afe24"
-resolved_reference = "333a19ee4d21f32537c0508aa1942ef1aa7afe24"
+version = "0.4.0"
+description = "A simple Python wrapper for FFmpeg"
+optional = false
+python-versions = "<4.0.0,>=3.8.1"
+files = [
+    {file = "ffmpy-0.4.0-py3-none-any.whl", hash = "sha256:39c0f20c5b465e7f8d29a5191f3a7d7675a8c546d9d985de8921151cd9b59e14"},
+    {file = "ffmpy-0.4.0.tar.gz", hash = "sha256:131b57794e802ad555f579007497f7a3d0cab0583d37496c685b8acae4837b1d"},
+]
 
 [[package]]
 name = "filelock"
@@ -2927,35 +2923,40 @@ tests = ["pytest", "pytz", "simplejson"]
 
 [[package]]
 name = "matplotlib"
-version = "3.9.1"
+version = "3.9.1.post1"
 description = "Python plotting package"
 optional = true
 python-versions = ">=3.9"
 files = [
-    {file = "matplotlib-3.9.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:7ccd6270066feb9a9d8e0705aa027f1ff39f354c72a87efe8fa07632f30fc6bb"},
-    {file = "matplotlib-3.9.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:591d3a88903a30a6d23b040c1e44d1afdd0d778758d07110eb7596f811f31842"},
-    {file = "matplotlib-3.9.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dd2a59ff4b83d33bca3b5ec58203cc65985367812cb8c257f3e101632be86d92"},
-    {file = "matplotlib-3.9.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0fc001516ffcf1a221beb51198b194d9230199d6842c540108e4ce109ac05cc0"},
-    {file = "matplotlib-3.9.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:83c6a792f1465d174c86d06f3ae85a8fe36e6f5964633ae8106312ec0921fdf5"},
-    {file = "matplotlib-3.9.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:b3fce58971b465e01b5c538f9d44915640c20ec5ff31346e963c9e1cd66fa812"},
-    {file = "matplotlib-3.9.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:a973c53ad0668c53e0ed76b27d2eeeae8799836fd0d0caaa4ecc66bf4e6676c0"},
-    {file = "matplotlib-3.9.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:82cd5acf8f3ef43f7532c2f230249720f5dc5dd40ecafaf1c60ac8200d46d7eb"},
-    {file = "matplotlib-3.9.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ab38a4f3772523179b2f772103d8030215b318fef6360cb40558f585bf3d017f"},
-    {file = "matplotlib-3.9.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:2315837485ca6188a4b632c5199900e28d33b481eb083663f6a44cfc8987ded3"},
-    {file = "matplotlib-3.9.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:565d572efea2b94f264dd86ef27919515aa6d629252a169b42ce5f570db7f37b"},
-    {file = "matplotlib-3.9.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:6d397fd8ccc64af2ec0af1f0efc3bacd745ebfb9d507f3f552e8adb689ed730a"},
-    {file = "matplotlib-3.9.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:26040c8f5121cd1ad712abffcd4b5222a8aec3a0fe40bc8542c94331deb8780d"},
-    {file = "matplotlib-3.9.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d12cb1837cffaac087ad6b44399d5e22b78c729de3cdae4629e252067b705e2b"},
-    {file = "matplotlib-3.9.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:0e835c6988edc3d2d08794f73c323cc62483e13df0194719ecb0723b564e0b5c"},
-    {file = "matplotlib-3.9.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:0c584210c755ae921283d21d01f03a49ef46d1afa184134dd0f95b0202ee6f03"},
-    {file = "matplotlib-3.9.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:11fed08f34fa682c2b792942f8902e7aefeed400da71f9e5816bea40a7ce28fe"},
-    {file = "matplotlib-3.9.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0000354e32efcfd86bda75729716b92f5c2edd5b947200be9881f0a671565c33"},
-    {file = "matplotlib-3.9.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4db17fea0ae3aceb8e9ac69c7e3051bae0b3d083bfec932240f9bf5d0197a049"},
-    {file = "matplotlib-3.9.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:208cbce658b72bf6a8e675058fbbf59f67814057ae78165d8a2f87c45b48d0ff"},
-    {file = "matplotlib-3.9.1-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:3fda72d4d472e2ccd1be0e9ccb6bf0d2eaf635e7f8f51d737ed7e465ac020cb3"},
-    {file = "matplotlib-3.9.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:84b3ba8429935a444f1fdc80ed930babbe06725bcf09fbeb5c8757a2cd74af04"},
-    {file = "matplotlib-3.9.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b918770bf3e07845408716e5bbda17eadfc3fcbd9307dc67f37d6cf834bb3d98"},
-    {file = "matplotlib-3.9.1.tar.gz", hash = "sha256:de06b19b8db95dd33d0dc17c926c7c9ebed9f572074b6fac4f65068a6814d010"},
+    {file = "matplotlib-3.9.1.post1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:3779ad3e8b72df22b8a622c5796bbcfabfa0069b835412e3c1dec8ee3de92d0c"},
+    {file = "matplotlib-3.9.1.post1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ec400340f8628e8e2260d679078d4e9b478699f386e5cc8094e80a1cb0039c7c"},
+    {file = "matplotlib-3.9.1.post1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:82c18791b8862ea095081f745b81f896b011c5a5091678fb33204fef641476af"},
+    {file = "matplotlib-3.9.1.post1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:621a628389c09a6b9f609a238af8e66acecece1cfa12febc5fe4195114ba7446"},
+    {file = "matplotlib-3.9.1.post1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:9a54734ca761ebb27cd4f0b6c2ede696ab6861052d7d7e7b8f7a6782665115f5"},
+    {file = "matplotlib-3.9.1.post1-cp310-cp310-win_amd64.whl", hash = "sha256:0721f93db92311bb514e446842e2b21c004541dcca0281afa495053e017c5458"},
+    {file = "matplotlib-3.9.1.post1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:b08b46058fe2a31ecb81ef6aa3611f41d871f6a8280e9057cb4016cb3d8e894a"},
+    {file = "matplotlib-3.9.1.post1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:22b344e84fcc574f561b5731f89a7625db8ef80cdbb0026a8ea855a33e3429d1"},
+    {file = "matplotlib-3.9.1.post1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4b49fee26d64aefa9f061b575f0f7b5fc4663e51f87375c7239efa3d30d908fa"},
+    {file = "matplotlib-3.9.1.post1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:89eb7e89e2b57856533c5c98f018aa3254fa3789fcd86d5f80077b9034a54c9a"},
+    {file = "matplotlib-3.9.1.post1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:c06e742bade41fda6176d4c9c78c9ea016e176cd338e62a1686384cb1eb8de41"},
+    {file = "matplotlib-3.9.1.post1-cp311-cp311-win_amd64.whl", hash = "sha256:c44edab5b849e0fc1f1c9d6e13eaa35ef65925f7be45be891d9784709ad95561"},
+    {file = "matplotlib-3.9.1.post1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:bf28b09986aee06393e808e661c3466be9c21eff443c9bc881bce04bfbb0c500"},
+    {file = "matplotlib-3.9.1.post1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:92aeb8c439d4831510d8b9d5e39f31c16c7f37873879767c26b147cef61e54cd"},
+    {file = "matplotlib-3.9.1.post1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f15798b0691b45c80d3320358a88ce5a9d6f518b28575b3ea3ed31b4bd95d009"},
+    {file = "matplotlib-3.9.1.post1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d59fc6096da7b9c1df275f9afc3fef5cbf634c21df9e5f844cba3dd8deb1847d"},
+    {file = "matplotlib-3.9.1.post1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:ab986817a32a70ce22302438691e7df4c6ee4a844d47289db9d583d873491e0b"},
+    {file = "matplotlib-3.9.1.post1-cp312-cp312-win_amd64.whl", hash = "sha256:0d78e7d2d86c4472da105d39aba9b754ed3dfeaeaa4ac7206b82706e0a5362fa"},
+    {file = "matplotlib-3.9.1.post1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:bd07eba6431b4dc9253cce6374a28c415e1d3a7dc9f8aba028ea7592f06fe172"},
+    {file = "matplotlib-3.9.1.post1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:ca230cc4482010d646827bd2c6d140c98c361e769ae7d954ebf6fff2a226f5b1"},
+    {file = "matplotlib-3.9.1.post1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ace27c0fdeded399cbc43f22ffa76e0f0752358f5b33106ec7197534df08725a"},
+    {file = "matplotlib-3.9.1.post1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9a4f3aeb7ba14c497dc6f021a076c48c2e5fbdf3da1e7264a5d649683e284a2f"},
+    {file = "matplotlib-3.9.1.post1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:23f96fbd4ff4cfa9b8a6b685a65e7eb3c2ced724a8d965995ec5c9c2b1f7daf5"},
+    {file = "matplotlib-3.9.1.post1-cp39-cp39-win_amd64.whl", hash = "sha256:2808b95452b4ffa14bfb7c7edffc5350743c31bda495f0d63d10fdd9bc69e895"},
+    {file = "matplotlib-3.9.1.post1-pp39-pypy39_pp73-macosx_10_15_x86_64.whl", hash = "sha256:ffc91239f73b4179dec256b01299d46d0ffa9d27d98494bc1476a651b7821cbe"},
+    {file = "matplotlib-3.9.1.post1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:f965ebca9fd4feaaca45937c4849d92b70653057497181100fcd1e18161e5f29"},
+    {file = "matplotlib-3.9.1.post1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:801ee9323fd7b2da0d405aebbf98d1da77ea430bbbbbec6834c0b3af15e5db44"},
+    {file = "matplotlib-3.9.1.post1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:50113e9b43ceb285739f35d43db36aa752fb8154325b35d134ff6e177452f9ec"},
+    {file = "matplotlib-3.9.1.post1.tar.gz", hash = "sha256:c91e585c65092c975a44dc9d4239ba8c594ba3c193d7c478b6d178c4ef61f406"},
 ]
 
 [package.dependencies]
@@ -3018,13 +3019,13 @@ files = [
 
 [[package]]
 name = "mistralai"
-version = "1.0.1"
+version = "1.0.3"
 description = "Python Client SDK for the Mistral AI API."
 optional = true
 python-versions = "<4.0,>=3.8"
 files = [
-    {file = "mistralai-1.0.1-py3-none-any.whl", hash = "sha256:5e5fc28122e11aec0ce37781b6419963e31cd7caccddf89f54eac1ece81f063f"},
-    {file = "mistralai-1.0.1.tar.gz", hash = "sha256:f6b055d21dd56e174e5023371295c35945d0f7b282486457d6a71ff47c703fe8"},
+    {file = "mistralai-1.0.3-py3-none-any.whl", hash = "sha256:64af7c9192e64dc66b2da6d1c4d54a1324a881c21665a2f93d6b35d9de9f87c8"},
+    {file = "mistralai-1.0.3.tar.gz", hash = "sha256:84f1a217666c76fec9d477ae266399b813c3ac32a4a348d2ecd5fe1c039b0667"},
 ]
 
 [package.dependencies]
@@ -3035,7 +3036,7 @@ python-dateutil = ">=2.9.0.post0,<3.0.0"
 typing-inspect = ">=0.9.0,<0.10.0"
 
 [package.extras]
-gcp = ["google-auth (>=2.31.0,<3.0.0)", "requests (>=2.32.3,<3.0.0)"]
+gcp = ["google-auth (==2.27.0)", "requests (>=2.32.3,<3.0.0)"]
 
 [[package]]
 name = "mmh3"
@@ -3896,8 +3897,6 @@ files = [
     {file = "orjson-3.10.6-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:960db0e31c4e52fa0fc3ecbaea5b2d3b58f379e32a95ae6b0ebeaa25b93dfd34"},
     {file = "orjson-3.10.6-cp312-none-win32.whl", hash = "sha256:a6ea7afb5b30b2317e0bee03c8d34c8181bc5a36f2afd4d0952f378972c4efd5"},
     {file = "orjson-3.10.6-cp312-none-win_amd64.whl", hash = "sha256:874ce88264b7e655dde4aeaacdc8fd772a7962faadfb41abe63e2a4861abc3dc"},
-    {file = "orjson-3.10.6-cp313-none-win32.whl", hash = "sha256:efdf2c5cde290ae6b83095f03119bdc00303d7a03b42b16c54517baa3c4ca3d0"},
-    {file = "orjson-3.10.6-cp313-none-win_amd64.whl", hash = "sha256:8e190fe7888e2e4392f52cafb9626113ba135ef53aacc65cd13109eb9746c43e"},
     {file = "orjson-3.10.6-cp38-cp38-macosx_10_15_x86_64.macosx_11_0_arm64.macosx_10_15_universal2.whl", hash = "sha256:66680eae4c4e7fc193d91cfc1353ad6d01b4801ae9b5314f17e11ba55e934183"},
     {file = "orjson-3.10.6-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:caff75b425db5ef8e8f23af93c80f072f97b4fb3afd4af44482905c9f588da28"},
     {file = "orjson-3.10.6-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:3722fddb821b6036fd2a3c814f6bd9b57a89dc6337b9924ecd614ebce3271394"},
@@ -6738,4 +6737,4 @@ vector-stores-qdrant = ["llama-index-vector-stores-qdrant"]
 [metadata]
 lock-version = "2.0"
 python-versions = ">=3.11,<3.12"
-content-hash = "3de5e86444ceee26b22bcecf8dd547d7c5ef2a14f62a1192a6125a4700e74640"
+content-hash = "119ebc4623e38c745677ca78dee1133087cce3b04ac210bc7a774e6c5cce26c6"
diff --git a/private_gpt/settings/settings.py b/private_gpt/settings/settings.py
index cc02b4c8..9b4238dd 100644
--- a/private_gpt/settings/settings.py
+++ b/private_gpt/settings/settings.py
@@ -104,6 +104,7 @@ class DataSettings(BaseModel):
         "It will be treated as an absolute path if it starts with /"
     )
 
+
 class LLMSettings(BaseModel):
     mode: Literal[
         "llamacpp",
@@ -196,7 +197,14 @@ class HuggingFaceSettings(BaseModel):
 
 class EmbeddingSettings(BaseModel):
     mode: Literal[
-        "huggingface", "openai", "azopenai", "sagemaker", "ollama", "mock", "gemini", "mistralai"
+        "huggingface",
+        "openai",
+        "azopenai",
+        "sagemaker",
+        "ollama",
+        "mock",
+        "gemini",
+        "mistralai",
     ]
     ingest_mode: Literal["simple", "batch", "parallel", "pipeline"] = Field(
         "simple",
diff --git a/private_gpt/ui/ui.py b/private_gpt/ui/ui.py
index 0bf06d19..2c1dcd3e 100644
--- a/private_gpt/ui/ui.py
+++ b/private_gpt/ui/ui.py
@@ -519,6 +519,7 @@ class PrivateGptUi:
                             "llamacpp": config_settings.llamacpp.llm_hf_model_file,
                             "openai": config_settings.openai.model,
                             "openailike": config_settings.openai.model,
+                            "azopenai": config_settings.azopenai.llm_model,
                             "sagemaker": config_settings.sagemaker.llm_endpoint_name,
                             "mock": llm_mode,
                             "ollama": config_settings.ollama.llm_model,
diff --git a/pyproject.toml b/pyproject.toml
index da3bd16c..733690ec 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "private-gpt"
-version = "0.6.0"
+version = "0.6.2"
 description = "Private GPT"
 authors = ["Zylon <hi@zylon.ai>"]
 
@@ -57,8 +57,7 @@ sentence-transformers = {version ="^3.0.1", optional = true}
 
 # Optional UI
 gradio = {version ="^4.37.2", optional = true}
-# Fix: https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/16289#issuecomment-2255106490
-ffmpy = {git = "https://github.com/EuDs63/ffmpy.git", rev = "333a19ee4d21f32537c0508aa1942ef1aa7afe24", optional = true}
+ffmpy = "0.4.0"
 
 # Optional Google Gemini dependency
 google-generativeai = {version ="^0.5.4", optional = true}
diff --git a/version.txt b/version.txt
index a918a2aa..b6160487 100644
--- a/version.txt
+++ b/version.txt
@@ -1 +1 @@
-0.6.0
+0.6.2