diff --git a/.github/workflows/pr.yml b/.github/workflows/pr.yml
index 5a5fff39..86f5ceb3 100644
--- a/.github/workflows/pr.yml
+++ b/.github/workflows/pr.yml
@@ -7,7 +7,7 @@ on:
 
 jobs:
   run-notebooks:
-    name: Run example Python notebooks
+    name: Cookbook notebooks
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
@@ -18,8 +18,8 @@ jobs:
           cwd: "./dial-cookbook/ci"
           up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
 
-  run-quickstart:
-    name: Run quickstart examples
+  run-quickstart-model:
+    name: Quickstart model
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
@@ -28,19 +28,44 @@ jobs:
         with:
           cwd: "./dial-docker-compose/ci/model"
           up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
+
+  run-quickstart-application:
+    name: Quickstart application
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
       - uses: isbang/compose-action@802a148945af6399a338c7906c267331b39a71af # v2.0.0
-        name: Run quickstart application example
         with:
           cwd: "./dial-docker-compose/ci/application"
           up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
+
+  run-quickstart-addon:
+    name: Quickstart addon
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
       - uses: isbang/compose-action@802a148945af6399a338c7906c267331b39a71af # v2.0.0
-        name: Run quickstart addon example
         with:
           cwd: "./dial-docker-compose/ci/addon"
           up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
 
+  run-quickstart-self-hosted-model:
+    name: Quickstart self-hosted model
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
+      - uses: isbang/compose-action@802a148945af6399a338c7906c267331b39a71af # v2.0.0
+        with:
+          cwd: "./dial-docker-compose/ci/ollama"
+          up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
+
   build:
-    needs: [run-notebooks, run-quickstart]
+    needs:
+      - run-notebooks
+      - run-quickstart-model
+      - run-quickstart-application
+      - run-quickstart-addon
+      - run-quickstart-self-hosted-model
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
index 38cdb0ba..e3828138 100644
--- a/.github/workflows/release.yml
+++ b/.github/workflows/release.yml
@@ -7,7 +7,7 @@ on:
 
 jobs:
   run-notebooks:
-    name: Run example Python notebooks
+    name: Cookbook notebooks
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
@@ -18,8 +18,9 @@ jobs:
           cwd: "./dial-cookbook/ci"
           up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
 
-  run-quickstart:
-    name: Run quickstart examples
+
+  run-quickstart-model:
+    name: Quickstart model
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
@@ -28,19 +29,44 @@ jobs:
         with:
           cwd: "./dial-docker-compose/ci/model"
           up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
+
+  run-quickstart-application:
+    name: Quickstart application
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
       - uses: isbang/compose-action@802a148945af6399a338c7906c267331b39a71af # v2.0.0
-        name: Run quickstart application example
         with:
           cwd: "./dial-docker-compose/ci/application"
           up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
+
+  run-quickstart-addon:
+    name: Quickstart addon
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
       - uses: isbang/compose-action@802a148945af6399a338c7906c267331b39a71af # v2.0.0
-        name: Run quickstart addon example
         with:
           cwd: "./dial-docker-compose/ci/addon"
           up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
 
+  run-quickstart-self-hosted-model:
+    name: Quickstart self-hosted model
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
+      - uses: isbang/compose-action@802a148945af6399a338c7906c267331b39a71af # v2.0.0
+        with:
+          cwd: "./dial-docker-compose/ci/ollama"
+          up-flags: "--abort-on-container-exit --exit-code-from test --timeout 300"
+
   build-and-deploy:
-    needs: [run-notebooks, run-quickstart]
+    needs:
+      - run-notebooks
+      - run-quickstart-model
+      - run-quickstart-application
+      - run-quickstart-addon
+      - run-quickstart-self-hosted-model
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@b4ffde65f46336ab88eb53be808477a3936bae11 # v4.1.1
diff --git a/.gitignore b/.gitignore
index 288b27ff..1c0d3cb8 100644
--- a/.gitignore
+++ b/.gitignore
@@ -23,8 +23,11 @@ yarn-error.log*
 .venv
 __pycache__
 
-# DIAL Core logs
-*.log
+# Docker container volumes
+core-data
+core-logs
+.ollama
+
 /.quarto/
 
 # Autogenerated files by Quarto
diff --git a/README.md b/README.md
index c169e8f2..db8095ca 100644
--- a/README.md
+++ b/README.md
@@ -13,10 +13,11 @@
 ## Helm Deployment
 
 * [AI DIAL Generic Installation Simple Guide](https://github.com/epam/ai-dial-helm/tree/main/charts/dial/examples/generic/simple)
-  
+
 ## Tutorials
 
 * [Launch AI DIAL Chat with an Azure model](./docs/tutorials/quick-start-model.md)
+* [Launch AI DIAL Chat with a self-hosted model](./docs/tutorials/quick-start-with-self-hosted-model.md)
 * [Launch AI DIAL Chat with a Sample Application](./docs/tutorials/quick-start-with-application.md)
 * [Launch AI DIAL Chat with a Sample Addon](./docs/tutorials/quick-start-with-addon.md)
 
@@ -31,7 +32,7 @@
 ## Configuration
 
 * Refer to [Configuration](./docs/Deployment/configuration.md)
-  
+
 ## Other AI DIAL Project Open Source Repositories
 
 Here is the current list of repositories where you can find more details. You can also refer to [repository map](https://epam-rail.com/open-source).
diff --git a/dial-docker-compose/addon/docker-compose.yml b/dial-docker-compose/addon/docker-compose.yml
index 9df5bd32..65c3715d 100644
--- a/dial-docker-compose/addon/docker-compose.yml
+++ b/dial-docker-compose/addon/docker-compose.yml
@@ -4,7 +4,7 @@ include:
 
 services:
   adapter-openai:
-    image: epam/ai-dial-adapter-openai:0.11.0
+    image: epam/ai-dial-adapter-openai:0.14.0
     environment:
       WEB_CONCURRENCY: "3"
 
diff --git a/dial-docker-compose/ci/ollama/.env b/dial-docker-compose/ci/ollama/.env
new file mode 100644
index 00000000..15ace1c5
--- /dev/null
+++ b/dial-docker-compose/ci/ollama/.env
@@ -0,0 +1,4 @@
+DIAL_DIR="./ollama"
+OLLAMA_CHAT_MODEL=llama3.1:8b-instruct-q4_0
+OLLAMA_VISION_MODEL=llava-phi3:3.8b-mini-q4_0
+OLLAMA_EMBEDDING_MODEL=nomic-embed-text:137m-v1.5-fp16
\ No newline at end of file
diff --git a/dial-docker-compose/ci/ollama/docker-compose.yml b/dial-docker-compose/ci/ollama/docker-compose.yml
new file mode 100644
index 00000000..aff7e6cc
--- /dev/null
+++ b/dial-docker-compose/ci/ollama/docker-compose.yml
@@ -0,0 +1,16 @@
+include:
+  - path: ../../ollama/docker-compose.yml
+    env_file: ./.env
+
+services:
+  test:
+    build: test
+    environment:
+      DIAL_URL: "http://core:8080"
+      DIAL_API_KEY: "dial_api_key"
+      DIAL_API_VERSION: "2024-02-01"
+    depends_on:
+      ollama-setup:
+        condition: service_healthy
+      core:
+        condition: service_healthy
\ No newline at end of file
diff --git a/dial-docker-compose/ci/ollama/test/.dockerignore b/dial-docker-compose/ci/ollama/test/.dockerignore
new file mode 100644
index 00000000..1d1fe94d
--- /dev/null
+++ b/dial-docker-compose/ci/ollama/test/.dockerignore
@@ -0,0 +1 @@
+Dockerfile
\ No newline at end of file
diff --git a/dial-docker-compose/ci/ollama/test/Dockerfile b/dial-docker-compose/ci/ollama/test/Dockerfile
new file mode 100644
index 00000000..c41fc702
--- /dev/null
+++ b/dial-docker-compose/ci/ollama/test/Dockerfile
@@ -0,0 +1,7 @@
+FROM python:3.11-alpine
+
+WORKDIR /app
+COPY * /app
+RUN pip install -r requirements.txt
+
+CMD ["python", "app.py"]
\ No newline at end of file
diff --git a/dial-docker-compose/ci/ollama/test/app.py b/dial-docker-compose/ci/ollama/test/app.py
new file mode 100644
index 00000000..66e49085
--- /dev/null
+++ b/dial-docker-compose/ci/ollama/test/app.py
@@ -0,0 +1,141 @@
+import base64
+import os
+from pathlib import Path
+from typing import Any
+import aiohttp
+import asyncio
+import backoff
+
+import logging
+import time
+from contextlib import asynccontextmanager
+
+
+def get_env(name: str) -> str:
+    value = os.environ.get(name)
+    if value is None:
+        raise ValueError(f"'{name}' environment variable must be defined")
+    return value
+
+
+DIAL_URL = get_env("DIAL_URL")
+DIAL_API_KEY = get_env("DIAL_API_KEY")
+DIAL_API_VERSION = get_env("DIAL_API_VERSION")
+
+logging.basicConfig(level=logging.DEBUG)
+log = logging.getLogger(__name__)
+
+
+@asynccontextmanager
+async def timer(name: str):
+    log.debug(f"[{name}] Starting...")
+    start = time.perf_counter()
+    yield
+    elapsed = time.perf_counter() - start
+    log.debug(f"[{name}] Executed in {elapsed:.2f} seconds")
+
+
+@backoff.on_exception(
+    backoff.expo,
+    (aiohttp.ClientError, aiohttp.ServerTimeoutError),
+    max_time=60,
+)
+async def post_with_retry(url: str, payload: dict, headers: dict, params: dict):
+    async with aiohttp.ClientSession() as session:
+        async with session.post(
+            url, json=payload, headers=headers, params=params
+        ) as response:
+            response.raise_for_status()
+            return await response.json()
+
+
+def read_image_base64(png_file: Path) -> str:
+    return base64.b64encode(png_file.read_bytes()).decode("utf-8")
+
+async def dial_chat_completion(deployment_id: str, messages: list) -> str:
+    api_url = f"{DIAL_URL}/openai/deployments/{deployment_id}/chat/completions"
+
+    payload = {
+        "model": deployment_id,
+        "messages": messages,
+        "stream": False,
+    }
+    headers = {"api-key": DIAL_API_KEY}
+    params = {"api-version": DIAL_API_VERSION}
+
+    body = await post_with_retry(api_url, payload, headers, params)
+    log.debug(f"Response: {body}")
+
+    content = body.get("choices", [])[0].get("message", {}).get("content", "")
+
+    log.debug(f"Content: {content}")
+
+    return content
+
+async def dial_embeddings(deployment_id: str, input: Any) -> str:
+    api_url = f"{DIAL_URL}/openai/deployments/{deployment_id}/embeddings"
+
+    payload = {
+        "model": deployment_id,
+        "input": input,
+    }
+    headers = {"api-key": DIAL_API_KEY}
+    params = {"api-version": DIAL_API_VERSION}
+
+    body = await post_with_retry(api_url, payload, headers, params)
+    log.debug(f"Response: {body}")
+
+    embedding = body.get("data", [])[0].get("embedding", [])
+
+    log.debug(f"Len embedding vector: {len(embedding)}")
+
+    return embedding
+
+async def test_chat_model(deployment_id: str):
+    message = "2 + 3 = ? Reply with a single number:"
+    messages = [{"role": "user", "content": message}]
+    content = await dial_chat_completion(deployment_id, messages)
+
+    if "5" not in content:
+        raise ValueError(f"Test failed for {deployment_id!r}")
+
+
+async def test_vision_model(deployment_id: str):
+    base64_data = read_image_base64(Path("./image.png"))
+    base64_image = f"data:image/png;base64,{base64_data}"
+
+    messages = [
+        {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": "Describe the image"},
+                {"type": "image_url", "image_url": {"url": base64_image}},
+            ],
+        }
+    ]
+
+    content = await dial_chat_completion(deployment_id, messages)
+
+    if "vision" not in content.lower():
+        raise ValueError(f"Test failed for {deployment_id!r}")
+
+async def test_embedding_model(deployment_id: str):
+    embeddings = await dial_embeddings(deployment_id, "cat")
+
+    if len(embeddings) == 0 or not isinstance(embeddings[0], float):
+        raise ValueError(f"Test failed for {deployment_id!r}")
+
+
+async def tests():
+    async with timer("Testing chat-model"):
+        await test_chat_model("chat-model")
+
+    async with timer("Testing vision-model"):
+        await test_vision_model("vision-model")
+
+    async with timer("Testing embedding-model"):
+        await test_embedding_model("embedding-model")
+
+if __name__ == "__main__":
+    loop = asyncio.get_event_loop()
+    loop.run_until_complete(tests())
diff --git a/dial-docker-compose/ci/ollama/test/image.png b/dial-docker-compose/ci/ollama/test/image.png
new file mode 100644
index 00000000..bfbcfc7e
Binary files /dev/null and b/dial-docker-compose/ci/ollama/test/image.png differ
diff --git a/dial-docker-compose/ci/ollama/test/requirements.txt b/dial-docker-compose/ci/ollama/test/requirements.txt
new file mode 100644
index 00000000..1c6d30a5
--- /dev/null
+++ b/dial-docker-compose/ci/ollama/test/requirements.txt
@@ -0,0 +1,2 @@
+aiohttp==3.9.4
+backoff==2.2.1
\ No newline at end of file
diff --git a/dial-docker-compose/common.yml b/dial-docker-compose/common.yml
index 6da6adbb..8e2ae74a 100644
--- a/dial-docker-compose/common.yml
+++ b/dial-docker-compose/common.yml
@@ -1,13 +1,13 @@
 services:
   themes:
-    image: epam/ai-dial-chat-themes:0.4.0
+    image: epam/ai-dial-chat-themes:0.6.0
     ports:
       - "3001:8080"
 
   chat:
     ports:
       - "3000:3000"
-    image: epam/ai-dial-chat:0.10.0
+    image: epam/ai-dial-chat:0.17.0
     depends_on:
       - themes
       - core
@@ -36,7 +36,7 @@ services:
     user: ${UID:-root}
     ports:
       - "8080:8080"
-    image: epam/ai-dial-core:0.9.0
+    image: epam/ai-dial-core:0.16.0
     environment:
       'AIDIAL_SETTINGS': '/opt/settings/settings.json'
       'JAVA_OPTS': '-Dgflog.config=/opt/settings/gflog.xml'
diff --git a/dial-docker-compose/model/docker-compose.yml b/dial-docker-compose/model/docker-compose.yml
index 1dd03ae0..a918cb85 100644
--- a/dial-docker-compose/model/docker-compose.yml
+++ b/dial-docker-compose/model/docker-compose.yml
@@ -4,6 +4,6 @@ include:
 
 services:
   adapter-openai:
-    image: epam/ai-dial-adapter-openai:0.11.0
+    image: epam/ai-dial-adapter-openai:0.14.0
     environment:
       WEB_CONCURRENCY: "3"
\ No newline at end of file
diff --git a/dial-docker-compose/ollama/.env b/dial-docker-compose/ollama/.env
new file mode 100644
index 00000000..cdabc6b5
--- /dev/null
+++ b/dial-docker-compose/ollama/.env
@@ -0,0 +1,4 @@
+DIAL_DIR="./ollama"
+OLLAMA_CHAT_MODEL=
+OLLAMA_VISION_MODEL=
+OLLAMA_EMBEDDING_MODEL=
\ No newline at end of file
diff --git a/dial-docker-compose/ollama/.env.example b/dial-docker-compose/ollama/.env.example
new file mode 100644
index 00000000..06216195
--- /dev/null
+++ b/dial-docker-compose/ollama/.env.example
@@ -0,0 +1,3 @@
+OLLAMA_CHAT_MODEL=llama3.1:8b-instruct-q4_0
+OLLAMA_VISION_MODEL=llava-phi3:3.8b-mini-q4_0
+OLLAMA_EMBEDDING_MODEL=bge-m3:567m-fp16
\ No newline at end of file
diff --git a/dial-docker-compose/ollama/core/config.json b/dial-docker-compose/ollama/core/config.json
new file mode 100644
index 00000000..e4b370cc
--- /dev/null
+++ b/dial-docker-compose/ollama/core/config.json
@@ -0,0 +1,44 @@
+{
+  "routes": {},
+  "models": {
+    "chat-model": {
+      "type": "chat",
+      "displayName": "Self-hosted chat model",
+      "endpoint": "http://ollama:11434/v1/chat/completions"
+    },
+    "vision-model": {
+      "type": "chat",
+      "displayName": "Self-hosted vision model",
+      "endpoint": "http://adapter-openai:5000/openai/deployments/vision-model/chat/completions",
+      "inputAttachmentTypes": [
+        "image/png",
+        "image/jpeg"
+      ],
+      "upstreams": [
+        {
+          "endpoint": "http://ollama:11434/v1/chat/completions",
+          "key": "dummy-key"
+        }
+      ]
+    },
+    "embedding-model": {
+      "type": "embedding",
+      "endpoint": "http://ollama:11434/v1/embeddings"
+    }
+  },
+  "keys": {
+    "dial_api_key": {
+      "project": "TEST-PROJECT",
+      "role": "default"
+    }
+  },
+  "roles": {
+    "default": {
+      "limits": {
+        "chat-model": {},
+        "vision-model": {},
+        "embedding-model": {}
+      }
+    }
+  }
+}
\ No newline at end of file
diff --git a/dial-docker-compose/ollama/docker-compose.yml b/dial-docker-compose/ollama/docker-compose.yml
new file mode 100644
index 00000000..68e316f0
--- /dev/null
+++ b/dial-docker-compose/ollama/docker-compose.yml
@@ -0,0 +1,35 @@
+include:
+  - path: ../common.yml
+    env_file: ./.env
+
+services:
+  ollama:
+    image: ollama/ollama:0.3.10
+    volumes:
+      - ./.ollama:/root/.ollama
+    ports:
+      - "11434:11434"
+
+  ollama-setup:
+    depends_on:
+      ollama:
+        condition: service_started
+    build: ./ollama_setup
+    environment:
+      - OLLAMA_URL=http://ollama:11434
+      - OLLAMA_CHAT_MODEL=${OLLAMA_CHAT_MODEL}
+      - OLLAMA_VISION_MODEL=${OLLAMA_VISION_MODEL}
+      - OLLAMA_EMBEDDING_MODEL=${OLLAMA_EMBEDDING_MODEL}
+    healthcheck:
+      test: ["CMD", "test", "-f", "/healthy"]
+      interval: 10s
+      start_period: 10s
+      retries: 10
+
+  adapter-openai:
+    image: epam/ai-dial-adapter-openai:0.14.0
+    environment:
+      WEB_CONCURRENCY: "3"
+      DIAL_URL: "http://core:8080"
+      DIAL_USE_FILE_STORAGE: "True"
+      GPT4_VISION_DEPLOYMENTS: "vision-model"
\ No newline at end of file
diff --git a/dial-docker-compose/ollama/ollama_setup/Dockerfile b/dial-docker-compose/ollama/ollama_setup/Dockerfile
new file mode 100644
index 00000000..91b223bf
--- /dev/null
+++ b/dial-docker-compose/ollama/ollama_setup/Dockerfile
@@ -0,0 +1,7 @@
+FROM python:3.11-alpine
+
+WORKDIR /app
+COPY * /app
+RUN pip install -r requirements.txt
+
+CMD ["sh", "-c", "python setup.py && tail -f /dev/null"]
diff --git a/dial-docker-compose/ollama/ollama_setup/requirements.txt b/dial-docker-compose/ollama/ollama_setup/requirements.txt
new file mode 100644
index 00000000..ac6a93f1
--- /dev/null
+++ b/dial-docker-compose/ollama/ollama_setup/requirements.txt
@@ -0,0 +1,3 @@
+httpx==0.27.2
+tqdm==4.66.5
+ollama==0.3.3
\ No newline at end of file
diff --git a/dial-docker-compose/ollama/ollama_setup/setup.py b/dial-docker-compose/ollama/ollama_setup/setup.py
new file mode 100755
index 00000000..3e27663e
--- /dev/null
+++ b/dial-docker-compose/ollama/ollama_setup/setup.py
@@ -0,0 +1,127 @@
+import asyncio
+from contextlib import asynccontextmanager
+import os
+import sys
+import time
+import asyncio
+from ollama import AsyncClient
+from tqdm import tqdm
+
+OLLAMA_URL = os.getenv("OLLAMA_URL")
+if OLLAMA_URL is None:
+    raise RuntimeError("OLLAMA_URL env var isn't set")
+
+OLLAMA_CHAT_MODEL = os.getenv("OLLAMA_CHAT_MODEL")
+OLLAMA_VISION_MODEL = os.getenv("OLLAMA_VISION_MODEL")
+OLLAMA_EMBEDDING_MODEL = os.getenv("OLLAMA_EMBEDDING_MODEL")
+
+HEALTH_FILE = "/healthy"
+
+
+class Writer:
+    @classmethod
+    def write(cls, s: str):
+        # NOTE: every tqdm progress bar update is deliberately ended with "\n",
+        # otherwise one wouldn't see the bar running in console upon running `docker compose up`.
+        print(s, file=sys.stdout, flush=True, end="\n")
+
+    @classmethod
+    def flush(cls):
+        sys.stdout.flush()
+
+
+print_info = Writer.write
+
+print_info(f"OLLAMA_URL = {OLLAMA_URL}")
+print_info(f"OLLAMA_CHAT_MODEL = {OLLAMA_CHAT_MODEL}")
+print_info(f"OLLAMA_VISION_MODEL = {OLLAMA_VISION_MODEL}")
+print_info(f"OLLAMA_EMBEDDING_MODEL = {OLLAMA_EMBEDDING_MODEL}")
+
+
+@asynccontextmanager
+async def timer(name: str):
+    print_info(f"[{name}] Starting...")
+    start = time.perf_counter()
+    yield
+    elapsed = time.perf_counter() - start
+    print_info(f"[{name}] Finished in {elapsed:.2f} seconds")
+
+
+async def wait_for_startup():
+    attempt = 0
+    while True:
+        attempt += 1
+        try:
+            await AsyncClient(host=OLLAMA_URL, timeout=5).ps()
+        except Exception:
+            print_info(f"[{attempt:>3}] Waiting for Ollama to start...")
+            await asyncio.sleep(5)
+        else:
+            break
+
+
+async def pull_model(client: AsyncClient, model: str):
+    response = await client.pull(model, stream=True)
+
+    progress_bar = None
+    prev_status = None
+
+    async for chunk in response:
+        status = chunk["status"]
+        total = chunk.get("total")
+        completed = chunk.get("completed")
+
+        if status != prev_status and total:
+            prev_status = status
+            if progress_bar:
+                progress_bar.close()
+            progress_bar = tqdm(
+                total=total, unit="B", unit_scale=True, desc=f"[{status}]", file=Writer
+            )
+
+        if completed and progress_bar and total:
+            progress_bar.n = completed
+            progress_bar.set_description(f"[{status}]")
+            progress_bar.refresh()
+
+        if total and total == completed and progress_bar:
+            progress_bar.close()
+
+        if not completed and not total:
+            print_info(f"[{status}]")
+
+
+async def create_health_mark():
+    open(HEALTH_FILE, "w").close()
+
+
+async def main():
+    client = AsyncClient(host=OLLAMA_URL, timeout=300000)
+
+    async with timer("Waiting for Ollama to start"):
+        await wait_for_startup()
+
+    for model, alias in [
+        (OLLAMA_CHAT_MODEL, "chat-model"),
+        (OLLAMA_VISION_MODEL, "vision-model"),
+        (OLLAMA_EMBEDDING_MODEL, "embedding-model"),
+    ]:
+        if model:
+            async with timer(f"Pulling model {model}"):
+                await pull_model(client, model)
+
+            async with timer(f"Creating alias for {model}: {alias}"):
+                await client.copy(model, alias)
+
+    if model_to_load := (OLLAMA_CHAT_MODEL or OLLAMA_VISION_MODEL):
+        async with timer(f"Loading model {model_to_load} into memory"):
+            await client.generate(model_to_load)
+
+    await create_health_mark()
+
+    print_info("The Ollama server is up and running.")
+
+
+if __name__ == "__main__":
+    loop = asyncio.get_event_loop()
+    loop.run_until_complete(main())
diff --git a/dial-docker-compose/settings/settings.json b/dial-docker-compose/settings/settings.json
index 446b1b6b..0471610d 100644
--- a/dial-docker-compose/settings/settings.json
+++ b/dial-docker-compose/settings/settings.json
@@ -9,7 +9,7 @@
     }
   },
   "encryption": {
-    "salt": "salt",
-    "password": "password"
+    "secret": "salt",
+    "key": "password"
   }
 }
\ No newline at end of file
diff --git a/docs/README.md b/docs/README.md
index a4beeb25..93b9a2de 100644
--- a/docs/README.md
+++ b/docs/README.md
@@ -33,8 +33,9 @@
 ## Tutorials
 
 * [Launch AI DIAL Chat with an Azure model](./tutorials/quick-start-model.md)
-* [Launch AI DIAL Chat with a Sample Application](./tutorials/quick-start-with-application.md)
-* [Launch AI DIAL Chat with a Sample Addon](./tutorials/quick-start-with-addon.md)
+* [Launch AI DIAL Chat with a self-hosted model](./tutorials/quick-start-with-self-hosted-model.md)
+* [Launch AI DIAL Chat with a sample application](./tutorials/quick-start-with-application.md)
+* [Launch AI DIAL Chat with a sample addon](./tutorials/quick-start-with-addon.md)
 
 ## AI DIAL Chat Application User Manual
 
diff --git a/docs/tutorials/quick-start-with-self-hosted-model.md b/docs/tutorials/quick-start-with-self-hosted-model.md
new file mode 100644
index 00000000..77b18828
--- /dev/null
+++ b/docs/tutorials/quick-start-with-self-hosted-model.md
@@ -0,0 +1,79 @@
+# Launch AI DIAL Chat with a Self-Hosted Model
+
+## Introduction
+
+In this tutorial, you will learn how to quickly launch AI DIAL Chat with a self-hosted model powered by [Ollama](https://ollama.com/).
+
+## Prerequisites
+
+Docker engine installed on your machine (Docker Compose Version 2.20.0 +).
+
+> Refer to [Docker](https://docs.docker.com/desktop/) documentation.
+
+## Step 1: Get AI DIAL
+
+Clone [the repository](https://github.com/epam/ai-dial/) with the tutorials and change directory to the following folder:
+
+```sh
+cd dial-docker-compose/ollama
+```
+
+## Step 2: Choose a model to run
+
+Ollama supports a wide range of popular open-source models.
+
+Consider first the modality your are interested in - is it a regular text-to-text chat model, a multi-modal vision model or an embedding model?
+
+Follow the feature tags _(`Embeddings`, `Code`, `Tools`, `Vision`)_ at [Ollama Search](https://ollama.com/search) to find the appropriate model.
+
+We recommend choosing one of the following models which have been tested.
+
+### Chat models
+
+|Model|Tools|
+|----|----|
+|[llama3.1:8b-instruct-q4_0](https://ollama.com/library/llama3.1:8b-instruct-q4_0)|✅ *(only in non-streaming mode)*|
+|[mistral:7b-instruct-q4_0](https://ollama.com/library/mistral:7b-instruct-q4_0)|❌|
+|[phi3.5:3.8b-mini-instruct-q4_0](https://ollama.com/library/phi3.5:3.8b-mini-instruct-q4_0)|❌|
+|[gemma2:2b-instruct-q4_0](https://ollama.com/library/gemma2:2b-instruct-q4_0)|❌|
+
+All the models support streaming.
+
+### Vision models
+
+* [llava:7b-v1.6-mistral-q4_0](https://ollama.com/library/llava:7b-v1.6-mistral-q4_0)
+* [llava-phi3:3.8b-mini-q4_0](https://ollama.com/library/llava-phi3:3.8b-mini-q4_0)
+
+### Embedding models
+
+* [nomic-embed-text:137m-v1.5-fp16](https://ollama.com/library/nomic-embed-text:137m-v1.5-fp16)
+* [bge-m3:567m-fp16](https://ollama.com/library/bge-m3:567m-fp16)
+
+## Step 3: Launch AI DIAL Chat
+
+1. Configure `.env` file in the current directory according to the type of model you've chosen:
+
+    * Set `OLLAMA_CHAT_MODEL` for the name of a text model.
+    * Set `OLLAMA_VISION_MODEL` for the name of a vision model.
+    * Set `OLLAMA_EMBEDDING_MODEL` for the name of an embedding model.
+
+    **Note**: It's not necessary to configure all the models. If a model isn't set, then it won't be downloaded.
+
+2. Then run the following command to pull and load into the memory of the Ollama server the specified models:
+
+    ```sh
+    docker compose up --abort-on-container-exit
+    ```
+
+    > Keep in mind that a typical size of a lightweight Ollama model is around a few gigabytes. So it may take a few minutes _(or dozens of minutes)_ to download them on the first run depending on your Internet bandwidth.
+    >
+    > The model is fully loaded once `ollama-setup` service prints `The Ollama server is up and running.`
+
+3. Finally, open http://localhost:3000/ in your browser to launch the AI DIAL Chat application and select an appropriate AI DIAL deployments to converse with:
+
+    * `Self-hosted chat model` deployment for the `OLLAMA_CHAT_MODEL`
+    * `Self-hosted vision model` deployment for the `OLLAMA_VISION_MODEL`
+
+> Note, that the vision models we tested, do not support streaming of response. Moreover, they are typically more computationally expensive than the chat models. So it may take minutes for a vision model to respond.
+
+The embedding model will become available in AI DIAL under the deployment name `embedding-model` and could be called via the endpoint: `localhost:8080/openai/deployments/embedding-model/embeddings`.
diff --git a/sidebars.js b/sidebars.js
index a0ab1bff..dc81800b 100644
--- a/sidebars.js
+++ b/sidebars.js
@@ -102,6 +102,11 @@ const sidebars = {
           id: 'tutorials/quick-start-model',
           label: 'Chat with OpenAI Model',
         },
+        {
+          type: 'doc',
+          id: 'tutorials/quick-start-with-self-hosted-model',
+          label: 'Chat with a Self-Hosted Model',
+        },
         {
           type: 'doc',
           id: 'tutorials/quick-start-with-addon',
@@ -197,13 +202,13 @@ const sidebars = {
           Demos: [
             {
               type: 'autogenerated',
-              dirName: 'video demos/demos', 
+              dirName: 'video demos/demos',
             },
           ],
           'Demos For Developers': [
             {
               type: 'autogenerated',
-              dirName: 'video demos/demos-for-developers', 
+              dirName: 'video demos/demos-for-developers',
             },
           ],
         },