diff --git a/README.md b/README.md
index 847653232c..2d4f80454e 100644
--- a/README.md
+++ b/README.md
@@ -92,6 +92,7 @@ However, you can try the [Azure pricing calculator](https://azure.com/e/a87a169b
 - Azure AI Document Intelligence: SO (Standard) tier using pre-built layout. Pricing per document page, sample documents have 261 pages total. [Pricing](https://azure.microsoft.com/pricing/details/form-recognizer/)
 - Azure AI Search: Basic tier, 1 replica, free level of semantic search. Pricing per hour. [Pricing](https://azure.microsoft.com/pricing/details/search/)
 - Azure Blob Storage: Standard tier with ZRS (Zone-redundant storage). Pricing per storage and read operations. [Pricing](https://azure.microsoft.com/pricing/details/storage/blobs/)
+- Azure Cosmos DB: Serverless tier. Pricing per request unit and storage. [Pricing](https://azure.microsoft.com/pricing/details/cosmos-db/)
 - Azure Monitor: Pay-as-you-go tier. Costs based on data ingested. [Pricing](https://azure.microsoft.com/pricing/details/monitor/)
 
 To reduce costs, you can switch to free SKUs for various services, but those SKUs have limitations.
diff --git a/app/backend/app.py b/app/backend/app.py
index 4098a12e1d..b83efefe62 100644
--- a/app/backend/app.py
+++ b/app/backend/app.py
@@ -53,6 +53,7 @@
 from approaches.chatreadretrievereadvision import ChatReadRetrieveReadVisionApproach
 from approaches.retrievethenread import RetrieveThenReadApproach
 from approaches.retrievethenreadvision import RetrieveThenReadVisionApproach
+from chat_history.cosmosdb import chat_history_cosmosdb_bp
 from config import (
     CONFIG_ASK_APPROACH,
     CONFIG_ASK_VISION_APPROACH,
@@ -60,6 +61,7 @@
     CONFIG_BLOB_CONTAINER_CLIENT,
     CONFIG_CHAT_APPROACH,
     CONFIG_CHAT_HISTORY_BROWSER_ENABLED,
+    CONFIG_CHAT_HISTORY_COSMOS_ENABLED,
     CONFIG_CHAT_VISION_APPROACH,
     CONFIG_CREDENTIAL,
     CONFIG_GPT4V_DEPLOYED,
@@ -224,7 +226,10 @@ async def chat(auth_claims: Dict[str, Any]):
         # else creates a new session_id depending on the chat history options enabled.
         session_state = request_json.get("session_state")
         if session_state is None:
-            session_state = create_session_id(current_app.config[CONFIG_CHAT_HISTORY_BROWSER_ENABLED])
+            session_state = create_session_id(
+                current_app.config[CONFIG_CHAT_HISTORY_COSMOS_ENABLED],
+                current_app.config[CONFIG_CHAT_HISTORY_BROWSER_ENABLED],
+            )
         result = await approach.run(
             request_json["messages"],
             context=context,
@@ -255,7 +260,10 @@ async def chat_stream(auth_claims: Dict[str, Any]):
         # else creates a new session_id depending on the chat history options enabled.
         session_state = request_json.get("session_state")
         if session_state is None:
-            session_state = create_session_id(current_app.config[CONFIG_CHAT_HISTORY_BROWSER_ENABLED])
+            session_state = create_session_id(
+                current_app.config[CONFIG_CHAT_HISTORY_COSMOS_ENABLED],
+                current_app.config[CONFIG_CHAT_HISTORY_BROWSER_ENABLED],
+            )
         result = await approach.run_stream(
             request_json["messages"],
             context=context,
@@ -289,6 +297,7 @@ def config():
             "showSpeechOutputBrowser": current_app.config[CONFIG_SPEECH_OUTPUT_BROWSER_ENABLED],
             "showSpeechOutputAzure": current_app.config[CONFIG_SPEECH_OUTPUT_AZURE_ENABLED],
             "showChatHistoryBrowser": current_app.config[CONFIG_CHAT_HISTORY_BROWSER_ENABLED],
+            "showChatHistoryCosmos": current_app.config[CONFIG_CHAT_HISTORY_COSMOS_ENABLED],
         }
     )
 
@@ -455,6 +464,7 @@ async def setup_clients():
     USE_SPEECH_OUTPUT_BROWSER = os.getenv("USE_SPEECH_OUTPUT_BROWSER", "").lower() == "true"
     USE_SPEECH_OUTPUT_AZURE = os.getenv("USE_SPEECH_OUTPUT_AZURE", "").lower() == "true"
     USE_CHAT_HISTORY_BROWSER = os.getenv("USE_CHAT_HISTORY_BROWSER", "").lower() == "true"
+    USE_CHAT_HISTORY_COSMOS = os.getenv("USE_CHAT_HISTORY_COSMOS", "").lower() == "true"
 
     # WEBSITE_HOSTNAME is always set by App Service, RUNNING_IN_PRODUCTION is set in main.bicep
     RUNNING_ON_AZURE = os.getenv("WEBSITE_HOSTNAME") is not None or os.getenv("RUNNING_IN_PRODUCTION") is not None
@@ -484,6 +494,9 @@ async def setup_clients():
         current_app.logger.info("Setting up Azure credential using AzureDeveloperCliCredential for home tenant")
         azure_credential = AzureDeveloperCliCredential(process_timeout=60)
 
+    # Set the Azure credential in the app config for use in other parts of the app
+    current_app.config[CONFIG_CREDENTIAL] = azure_credential
+
     # Set up clients for AI Search and Storage
     search_client = SearchClient(
         endpoint=f"https://{AZURE_SEARCH_SERVICE}.search.windows.net",
@@ -573,7 +586,6 @@ async def setup_clients():
         current_app.config[CONFIG_SPEECH_SERVICE_VOICE] = AZURE_SPEECH_SERVICE_VOICE
         # Wait until token is needed to fetch for the first time
         current_app.config[CONFIG_SPEECH_SERVICE_TOKEN] = None
-        current_app.config[CONFIG_CREDENTIAL] = azure_credential
 
     if OPENAI_HOST.startswith("azure"):
         if OPENAI_HOST == "azure_custom":
@@ -628,6 +640,7 @@ async def setup_clients():
     current_app.config[CONFIG_SPEECH_OUTPUT_BROWSER_ENABLED] = USE_SPEECH_OUTPUT_BROWSER
     current_app.config[CONFIG_SPEECH_OUTPUT_AZURE_ENABLED] = USE_SPEECH_OUTPUT_AZURE
     current_app.config[CONFIG_CHAT_HISTORY_BROWSER_ENABLED] = USE_CHAT_HISTORY_BROWSER
+    current_app.config[CONFIG_CHAT_HISTORY_COSMOS_ENABLED] = USE_CHAT_HISTORY_COSMOS
 
     # Various approaches to integrate GPT and external knowledge, most applications will use a single one of these patterns
     # or some derivative, here we include several for exploration purposes
@@ -717,6 +730,7 @@ async def close_clients():
 def create_app():
     app = Quart(__name__)
     app.register_blueprint(bp)
+    app.register_blueprint(chat_history_cosmosdb_bp)
 
     if os.getenv("APPLICATIONINSIGHTS_CONNECTION_STRING"):
         app.logger.info("APPLICATIONINSIGHTS_CONNECTION_STRING is set, enabling Azure Monitor")
diff --git a/app/backend/chat_history/__init__.py b/app/backend/chat_history/__init__.py
new file mode 100644
index 0000000000..e69de29bb2
diff --git a/app/backend/chat_history/cosmosdb.py b/app/backend/chat_history/cosmosdb.py
new file mode 100644
index 0000000000..49760970f7
--- /dev/null
+++ b/app/backend/chat_history/cosmosdb.py
@@ -0,0 +1,192 @@
+import os
+import time
+from typing import Any, Dict, Union
+
+from azure.cosmos.aio import ContainerProxy, CosmosClient
+from azure.identity.aio import AzureDeveloperCliCredential, ManagedIdentityCredential
+from quart import Blueprint, current_app, jsonify, request
+
+from config import (
+    CONFIG_CHAT_HISTORY_COSMOS_ENABLED,
+    CONFIG_COSMOS_HISTORY_CLIENT,
+    CONFIG_COSMOS_HISTORY_CONTAINER,
+    CONFIG_CREDENTIAL,
+)
+from decorators import authenticated
+from error import error_response
+
+chat_history_cosmosdb_bp = Blueprint("chat_history_cosmos", __name__, static_folder="static")
+
+
+@chat_history_cosmosdb_bp.post("/chat_history")
+@authenticated
+async def post_chat_history(auth_claims: Dict[str, Any]):
+    if not current_app.config[CONFIG_CHAT_HISTORY_COSMOS_ENABLED]:
+        return jsonify({"error": "Chat history not enabled"}), 400
+
+    container: ContainerProxy = current_app.config[CONFIG_COSMOS_HISTORY_CONTAINER]
+    if not container:
+        return jsonify({"error": "Chat history not enabled"}), 400
+
+    entra_oid = auth_claims.get("oid")
+    if not entra_oid:
+        return jsonify({"error": "User OID not found"}), 401
+
+    try:
+        request_json = await request.get_json()
+        id = request_json.get("id")
+        answers = request_json.get("answers")
+        title = answers[0][0][:50] + "..." if len(answers[0][0]) > 50 else answers[0][0]
+        timestamp = int(time.time() * 1000)
+
+        await container.upsert_item(
+            {"id": id, "entra_oid": entra_oid, "title": title, "answers": answers, "timestamp": timestamp}
+        )
+
+        return jsonify({}), 201
+    except Exception as error:
+        return error_response(error, "/chat_history")
+
+
+@chat_history_cosmosdb_bp.post("/chat_history/items")
+@authenticated
+async def get_chat_history(auth_claims: Dict[str, Any]):
+    if not current_app.config[CONFIG_CHAT_HISTORY_COSMOS_ENABLED]:
+        return jsonify({"error": "Chat history not enabled"}), 400
+
+    container: ContainerProxy = current_app.config[CONFIG_COSMOS_HISTORY_CONTAINER]
+    if not container:
+        return jsonify({"error": "Chat history not enabled"}), 400
+
+    entra_oid = auth_claims.get("oid")
+    if not entra_oid:
+        return jsonify({"error": "User OID not found"}), 401
+
+    try:
+        request_json = await request.get_json()
+        count = request_json.get("count", 20)
+        continuation_token = request_json.get("continuation_token")
+
+        res = container.query_items(
+            query="SELECT c.id, c.entra_oid, c.title, c.timestamp FROM c WHERE c.entra_oid = @entra_oid ORDER BY c.timestamp DESC",
+            parameters=[dict(name="@entra_oid", value=entra_oid)],
+            max_item_count=count,
+        )
+
+        # set the continuation token for the next page
+        pager = res.by_page(continuation_token)
+
+        # Get the first page, and the continuation token
+        try:
+            page = await pager.__anext__()
+            continuation_token = pager.continuation_token  # type: ignore
+
+            items = []
+            async for item in page:
+                items.append(
+                    {
+                        "id": item.get("id"),
+                        "entra_oid": item.get("entra_oid"),
+                        "title": item.get("title", "untitled"),
+                        "timestamp": item.get("timestamp"),
+                    }
+                )
+
+        # If there are no more pages, StopAsyncIteration is raised
+        except StopAsyncIteration:
+            items = []
+            continuation_token = None
+
+        return jsonify({"items": items, "continuation_token": continuation_token}), 200
+
+    except Exception as error:
+        return error_response(error, "/chat_history/items")
+
+
+@chat_history_cosmosdb_bp.get("/chat_history/items/<item_id>")
+@authenticated
+async def get_chat_history_session(auth_claims: Dict[str, Any], item_id: str):
+    if not current_app.config[CONFIG_CHAT_HISTORY_COSMOS_ENABLED]:
+        return jsonify({"error": "Chat history not enabled"}), 400
+
+    container: ContainerProxy = current_app.config[CONFIG_COSMOS_HISTORY_CONTAINER]
+    if not container:
+        return jsonify({"error": "Chat history not enabled"}), 400
+
+    entra_oid = auth_claims.get("oid")
+    if not entra_oid:
+        return jsonify({"error": "User OID not found"}), 401
+
+    try:
+        res = await container.read_item(item=item_id, partition_key=entra_oid)
+        return (
+            jsonify(
+                {
+                    "id": res.get("id"),
+                    "entra_oid": res.get("entra_oid"),
+                    "title": res.get("title", "untitled"),
+                    "timestamp": res.get("timestamp"),
+                    "answers": res.get("answers", []),
+                }
+            ),
+            200,
+        )
+    except Exception as error:
+        return error_response(error, f"/chat_history/items/{item_id}")
+
+
+@chat_history_cosmosdb_bp.delete("/chat_history/items/<item_id>")
+@authenticated
+async def delete_chat_history_session(auth_claims: Dict[str, Any], item_id: str):
+    if not current_app.config[CONFIG_CHAT_HISTORY_COSMOS_ENABLED]:
+        return jsonify({"error": "Chat history not enabled"}), 400
+
+    container: ContainerProxy = current_app.config[CONFIG_COSMOS_HISTORY_CONTAINER]
+    if not container:
+        return jsonify({"error": "Chat history not enabled"}), 400
+
+    entra_oid = auth_claims.get("oid")
+    if not entra_oid:
+        return jsonify({"error": "User OID not found"}), 401
+
+    try:
+        await container.delete_item(item=item_id, partition_key=entra_oid)
+        return jsonify({}), 204
+    except Exception as error:
+        return error_response(error, f"/chat_history/items/{item_id}")
+
+
+@chat_history_cosmosdb_bp.before_app_serving
+async def setup_clients():
+    USE_CHAT_HISTORY_COSMOS = os.getenv("USE_CHAT_HISTORY_COSMOS", "").lower() == "true"
+    AZURE_COSMOSDB_ACCOUNT = os.getenv("AZURE_COSMOSDB_ACCOUNT")
+    AZURE_CHAT_HISTORY_DATABASE = os.getenv("AZURE_CHAT_HISTORY_DATABASE")
+    AZURE_CHAT_HISTORY_CONTAINER = os.getenv("AZURE_CHAT_HISTORY_CONTAINER")
+
+    azure_credential: Union[AzureDeveloperCliCredential, ManagedIdentityCredential] = current_app.config[
+        CONFIG_CREDENTIAL
+    ]
+
+    if USE_CHAT_HISTORY_COSMOS:
+        current_app.logger.info("USE_CHAT_HISTORY_COSMOS is true, setting up CosmosDB client")
+        if not AZURE_COSMOSDB_ACCOUNT:
+            raise ValueError("AZURE_COSMOSDB_ACCOUNT must be set when USE_CHAT_HISTORY_COSMOS is true")
+        if not AZURE_CHAT_HISTORY_DATABASE:
+            raise ValueError("AZURE_CHAT_HISTORY_DATABASE must be set when USE_CHAT_HISTORY_COSMOS is true")
+        if not AZURE_CHAT_HISTORY_CONTAINER:
+            raise ValueError("AZURE_CHAT_HISTORY_CONTAINER must be set when USE_CHAT_HISTORY_COSMOS is true")
+        cosmos_client = CosmosClient(
+            url=f"https://{AZURE_COSMOSDB_ACCOUNT}.documents.azure.com:443/", credential=azure_credential
+        )
+        cosmos_db = cosmos_client.get_database_client(AZURE_CHAT_HISTORY_DATABASE)
+        cosmos_container = cosmos_db.get_container_client(AZURE_CHAT_HISTORY_CONTAINER)
+
+        current_app.config[CONFIG_COSMOS_HISTORY_CLIENT] = cosmos_client
+        current_app.config[CONFIG_COSMOS_HISTORY_CONTAINER] = cosmos_container
+
+
+@chat_history_cosmosdb_bp.after_app_serving
+async def close_clients():
+    if current_app.config.get(CONFIG_COSMOS_HISTORY_CLIENT):
+        cosmos_client: CosmosClient = current_app.config[CONFIG_COSMOS_HISTORY_CLIENT]
+        await cosmos_client.close()
diff --git a/app/backend/config.py b/app/backend/config.py
index e5f274fa38..eaba154116 100644
--- a/app/backend/config.py
+++ b/app/backend/config.py
@@ -23,3 +23,6 @@
 CONFIG_SPEECH_SERVICE_TOKEN = "speech_service_token"
 CONFIG_SPEECH_SERVICE_VOICE = "speech_service_voice"
 CONFIG_CHAT_HISTORY_BROWSER_ENABLED = "chat_history_browser_enabled"
+CONFIG_CHAT_HISTORY_COSMOS_ENABLED = "chat_history_cosmos_enabled"
+CONFIG_COSMOS_HISTORY_CLIENT = "cosmos_history_client"
+CONFIG_COSMOS_HISTORY_CONTAINER = "cosmos_history_container"
diff --git a/app/backend/core/sessionhelper.py b/app/backend/core/sessionhelper.py
index 28dd0e811b..ddda8e03b7 100644
--- a/app/backend/core/sessionhelper.py
+++ b/app/backend/core/sessionhelper.py
@@ -2,7 +2,11 @@
 from typing import Union
 
 
-def create_session_id(config_chat_history_browser_enabled: bool) -> Union[str, None]:
+def create_session_id(
+    config_chat_history_cosmos_enabled: bool, config_chat_history_browser_enabled: bool
+) -> Union[str, None]:
+    if config_chat_history_cosmos_enabled:
+        return str(uuid.uuid4())
     if config_chat_history_browser_enabled:
         return str(uuid.uuid4())
     return None
diff --git a/app/backend/decorators.py b/app/backend/decorators.py
index 32f6b9a2b5..f4becc4b70 100644
--- a/app/backend/decorators.py
+++ b/app/backend/decorators.py
@@ -1,6 +1,6 @@
 import logging
 from functools import wraps
-from typing import Any, Callable, Dict
+from typing import Any, Callable, Dict, TypeVar, cast
 
 from quart import abort, current_app, request
 
@@ -37,19 +37,22 @@ async def auth_handler(path=""):
     return auth_handler
 
 
-def authenticated(route_fn: Callable[[Dict[str, Any]], Any]):
+_C = TypeVar("_C", bound=Callable[..., Any])
+
+
+def authenticated(route_fn: _C) -> _C:
     """
     Decorator for routes that might require access control. Unpacks Authorization header information into an auth_claims dictionary
     """
 
     @wraps(route_fn)
-    async def auth_handler():
+    async def auth_handler(*args, **kwargs):
         auth_helper = current_app.config[CONFIG_AUTH_CLIENT]
         try:
             auth_claims = await auth_helper.get_auth_claims_if_enabled(request.headers)
         except AuthError:
             abort(403)
 
-        return await route_fn(auth_claims)
+        return await route_fn(auth_claims, *args, **kwargs)
 
-    return auth_handler
+    return cast(_C, auth_handler)
diff --git a/app/backend/requirements.in b/app/backend/requirements.in
index 99cb44e678..765a72c486 100644
--- a/app/backend/requirements.in
+++ b/app/backend/requirements.in
@@ -7,6 +7,7 @@ tiktoken
 tenacity
 azure-ai-documentintelligence
 azure-cognitiveservices-speech
+azure-cosmos
 azure-search-documents==11.6.0b6
 azure-storage-blob
 azure-storage-file-datalake
diff --git a/app/backend/requirements.txt b/app/backend/requirements.txt
index fe339f08c1..0dcf9f86a4 100644
--- a/app/backend/requirements.txt
+++ b/app/backend/requirements.txt
@@ -34,6 +34,7 @@ azure-core==1.30.2
     # via
     #   azure-ai-documentintelligence
     #   azure-core-tracing-opentelemetry
+    #   azure-cosmos
     #   azure-identity
     #   azure-monitor-opentelemetry
     #   azure-monitor-opentelemetry-exporter
@@ -44,6 +45,8 @@ azure-core==1.30.2
     #   msrest
 azure-core-tracing-opentelemetry==1.0.0b11
     # via azure-monitor-opentelemetry
+azure-cosmos==4.7.0
+    # via -r requirements.in
 azure-identity==1.17.1
     # via
     #   -r requirements.in
@@ -402,6 +405,7 @@ typing-extensions==4.12.2
     # via
     #   azure-ai-documentintelligence
     #   azure-core
+    #   azure-cosmos
     #   azure-identity
     #   azure-search-documents
     #   azure-storage-blob
diff --git a/app/frontend/src/api/api.ts b/app/frontend/src/api/api.ts
index f2cd36507e..76636d4d05 100644
--- a/app/frontend/src/api/api.ts
+++ b/app/frontend/src/api/api.ts
@@ -1,6 +1,6 @@
 const BACKEND_URI = "";
 
-import { ChatAppResponse, ChatAppResponseOrError, ChatAppRequest, Config, SimpleAPIResponse } from "./models";
+import { ChatAppResponse, ChatAppResponseOrError, ChatAppRequest, Config, SimpleAPIResponse, HistoryListApiResponse, HistroyApiResponse } from "./models";
 import { useLogin, getToken, isUsingAppServicesLogin } from "../authConfig";
 
 export async function getHeaders(idToken: string | undefined): Promise<Record<string, string>> {
@@ -126,3 +126,65 @@ export async function listUploadedFilesApi(idToken: string): Promise<string[]> {
     const dataResponse: string[] = await response.json();
     return dataResponse;
 }
+
+export async function postChatHistoryApi(item: any, idToken: string): Promise<any> {
+    const headers = await getHeaders(idToken);
+    const response = await fetch("/chat_history", {
+        method: "POST",
+        headers: { ...headers, "Content-Type": "application/json" },
+        body: JSON.stringify(item)
+    });
+
+    if (!response.ok) {
+        throw new Error(`Posting chat history failed: ${response.statusText}`);
+    }
+
+    const dataResponse: any = await response.json();
+    return dataResponse;
+}
+
+export async function getChatHistoryListApi(count: number, continuationToken: string | undefined, idToken: string): Promise<HistoryListApiResponse> {
+    const headers = await getHeaders(idToken);
+    const response = await fetch("/chat_history/items", {
+        method: "POST",
+        headers: { ...headers, "Content-Type": "application/json" },
+        body: JSON.stringify({ count: count, continuation_token: continuationToken })
+    });
+
+    if (!response.ok) {
+        throw new Error(`Getting chat histories failed: ${response.statusText}`);
+    }
+
+    const dataResponse: HistoryListApiResponse = await response.json();
+    return dataResponse;
+}
+
+export async function getChatHistoryApi(id: string, idToken: string): Promise<HistroyApiResponse> {
+    const headers = await getHeaders(idToken);
+    const response = await fetch(`/chat_history/items/${id}`, {
+        method: "GET",
+        headers: { ...headers, "Content-Type": "application/json" }
+    });
+
+    if (!response.ok) {
+        throw new Error(`Getting chat history failed: ${response.statusText}`);
+    }
+
+    const dataResponse: HistroyApiResponse = await response.json();
+    return dataResponse;
+}
+
+export async function deleteChatHistoryApi(id: string, idToken: string): Promise<any> {
+    const headers = await getHeaders(idToken);
+    const response = await fetch(`/chat_history/items/${id}`, {
+        method: "DELETE",
+        headers: { ...headers, "Content-Type": "application/json" }
+    });
+
+    if (!response.ok) {
+        throw new Error(`Deleting chat history failed: ${response.statusText}`);
+    }
+
+    const dataResponse: any = await response.json();
+    return dataResponse;
+}
diff --git a/app/frontend/src/api/models.ts b/app/frontend/src/api/models.ts
index 633af8bd3f..ef1fa154b0 100644
--- a/app/frontend/src/api/models.ts
+++ b/app/frontend/src/api/models.ts
@@ -91,6 +91,7 @@ export type Config = {
     showSpeechOutputBrowser: boolean;
     showSpeechOutputAzure: boolean;
     showChatHistoryBrowser: boolean;
+    showChatHistoryCosmos: boolean;
 };
 
 export type SimpleAPIResponse = {
@@ -104,3 +105,21 @@ export interface SpeechConfig {
     isPlaying: boolean;
     setIsPlaying: (isPlaying: boolean) => void;
 }
+
+export type HistoryListApiResponse = {
+    items: {
+        id: string;
+        entra_oid: string;
+        title: string;
+        timestamp: number;
+    }[];
+    continuation_token?: string;
+};
+
+export type HistroyApiResponse = {
+    id: string;
+    entra_oid: string;
+    title: string;
+    answers: any;
+    timestamp: number;
+};
diff --git a/app/frontend/src/components/HistoryPanel/HistoryPanel.tsx b/app/frontend/src/components/HistoryPanel/HistoryPanel.tsx
index b70a723305..acaf3b7870 100644
--- a/app/frontend/src/components/HistoryPanel/HistoryPanel.tsx
+++ b/app/frontend/src/components/HistoryPanel/HistoryPanel.tsx
@@ -1,4 +1,6 @@
-import { Panel, PanelType } from "@fluentui/react";
+import { useMsal } from "@azure/msal-react";
+import { getToken, useLogin } from "../../authConfig";
+import { Panel, PanelType, Spinner } from "@fluentui/react";
 import { useEffect, useMemo, useRef, useState } from "react";
 import { HistoryData, HistoryItem } from "../HistoryItem";
 import { Answers, HistoryProviderOptions } from "../HistoryProviders/IProvider";
@@ -26,6 +28,8 @@ export const HistoryPanel = ({
     const [isLoading, setIsLoading] = useState(false);
     const [hasMoreHistory, setHasMoreHistory] = useState(false);
 
+    const client = useLogin ? useMsal().instance : undefined;
+
     useEffect(() => {
         if (!isOpen) return;
         if (notify) {
@@ -37,7 +41,8 @@ export const HistoryPanel = ({
 
     const loadMoreHistory = async () => {
         setIsLoading(() => true);
-        const items = await historyManager.getNextItems(HISTORY_COUNT_PER_LOAD);
+        const token = client ? await getToken(client) : undefined;
+        const items = await historyManager.getNextItems(HISTORY_COUNT_PER_LOAD, token);
         if (items.length === 0) {
             setHasMoreHistory(false);
         }
@@ -46,14 +51,16 @@ export const HistoryPanel = ({
     };
 
     const handleSelect = async (id: string) => {
-        const item = await historyManager.getItem(id);
+        const token = client ? await getToken(client) : undefined;
+        const item = await historyManager.getItem(id, token);
         if (item) {
             onChatSelected(item);
         }
     };
 
     const handleDelete = async (id: string) => {
-        await historyManager.deleteItem(id);
+        const token = client ? await getToken(client) : undefined;
+        await historyManager.deleteItem(id, token);
         setHistory(prevHistory => prevHistory.filter(item => item.id !== id));
     };
 
@@ -85,7 +92,8 @@ export const HistoryPanel = ({
                         ))}
                     </div>
                 ))}
-                {history.length === 0 && <p>{t("history.noHistory")}</p>}
+                {isLoading && <Spinner style={{ marginTop: "10px" }} />}
+                {history.length === 0 && !isLoading && <p>{t("history.noHistory")}</p>}
                 {hasMoreHistory && !isLoading && <InfiniteLoadingButton func={loadMoreHistory} />}
             </div>
         </Panel>
diff --git a/app/frontend/src/components/HistoryProviders/CosmosDB.ts b/app/frontend/src/components/HistoryProviders/CosmosDB.ts
new file mode 100644
index 0000000000..4d613b28a8
--- /dev/null
+++ b/app/frontend/src/components/HistoryProviders/CosmosDB.ts
@@ -0,0 +1,51 @@
+import { IHistoryProvider, Answers, HistoryProviderOptions, HistoryMetaData } from "./IProvider";
+import { deleteChatHistoryApi, getChatHistoryApi, getChatHistoryListApi, postChatHistoryApi } from "../../api";
+
+export class CosmosDBProvider implements IHistoryProvider {
+    getProviderName = () => HistoryProviderOptions.CosmosDB;
+
+    private continuationToken: string | undefined;
+    private isItemEnd: boolean = false;
+
+    resetContinuationToken() {
+        this.continuationToken = undefined;
+        this.isItemEnd = false;
+    }
+
+    async getNextItems(count: number, idToken?: string): Promise<HistoryMetaData[]> {
+        if (this.isItemEnd) {
+            return [];
+        }
+
+        try {
+            const response = await getChatHistoryListApi(count, this.continuationToken, idToken || "");
+            this.continuationToken = response.continuation_token;
+            if (!this.continuationToken) {
+                this.isItemEnd = true;
+            }
+            return response.items.map(item => ({
+                id: item.id,
+                title: item.title,
+                timestamp: item.timestamp
+            }));
+        } catch (e) {
+            console.error(e);
+            return [];
+        }
+    }
+
+    async addItem(id: string, answers: Answers, idToken?: string): Promise<void> {
+        await postChatHistoryApi({ id, answers }, idToken || "");
+        return;
+    }
+
+    async getItem(id: string, idToken?: string): Promise<Answers | null> {
+        const response = await getChatHistoryApi(id, idToken || "");
+        return response.answers || null;
+    }
+
+    async deleteItem(id: string, idToken?: string): Promise<void> {
+        await deleteChatHistoryApi(id, idToken || "");
+        return;
+    }
+}
diff --git a/app/frontend/src/components/HistoryProviders/HistoryManager.ts b/app/frontend/src/components/HistoryProviders/HistoryManager.ts
index fa31c6314d..e796d04933 100644
--- a/app/frontend/src/components/HistoryProviders/HistoryManager.ts
+++ b/app/frontend/src/components/HistoryProviders/HistoryManager.ts
@@ -2,12 +2,15 @@ import { useMemo } from "react";
 import { IHistoryProvider, HistoryProviderOptions } from "../HistoryProviders/IProvider";
 import { NoneProvider } from "../HistoryProviders/None";
 import { IndexedDBProvider } from "../HistoryProviders/IndexedDB";
+import { CosmosDBProvider } from "../HistoryProviders/CosmosDB";
 
 export const useHistoryManager = (provider: HistoryProviderOptions): IHistoryProvider => {
     const providerInstance = useMemo(() => {
         switch (provider) {
             case HistoryProviderOptions.IndexedDB:
                 return new IndexedDBProvider("chat-database", "chat-history");
+            case HistoryProviderOptions.CosmosDB:
+                return new CosmosDBProvider();
             case HistoryProviderOptions.None:
             default:
                 return new NoneProvider();
diff --git a/app/frontend/src/components/HistoryProviders/IProvider.ts b/app/frontend/src/components/HistoryProviders/IProvider.ts
index 330437a8ec..026443d681 100644
--- a/app/frontend/src/components/HistoryProviders/IProvider.ts
+++ b/app/frontend/src/components/HistoryProviders/IProvider.ts
@@ -5,14 +5,15 @@ export type Answers = [user: string, response: ChatAppResponse][];
 
 export const enum HistoryProviderOptions {
     None = "none",
-    IndexedDB = "indexedDB"
+    IndexedDB = "indexedDB",
+    CosmosDB = "cosmosDB"
 }
 
 export interface IHistoryProvider {
     getProviderName(): HistoryProviderOptions;
     resetContinuationToken(): void;
-    getNextItems(count: number): Promise<HistoryMetaData[]>;
-    addItem(id: string, answers: Answers): Promise<void>;
-    getItem(id: string): Promise<Answers | null>;
-    deleteItem(id: string): Promise<void>;
+    getNextItems(count: number, idToken?: string): Promise<HistoryMetaData[]>;
+    addItem(id: string, answers: Answers, idToken?: string): Promise<void>;
+    getItem(id: string, idToken?: string): Promise<Answers | null>;
+    deleteItem(id: string, idToken?: string): Promise<void>;
 }
diff --git a/app/frontend/src/pages/chat/Chat.tsx b/app/frontend/src/pages/chat/Chat.tsx
index 1fa09ec511..7dabff8c7f 100644
--- a/app/frontend/src/pages/chat/Chat.tsx
+++ b/app/frontend/src/pages/chat/Chat.tsx
@@ -83,6 +83,7 @@ const Chat = () => {
     const [showSpeechOutputBrowser, setShowSpeechOutputBrowser] = useState<boolean>(false);
     const [showSpeechOutputAzure, setShowSpeechOutputAzure] = useState<boolean>(false);
     const [showChatHistoryBrowser, setShowChatHistoryBrowser] = useState<boolean>(false);
+    const [showChatHistoryCosmos, setShowChatHistoryCosmos] = useState<boolean>(false);
     const audio = useRef(new Audio()).current;
     const [isPlaying, setIsPlaying] = useState(false);
 
@@ -109,6 +110,7 @@ const Chat = () => {
             setShowSpeechOutputBrowser(config.showSpeechOutputBrowser);
             setShowSpeechOutputAzure(config.showSpeechOutputAzure);
             setShowChatHistoryBrowser(config.showChatHistoryBrowser);
+            setShowChatHistoryCosmos(config.showChatHistoryCosmos);
         });
     };
 
@@ -158,7 +160,11 @@ const Chat = () => {
     const client = useLogin ? useMsal().instance : undefined;
     const { loggedIn } = useContext(LoginContext);
 
-    const historyProvider: HistoryProviderOptions = showChatHistoryBrowser ? HistoryProviderOptions.IndexedDB : HistoryProviderOptions.None;
+    const historyProvider: HistoryProviderOptions = (() => {
+        if (useLogin && showChatHistoryCosmos) return HistoryProviderOptions.CosmosDB;
+        if (showChatHistoryBrowser) return HistoryProviderOptions.IndexedDB;
+        return HistoryProviderOptions.None;
+    })();
     const historyManager = useHistoryManager(historyProvider);
 
     const makeApiRequest = async (question: string) => {
@@ -216,7 +222,8 @@ const Chat = () => {
                 const parsedResponse: ChatAppResponse = await handleAsyncRequest(question, answers, response.body);
                 setAnswers([...answers, [question, parsedResponse]]);
                 if (typeof parsedResponse.session_state === "string" && parsedResponse.session_state !== "") {
-                    historyManager.addItem(parsedResponse.session_state, [...answers, [question, parsedResponse]]);
+                    const token = client ? await getToken(client) : undefined;
+                    historyManager.addItem(parsedResponse.session_state, [...answers, [question, parsedResponse]], token);
                 }
             } else {
                 const parsedResponse: ChatAppResponseOrError = await response.json();
@@ -225,7 +232,8 @@ const Chat = () => {
                 }
                 setAnswers([...answers, [question, parsedResponse as ChatAppResponse]]);
                 if (typeof parsedResponse.session_state === "string" && parsedResponse.session_state !== "") {
-                    historyManager.addItem(parsedResponse.session_state, [...answers, [question, parsedResponse as ChatAppResponse]]);
+                    const token = client ? await getToken(client) : undefined;
+                    historyManager.addItem(parsedResponse.session_state, [...answers, [question, parsedResponse as ChatAppResponse]], token);
                 }
             }
             setSpeechUrls([...speechUrls, null]);
@@ -348,7 +356,9 @@ const Chat = () => {
             </Helmet>
             <div className={styles.commandsSplitContainer}>
                 <div className={styles.commandsContainer}>
-                    {showChatHistoryBrowser && <HistoryButton className={styles.commandButton} onClick={() => setIsHistoryPanelOpen(!isHistoryPanelOpen)} />}
+                    {((useLogin && showChatHistoryCosmos) || showChatHistoryBrowser) && (
+                        <HistoryButton className={styles.commandButton} onClick={() => setIsHistoryPanelOpen(!isHistoryPanelOpen)} />
+                    )}
                 </div>
                 <div className={styles.commandsContainer}>
                     <ClearChatButton className={styles.commandButton} onClick={clearChat} disabled={!lastQuestionRef.current || isLoading} />
@@ -457,7 +467,7 @@ const Chat = () => {
                     />
                 )}
 
-                {showChatHistoryBrowser && (
+                {((useLogin && showChatHistoryCosmos) || showChatHistoryBrowser) && (
                     <HistoryPanel
                         provider={historyProvider}
                         isOpen={isHistoryPanelOpen}
diff --git a/app/frontend/vite.config.ts b/app/frontend/vite.config.ts
index 7fe15e7533..a5248e21b2 100644
--- a/app/frontend/vite.config.ts
+++ b/app/frontend/vite.config.ts
@@ -34,7 +34,8 @@ export default defineConfig({
             "/config": "http://localhost:50505",
             "/upload": "http://localhost:50505",
             "/delete_uploaded": "http://localhost:50505",
-            "/list_uploaded": "http://localhost:50505"
+            "/list_uploaded": "http://localhost:50505",
+            "/chat_history": "http://localhost:50505"
         }
     }
 });
diff --git a/docs/deploy_features.md b/docs/deploy_features.md
index 0d7a47f389..b1291a00b4 100644
--- a/docs/deploy_features.md
+++ b/docs/deploy_features.md
@@ -7,7 +7,8 @@ You should typically enable these features before running `azd up`. Once you've
 * [Using GPT-4](#using-gpt-4)
 * [Using text-embedding-3 models](#using-text-embedding-3-models)
 * [Enabling GPT-4 Turbo with Vision](#enabling-gpt-4-turbo-with-vision)
-* [Enabling chat history](#enabling-chat-history)
+* [Enabling client-side chat history](#enabling-client-side-chat-history)
+* [Enabling persistent chat history with Azure Cosmos DB](#enabling-persistent-chat-history-with-azure-cosmos-db)
 * [Enabling language picker](#enabling-language-picker)
 * [Enabling speech input/output](#enabling-speech-inputoutput)
 * [Enabling Integrated Vectorization](#enabling-integrated-vectorization)
@@ -150,7 +151,7 @@ If you have already deployed:
 
 This section covers the integration of GPT-4 Vision with Azure AI Search. Learn how to enhance your search capabilities with the power of image and text indexing, enabling advanced search functionalities over diverse document types. For a detailed guide on setup and usage, visit our [Enabling GPT-4 Turbo with Vision](gpt4v.md) page.
 
-## Enabling chat history
+## Enabling client-side chat history
 
 This feature allows users to view the chat history of their conversation, stored in the browser using [IndexedDB](https://developer.mozilla.org/docs/Web/API/IndexedDB_API). That means the chat history will be available only on the device where the chat was initiated. To enable browser-stored chat history, run:
 
@@ -158,7 +159,15 @@ This feature allows users to view the chat history of their conversation, stored
 azd env set USE_CHAT_HISTORY_BROWSER true
 ```
 
-In the future, we plan to add support for optionally storing chat history in a server-side storage such as Cosmos DB.
+## Enabling persistent chat history with Azure Cosmos DB
+
+This feature allows authenticated users to view the chat history of their conversations, stored in the server-side storage using [Azure Cosmos DB](https://learn.microsoft.com/azure/cosmos-db/).This option requires that authentication be enabled. The chat history will be persistent and accessible from any device where the user logs in with the same account. To enable server-stored chat history, run:
+
+```shell
+azd env set USE_CHAT_HISTORY_COSMOS true
+```
+
+When both the browser-stored and Cosmos DB options are enabled, Cosmos DB will take precedence over browser-stored chat history.
 
 ## Enabling language picker
 
diff --git a/docs/deploy_lowcost.md b/docs/deploy_lowcost.md
index fd3e33feff..1416f15e4c 100644
--- a/docs/deploy_lowcost.md
+++ b/docs/deploy_lowcost.md
@@ -71,6 +71,14 @@ However, if your goal is to minimize costs while prototyping your application, f
       azd env set USE_LOCAL_HTML_PARSER true
       ```
 
+1. Use the free tier of Azure Cosmos DB:
+
+    ```shell
+    azd env set AZURE_COSMOSDB_SKU free
+    ```
+
+    Limitation: You can have only one free Cosmos DB account. To keep your account free of charge, ensure that you do not exceed the free tier limits. For more information, see the [Azure Cosmos DB lifetime free tier](https://learn.microsoft.com/azure/cosmos-db/free-tier).
+
 1. Turn off Azure Monitor (Application Insights):
 
     ```shell
diff --git a/docs/other_samples.md b/docs/other_samples.md
index 2e678d5ae2..2e144eef98 100644
--- a/docs/other_samples.md
+++ b/docs/other_samples.md
@@ -31,7 +31,7 @@ Feature comparison:
 | RAG approach | Multiple approaches | Only via ChatCompletion API data_sources |
 | Vector support | ✅ Yes | ✅ Yes |
 | Data ingestion | ✅ Yes ([Many formats](data_ingestion.md#supported-document-formats)) | ✅ Yes ([Many formats](https://learn.microsoft.com/azure/ai-services/openai/concepts/use-your-data?tabs=ai-search#data-formats-and-file-types)) |
-| Persistent chat history | ❌ No (browser tab only) | ✅ Yes, in CosmosDB |
+| Persistent chat history | ✅ Yes | ✅ Yes |
 | User feedback | ❌ No | ✅ Yes |
 | GPT-4-vision |  ✅ Yes | ❌ No |
 | Auth + ACL |  ✅ Yes | ✅ Yes |
diff --git a/infra/core/security/documentdb-sql-role.bicep b/infra/core/security/documentdb-sql-role.bicep
new file mode 100644
index 0000000000..3a8c2f74d1
--- /dev/null
+++ b/infra/core/security/documentdb-sql-role.bicep
@@ -0,0 +1,27 @@
+metadata name = 'DocumentDB Database Account SQL Role Assignments.'
+metadata description = 'Assign RBAC role for data plane access to Azure Cosmos DB for NoSQL.'
+
+@description('Name of the Azure Cosmos DB for NoSQL account.')
+param databaseAccountName string
+
+@description('Id of the identity/principal to assign this role in the context of the account.')
+param principalId string = ''
+
+@description('Id of the role definition to assign to the targeted principal in the context of the account.')
+param roleDefinitionId string
+
+resource databaseAccount 'Microsoft.DocumentDB/databaseAccounts@2023-04-15' existing = {
+  name: databaseAccountName
+}
+
+resource sqlRoleAssignment 'Microsoft.DocumentDB/databaseAccounts/sqlRoleAssignments@2023-04-15' = {
+  name: guid(databaseAccount.id, principalId, roleDefinitionId)
+  parent: databaseAccount
+  properties: {
+    principalId: principalId
+    roleDefinitionId: roleDefinitionId
+    scope: databaseAccount.id
+  }
+}
+
+output sqlRoleAssignmentId string = sqlRoleAssignment.id
diff --git a/infra/main.bicep b/infra/main.bicep
index 9339abe02f..344623df20 100644
--- a/infra/main.bicep
+++ b/infra/main.bicep
@@ -60,6 +60,15 @@ param speechServiceSkuName string // Set in main.parameters.json
 param speechServiceVoice string = ''
 param useGPT4V bool = false
 
+@allowed(['free', 'provisioned', 'serverless'])
+param cosmosDbSkuName string // Set in main.parameters.json
+param cosmodDbResourceGroupName string = ''
+param cosmosDbLocation string = ''
+param cosmosDbAccountName string = ''
+param cosmosDbThroughput int = 400
+param chatHistoryDatabaseName string = 'chat-database'
+param chatHistoryContainerName string = 'chat-history'
+
 // https://learn.microsoft.com/azure/ai-services/openai/concepts/models?tabs=python-secure%2Cstandard%2Cstandard-chat-completions#standard-deployment-model-availability
 @description('Location for the OpenAI resource group')
 @allowed([
@@ -200,6 +209,8 @@ param useSpeechOutputBrowser bool = false
 param useSpeechOutputAzure bool = false
 @description('Use chat history feature in browser')
 param useChatHistoryBrowser bool = false
+@description('Use chat history feature in CosmosDB')
+param useChatHistoryCosmos bool = false
 @description('Show options to use vector embeddings for searching in the app UI')
 param useVectors bool = false
 @description('Use Built-in integrated Vectorization feature of AI Search to vectorize and ingest documents')
@@ -268,6 +279,10 @@ resource speechResourceGroup 'Microsoft.Resources/resourceGroups@2021-04-01' exi
   name: !empty(speechServiceResourceGroupName) ? speechServiceResourceGroupName : resourceGroup.name
 }
 
+resource cosmosDbResourceGroup 'Microsoft.Resources/resourceGroups@2021-04-01' existing = if (!empty(cosmodDbResourceGroupName)) {
+  name: !empty(cosmodDbResourceGroupName) ? cosmodDbResourceGroupName : resourceGroup.name
+}
+
 // Monitor application with Azure Monitor
 module monitoring 'core/monitor/monitoring.bicep' = if (useApplicationInsights) {
   name: 'monitoring'
@@ -332,7 +347,12 @@ var appEnvVariables = {
   USE_SPEECH_INPUT_BROWSER: useSpeechInputBrowser
   USE_SPEECH_OUTPUT_BROWSER: useSpeechOutputBrowser
   USE_SPEECH_OUTPUT_AZURE: useSpeechOutputAzure
+  // Chat history settings
   USE_CHAT_HISTORY_BROWSER: useChatHistoryBrowser
+  USE_CHAT_HISTORY_COSMOS: useChatHistoryCosmos
+  AZURE_COSMOSDB_ACCOUNT: (useAuthentication && useChatHistoryCosmos) ? cosmosDb.outputs.name : ''
+  AZURE_CHAT_HISTORY_DATABASE: chatHistoryDatabaseName
+  AZURE_CHAT_HISTORY_CONTAINER: chatHistoryContainerName
   // Shared by all OpenAI deployments
   OPENAI_HOST: openAiHost
   AZURE_OPENAI_EMB_MODEL_NAME: embedding.modelName
@@ -671,6 +691,64 @@ module userStorage 'core/storage/storage-account.bicep' = if (useUserUpload) {
   }
 }
 
+module cosmosDb 'br/public:avm/res/document-db/database-account:0.6.1' = if (useAuthentication && useChatHistoryCosmos) {
+  name: 'cosmosdb'
+  scope: cosmosDbResourceGroup
+  params: {
+    name: !empty(cosmosDbAccountName) ? cosmosDbAccountName : '${abbrs.documentDBDatabaseAccounts}${resourceToken}'
+    location: !empty(cosmosDbLocation) ? cosmosDbLocation : location
+    locations: [
+      {
+        locationName: !empty(cosmosDbLocation) ? cosmosDbLocation : location
+        failoverPriority: 0
+        isZoneRedundant: false
+      }
+    ]
+    enableFreeTier: cosmosDbSkuName == 'free'
+    capabilitiesToAdd: cosmosDbSkuName == 'serverless' ? ['EnableServerless'] : []
+    networkRestrictions: {
+      ipRules: []
+      networkAclBypass: bypass
+      publicNetworkAccess: publicNetworkAccess
+      virtualNetworkRules: []
+    }
+    sqlDatabases: [
+      {
+        name: chatHistoryDatabaseName
+        throughput: (cosmosDbSkuName == 'serverless') ? null : cosmosDbThroughput
+        containers: [
+          {
+            name: chatHistoryContainerName
+            paths: [
+              '/entra_oid'
+            ]
+            indexingPolicy: {
+              indexingMode: 'consistent'
+              automatic: true
+              includedPaths: [
+                {
+                  path: '/*'
+                }
+              ]
+              excludedPaths: [
+                {
+                  path: '/title/?'
+                }
+                {
+                  path: '/answers/*'
+                }
+                {
+                  path: '/"_etag"/?'
+                }
+              ]
+            }
+          }
+        ]
+      }
+    ]
+  }
+}
+
 // USER ROLES
 var principalType = empty(runningOnGh) && empty(runningOnAdo) ? 'User' : 'ServicePrincipal'
 
@@ -765,6 +843,31 @@ module searchSvcContribRoleUser 'core/security/role.bicep' = {
   }
 }
 
+module cosmosDbAccountContribRoleUser 'core/security/role.bicep' = if (useAuthentication && useChatHistoryCosmos) {
+  scope: cosmosDbResourceGroup
+  name: 'cosmosdb-account-contrib-role-user'
+  params: {
+    principalId: principalId
+    roleDefinitionId: '5bd9cd88-fe45-4216-938b-f97437e15450'
+    principalType: principalType
+  }
+}
+
+// RBAC for Cosmos DB
+// https://learn.microsoft.com/azure/cosmos-db/nosql/security/how-to-grant-data-plane-role-based-access
+module cosmosDbDataContribRoleUser 'core/security/documentdb-sql-role.bicep' = if (useAuthentication && useChatHistoryCosmos) {
+  scope: cosmosDbResourceGroup
+  name: 'cosmosdb-data-contrib-role-user'
+  params: {
+    databaseAccountName: (useAuthentication && useChatHistoryCosmos) ? cosmosDb.outputs.name : ''
+    principalId: principalId
+    // Cosmos DB Built-in Data Contributor role
+    roleDefinitionId: (useAuthentication && useChatHistoryCosmos)
+      ? '/${subscription().id}/resourceGroups/${cosmosDb.outputs.resourceGroupName}/providers/Microsoft.DocumentDB/databaseAccounts/${cosmosDb.outputs.name}/sqlRoleDefinitions/00000000-0000-0000-0000-000000000002'
+      : ''
+  }
+}
+
 // SYSTEM IDENTITIES
 module openAiRoleBackend 'core/security/role.bicep' = if (isAzureOpenAiHost && deployAzureOpenAi) {
   scope: openAiResourceGroup
@@ -848,6 +951,23 @@ module speechRoleBackend 'core/security/role.bicep' = {
   }
 }
 
+// RBAC for Cosmos DB
+// https://learn.microsoft.com/azure/cosmos-db/nosql/security/how-to-grant-data-plane-role-based-access
+module cosmosDbRoleBackend 'core/security/documentdb-sql-role.bicep' = if (useAuthentication && useChatHistoryCosmos) {
+  scope: cosmosDbResourceGroup
+  name: 'cosmosdb-role-backend'
+  params: {
+    databaseAccountName: (useAuthentication && useChatHistoryCosmos) ? cosmosDb.outputs.name : ''
+    principalId: (deploymentTarget == 'appservice')
+      ? backend.outputs.identityPrincipalId
+      : acaBackend.outputs.identityPrincipalId
+    // Cosmos DB Built-in Data Contributor role
+    roleDefinitionId: (useAuthentication && useChatHistoryCosmos)
+      ? '/${subscription().id}/resourceGroups/${cosmosDb.outputs.resourceGroupName}/providers/Microsoft.DocumentDB/databaseAccounts/${cosmosDb.outputs.name}/sqlRoleDefinitions/00000000-0000-0000-0000-000000000002'
+      : ''
+  }
+}
+
 module isolation 'network-isolation.bicep' = {
   name: 'networks'
   scope: resourceGroup
@@ -894,6 +1014,11 @@ var otherPrivateEndpointConnections = (usePrivateEndpoint && deploymentTarget ==
         dnsZoneName: 'privatelink.azurewebsites.net'
         resourceIds: [backend.outputs.id]
       }
+      {
+        groupId: 'cosmosdb'
+        dnsZoneName: 'privatelink.documents.azure.com'
+        resourceIds: (useAuthentication && useChatHistoryCosmos) ? [cosmosDb.outputs.resourceId] : []
+      }
     ]
   : []
 
@@ -1000,6 +1125,10 @@ output AZURE_SEARCH_SERVICE_RESOURCE_GROUP string = searchServiceResourceGroup.n
 output AZURE_SEARCH_SEMANTIC_RANKER string = actualSearchServiceSemanticRankerLevel
 output AZURE_SEARCH_SERVICE_ASSIGNED_USERID string = searchService.outputs.principalId
 
+output AZURE_COSMOSDB_ACCOUNT string = (useAuthentication && useChatHistoryCosmos) ? cosmosDb.outputs.name : ''
+output AZURE_CHAT_HISTORY_DATABASE string = chatHistoryDatabaseName
+output AZURE_CHAT_HISTORY_CONTAINER string = chatHistoryContainerName
+
 output AZURE_STORAGE_ACCOUNT string = storage.outputs.name
 output AZURE_STORAGE_CONTAINER string = storageContainerName
 output AZURE_STORAGE_RESOURCE_GROUP string = storageResourceGroup.name
diff --git a/infra/main.parameters.json b/infra/main.parameters.json
index 1a63507f78..a7ba80373e 100644
--- a/infra/main.parameters.json
+++ b/infra/main.parameters.json
@@ -185,9 +185,6 @@
     "useSpeechOutputAzure": {
       "value": "${USE_SPEECH_OUTPUT_AZURE=false}"
     },
-    "useChatHistoryBrowser": {
-      "value": "${USE_CHAT_HISTORY_BROWSER=false}"
-    },
     "speechServiceName": {
       "value": "${AZURE_SPEECH_SERVICE}"
     },
@@ -200,6 +197,27 @@
     "speechServiceLocation": {
       "value": "${AZURE_SPEECH_SERVICE_LOCATION}"
     },
+    "useChatHistoryBrowser": {
+      "value": "${USE_CHAT_HISTORY_BROWSER=false}"
+    },
+    "useChatHistoryCosmos": {
+      "value": "${USE_CHAT_HISTORY_COSMOS=false}"
+    },
+    "cosmosDbSkuName": {
+      "value": "${AZURE_COSMOSDB_SKU=serverless}"
+    },
+    "cosmodDbResourceGroupName": {
+      "value": "${AZURE_COSMOSDB_RESOURCE_GROUP}"
+    },
+    "cosmosDbLocation": {
+      "value": "${AZURE_COSMOSDB_LOCATION}"
+    },
+    "cosmosDbAccountName": {
+      "value": "${AZURE_COSMOSDB_ACCOUNT}"
+    },
+    "cosmosDbThroughput": {
+      "value": "${AZURE_COSMOSDB_THROUGHPUT}"
+    },
     "speechServiceVoice": {
       "value": "${AZURE_SPEECH_SERVICE_VOICE}"
     },
diff --git a/tests/conftest.py b/tests/conftest.py
index 279198b18c..cfc5326f31 100644
--- a/tests/conftest.py
+++ b/tests/conftest.py
@@ -419,6 +419,11 @@ async def auth_public_documents_client(
     monkeypatch.setenv("USE_LOCAL_PDF_PARSER", "true")
     monkeypatch.setenv("USE_LOCAL_HTML_PARSER", "true")
     monkeypatch.setenv("AZURE_DOCUMENTINTELLIGENCE_SERVICE", "test-documentintelligence-service")
+    monkeypatch.setenv("USE_CHAT_HISTORY_COSMOS", "true")
+    monkeypatch.setenv("AZURE_COSMOSDB_ACCOUNT", "test-cosmosdb-account")
+    monkeypatch.setenv("AZURE_CHAT_HISTORY_DATABASE", "test-cosmosdb-database")
+    monkeypatch.setenv("AZURE_CHAT_HISTORY_CONTAINER", "test-cosmosdb-container")
+
     for key, value in request.param.items():
         monkeypatch.setenv(key, value)
 
diff --git a/tests/snapshots/test_app/test_chat_text_filter_public_documents/auth_public_documents_client0/result.json b/tests/snapshots/test_app/test_chat_text_filter_public_documents/auth_public_documents_client0/result.json
index bb67fe067b..04fea8c332 100644
--- a/tests/snapshots/test_app/test_chat_text_filter_public_documents/auth_public_documents_client0/result.json
+++ b/tests/snapshots/test_app/test_chat_text_filter_public_documents/auth_public_documents_client0/result.json
@@ -99,6 +99,5 @@
     "message": {
         "content": "The capital of France is Paris. [Benefit_Options-2.pdf].",
         "role": "assistant"
-    },
-    "session_state": null
+    }
 }
\ No newline at end of file
diff --git a/tests/snapshots/test_cosmosdb/test_chathistory_getitem/auth_public_documents_client0/result.json b/tests/snapshots/test_cosmosdb/test_chathistory_getitem/auth_public_documents_client0/result.json
new file mode 100644
index 0000000000..62f6f0f0f5
--- /dev/null
+++ b/tests/snapshots/test_cosmosdb/test_chathistory_getitem/auth_public_documents_client0/result.json
@@ -0,0 +1,11 @@
+{
+    "answers": [
+        [
+            "This is a test message"
+        ]
+    ],
+    "entra_oid": "OID_X",
+    "id": "123",
+    "timestamp": 123456789,
+    "title": "This is a test message"
+}
\ No newline at end of file
diff --git a/tests/snapshots/test_cosmosdb/test_chathistory_query/auth_public_documents_client0/result.json b/tests/snapshots/test_cosmosdb/test_chathistory_query/auth_public_documents_client0/result.json
new file mode 100644
index 0000000000..1c3422fbca
--- /dev/null
+++ b/tests/snapshots/test_cosmosdb/test_chathistory_query/auth_public_documents_client0/result.json
@@ -0,0 +1,11 @@
+{
+    "continuation_token": "next",
+    "items": [
+        {
+            "entra_oid": "OID_X",
+            "id": "123",
+            "timestamp": 123456789,
+            "title": "This is a test message"
+        }
+    ]
+}
\ No newline at end of file
diff --git a/tests/snapshots/test_cosmosdb/test_chathistory_query_continuation/auth_public_documents_client0/result.json b/tests/snapshots/test_cosmosdb/test_chathistory_query_continuation/auth_public_documents_client0/result.json
new file mode 100644
index 0000000000..2983ef0689
--- /dev/null
+++ b/tests/snapshots/test_cosmosdb/test_chathistory_query_continuation/auth_public_documents_client0/result.json
@@ -0,0 +1,4 @@
+{
+    "continuation_token": null,
+    "items": []
+}
\ No newline at end of file
diff --git a/tests/test_app.py b/tests/test_app.py
index 1b8775fac5..9c20b9421a 100644
--- a/tests/test_app.py
+++ b/tests/test_app.py
@@ -514,6 +514,8 @@ async def test_chat_text_filter_public_documents(auth_public_documents_client, s
         == "category ne 'excluded' and ((oids/any(g:search.in(g, 'OID_X')) or groups/any(g:search.in(g, 'GROUP_Y, GROUP_Z'))) or (not oids/any() and not groups/any()))"
     )
     result = await response.get_json()
+    if result.get("session_state"):
+        del result["session_state"]
     snapshot.assert_match(json.dumps(result, indent=4), "result.json")
 
 
diff --git a/tests/test_cosmosdb.py b/tests/test_cosmosdb.py
new file mode 100644
index 0000000000..5495d8447a
--- /dev/null
+++ b/tests/test_cosmosdb.py
@@ -0,0 +1,349 @@
+import json
+
+import pytest
+from azure.cosmos.aio import ContainerProxy
+
+from .mocks import MockAsyncPageIterator
+
+
+class MockCosmosDBResultsIterator:
+    def __init__(self, empty=False):
+        if empty:
+            self.data = []
+        else:
+            self.data = [
+                [
+                    {
+                        "id": "123",
+                        "entra_oid": "OID_X",
+                        "title": "This is a test message",
+                        "timestamp": 123456789,
+                        "answers": [["This is a test message"]],
+                    }
+                ]
+            ]
+
+    def __aiter__(self):
+        return self
+
+    async def __anext__(self):
+        if not self.data:
+            raise StopAsyncIteration
+        return MockAsyncPageIterator(self.data.pop(0))
+
+    async def get_count(self):
+        return len(self.data)
+
+    def by_page(self, continuation_token=None):
+        if continuation_token:
+            self.continuation_token = continuation_token + "next"
+        else:
+            self.continuation_token = "next"
+        return self
+
+
+@pytest.mark.asyncio
+async def test_chathistory_newitem(auth_public_documents_client, monkeypatch):
+
+    async def mock_upsert_item(container_proxy, item, **kwargs):
+        assert item["id"] == "123"
+        assert item["answers"] == [["This is a test message"]]
+        assert item["entra_oid"] == "OID_X"
+        assert item["title"] == "This is a test message"
+
+    monkeypatch.setattr(ContainerProxy, "upsert_item", mock_upsert_item)
+
+    response = await auth_public_documents_client.post(
+        "/chat_history",
+        headers={"Authorization": "Bearer MockToken"},
+        json={
+            "id": "123",
+            "answers": [["This is a test message"]],
+        },
+    )
+    assert response.status_code == 201
+
+
+@pytest.mark.asyncio
+async def test_chathistory_newitem_error_disabled(client, monkeypatch):
+
+    response = await client.post(
+        "/chat_history",
+        headers={"Authorization": "Bearer MockToken"},
+        json={
+            "id": "123",
+            "answers": [["This is a test message"]],
+        },
+    )
+    assert response.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_chathistory_newitem_error_container(auth_public_documents_client, monkeypatch):
+    auth_public_documents_client.app.config["cosmos_history_container"] = None
+    response = await auth_public_documents_client.post(
+        "/chat_history",
+        headers={"Authorization": "Bearer MockToken"},
+        json={
+            "id": "123",
+            "answers": [["This is a test message"]],
+        },
+    )
+    assert response.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_chathistory_newitem_error_entra(auth_public_documents_client, monkeypatch):
+    response = await auth_public_documents_client.post(
+        "/chat_history",
+        json={
+            "id": "123",
+            "answers": [["This is a test message"]],
+        },
+    )
+    assert response.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_chathistory_newitem_error_runtime(auth_public_documents_client, monkeypatch):
+
+    async def mock_upsert_item(container_proxy, item, **kwargs):
+        raise Exception("Test Exception")
+
+    monkeypatch.setattr(ContainerProxy, "upsert_item", mock_upsert_item)
+
+    response = await auth_public_documents_client.post(
+        "/chat_history",
+        headers={"Authorization": "Bearer MockToken"},
+        json={
+            "id": "123",
+            "answers": [["This is a test message"]],
+        },
+    )
+    assert response.status_code == 500
+    assert (await response.get_json()) == {
+        "error": "The app encountered an error processing your request.\nIf you are an administrator of the app, view the full error in the logs. See aka.ms/appservice-logs for more information.\nError type: <class 'Exception'>\n"
+    }
+
+
+@pytest.mark.asyncio
+async def test_chathistory_query(auth_public_documents_client, monkeypatch, snapshot):
+
+    def mock_query_items(container_proxy, query, **kwargs):
+        return MockCosmosDBResultsIterator()
+
+    monkeypatch.setattr(ContainerProxy, "query_items", mock_query_items)
+
+    response = await auth_public_documents_client.post(
+        "/chat_history/items",
+        headers={"Authorization": "Bearer MockToken"},
+        json={"count": 20},
+    )
+    assert response.status_code == 200
+    result = await response.get_json()
+    snapshot.assert_match(json.dumps(result, indent=4), "result.json")
+
+
+@pytest.mark.asyncio
+async def test_chathistory_query_continuation(auth_public_documents_client, monkeypatch, snapshot):
+
+    def mock_query_items(container_proxy, query, **kwargs):
+        return MockCosmosDBResultsIterator(empty=True)
+
+    monkeypatch.setattr(ContainerProxy, "query_items", mock_query_items)
+
+    response = await auth_public_documents_client.post(
+        "/chat_history/items",
+        headers={"Authorization": "Bearer MockToken"},
+        json={"count": 20},
+    )
+    assert response.status_code == 200
+    result = await response.get_json()
+    snapshot.assert_match(json.dumps(result, indent=4), "result.json")
+
+
+@pytest.mark.asyncio
+async def test_chathistory_query_error_disabled(client, monkeypatch):
+
+    response = await client.post(
+        "/chat_history/items",
+        headers={"Authorization": "Bearer MockToken"},
+        json={
+            "id": "123",
+            "answers": [["This is a test message"]],
+        },
+    )
+    assert response.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_chathistory_query_error_container(auth_public_documents_client, monkeypatch):
+    auth_public_documents_client.app.config["cosmos_history_container"] = None
+    response = await auth_public_documents_client.post(
+        "/chat_history/items",
+        headers={"Authorization": "Bearer MockToken"},
+        json={
+            "id": "123",
+            "answers": [["This is a test message"]],
+        },
+    )
+    assert response.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_chathistory_query_error_entra(auth_public_documents_client, monkeypatch):
+    response = await auth_public_documents_client.post(
+        "/chat_history/items",
+        json={
+            "id": "123",
+            "answers": [["This is a test message"]],
+        },
+    )
+    assert response.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_chathistory_query_error_runtime(auth_public_documents_client, monkeypatch):
+
+    def mock_query_items(container_proxy, query, **kwargs):
+        raise Exception("Test Exception")
+
+    monkeypatch.setattr(ContainerProxy, "query_items", mock_query_items)
+
+    response = await auth_public_documents_client.post(
+        "/chat_history/items",
+        headers={"Authorization": "Bearer MockToken"},
+        json={"count": 20},
+    )
+    assert response.status_code == 500
+    assert (await response.get_json()) == {
+        "error": "The app encountered an error processing your request.\nIf you are an administrator of the app, view the full error in the logs. See aka.ms/appservice-logs for more information.\nError type: <class 'Exception'>\n"
+    }
+
+
+# Tests for getting an individual chat history item
+@pytest.mark.asyncio
+async def test_chathistory_getitem(auth_public_documents_client, monkeypatch, snapshot):
+
+    async def mock_read_item(container_proxy, item, partition_key, **kwargs):
+        return {
+            "id": "123",
+            "entra_oid": "OID_X",
+            "title": "This is a test message",
+            "timestamp": 123456789,
+            "answers": [["This is a test message"]],
+        }
+
+    monkeypatch.setattr(ContainerProxy, "read_item", mock_read_item)
+
+    response = await auth_public_documents_client.get(
+        "/chat_history/items/123",
+        headers={"Authorization": "Bearer MockToken"},
+    )
+    assert response.status_code == 200
+    result = await response.get_json()
+    snapshot.assert_match(json.dumps(result, indent=4), "result.json")
+
+
+# Error handling tests for getting an individual chat history item
+@pytest.mark.asyncio
+async def test_chathistory_getitem_error_disabled(client, monkeypatch):
+
+    response = await client.get(
+        "/chat_history/items/123",
+        headers={"Authorization": "BearerMockToken"},
+    )
+    assert response.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_chathistory_getitem_error_container(auth_public_documents_client, monkeypatch):
+    auth_public_documents_client.app.config["cosmos_history_container"] = None
+    response = await auth_public_documents_client.get(
+        "/chat_history/items/123",
+        headers={"Authorization": "BearerMockToken"},
+    )
+    assert response.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_chathistory_getitem_error_entra(auth_public_documents_client, monkeypatch):
+    response = await auth_public_documents_client.get(
+        "/chat_history/items/123",
+    )
+    assert response.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_chathistory_getitem_error_runtime(auth_public_documents_client, monkeypatch):
+
+    async def mock_read_item(container_proxy, item, partition_key, **kwargs):
+        raise Exception("Test Exception")
+
+    monkeypatch.setattr(ContainerProxy, "read_item", mock_read_item)
+
+    response = await auth_public_documents_client.get(
+        "/chat_history/items/123",
+        headers={"Authorization": "Bearer MockToken"},
+    )
+    assert response.status_code == 500
+
+
+# Tests for deleting an individual chat history item
+@pytest.mark.asyncio
+async def test_chathistory_deleteitem(auth_public_documents_client, monkeypatch):
+
+    async def mock_delete_item(container_proxy, item, partition_key, **kwargs):
+        assert item == "123"
+        assert partition_key == "OID_X"
+
+    monkeypatch.setattr(ContainerProxy, "delete_item", mock_delete_item)
+
+    response = await auth_public_documents_client.delete(
+        "/chat_history/items/123",
+        headers={"Authorization": "Bearer MockToken"},
+    )
+    assert response.status_code == 204
+
+
+@pytest.mark.asyncio
+async def test_chathistory_deleteitem_error_disabled(client, monkeypatch):
+
+    response = await client.delete(
+        "/chat_history/items/123",
+        headers={"Authorization": "Bearer MockToken"},
+    )
+    assert response.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_chathistory_deleteitem_error_container(auth_public_documents_client, monkeypatch):
+    auth_public_documents_client.app.config["cosmos_history_container"] = None
+    response = await auth_public_documents_client.delete(
+        "/chat_history/items/123",
+        headers={"Authorization": "Bearer MockToken"},
+    )
+    assert response.status_code == 400
+
+
+@pytest.mark.asyncio
+async def test_chathistory_deleteitem_error_entra(auth_public_documents_client, monkeypatch):
+    response = await auth_public_documents_client.delete(
+        "/chat_history/items/123",
+    )
+    assert response.status_code == 401
+
+
+@pytest.mark.asyncio
+async def test_chathistory_deleteitem_error_runtime(auth_public_documents_client, monkeypatch):
+
+    async def mock_delete_item(container_proxy, item, partition_key, **kwargs):
+        raise Exception("Test Exception")
+
+    monkeypatch.setattr(ContainerProxy, "delete_item", mock_delete_item)
+
+    response = await auth_public_documents_client.delete(
+        "/chat_history/items/123",
+        headers={"Authorization": "Bearer MockToken"},
+    )
+    assert response.status_code == 500