diff --git a/app/main.py b/app/main.py
index aff11847..e1a2ca7a 100644
--- a/app/main.py
+++ b/app/main.py
@@ -36,7 +36,8 @@
     description=f"The server application that provides APIs to interact \
 with the underlying Databases and modules in Vachan-Engine. \
 \n • For Vachan-CMS docs: {root_url}/v2/cms/rest/docs,\
-\n • For Vachan-TBT docs: {root_url}/v2/text/translate/token-based/docs")
+\n • For Vachan-TBT docs: {root_url}/v2/text/translate/token-based/docs,\
+\n • For Vachan-AI docs: {root_url}/v2/ai/model/docs")
 template = Jinja2Templates(directory="templates")
 app.mount("/static", StaticFiles(directory="static"), name="static")
 
@@ -253,6 +254,7 @@ def custom_openapi():
         underlying Databases \and modules in Vachan-Engine. "
         f"<br> • <a href=\"{root_url}/v2/text/translate/token-based/docs\" > Vachan-TBT docs </a>"
         f"<br> • <a href=\"{root_url}/v2/cms/rest/docs\" > Vachan-CMS docs </a>"
+        f"<br> • <a href=\"{root_url}/v2/ai/model/docs\" > Vachan-AI docs </a>"
         ),
         routes=app.routes
     )
diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml
index 481e781a..f54cc5f1 100644
--- a/docker/docker-compose.yml
+++ b/docker/docker-compose.yml
@@ -288,6 +288,62 @@ services:
     networks:
      - VE-network
 
+ vachan_ai:
+    image: jayasankarkk/vachan-ai:0.0.0-alpha.3
+    healthcheck:
+     timeout: 45s
+     interval: 10s
+     retries: 10
+    environment:
+     - VACHAN_AI_POSTGRES_HOST=192.168.3.157
+     - VACHAN_AI_POSTGRES_USER=${VACHAN_AI_POSTGRES_USER:-postgres}
+     - VACHAN_AI_POSTGRES_PASSWORD=${VACHAN_AI_POSTGRES_PASSWORD:-secret}
+     - VACHAN_AI_POSTGRES_DATABASE=${VACHAN_AI_POSTGRES_DATABASE:-vachan_ai_db}
+     - VACHAN_AI_POSTGRES_SCHEMA=${VACHAN_AI_POSTGRES_DATABASE:-vachan_ai}
+
+     - VACHAN_AI_XLSR_MAX_AUDIO_DURATION=${VACHAN_AI_XLSR_MAX_AUDIO_DURATION:-25}
+     - VACHAN_AI_XLSR_SAMPLING_RATE=${VACHAN_AI_XLSR_SAMPLING_RATE:-16000}
+     - VACHAN_AI_NLLB_MAX_SRC_CHARS=${VACHAN_AI_NLLB_MAX_SRC_CHARS:-512}
+     - VACHAN_AI_NLLB_BATCH_SIZE=${VACHAN_AI_NLLB_BATCH_SIZE:-10}
+      
+    
+     - MLFLOW_TRACKING_URI=${MLFLOW_TRACKING_URI:-http://192.168.3.157:5000}
+     - VACHAN_AI_ARTIFACT_PATH=${VACHAN_AI_ARTIFACT_PATH:-models}
+     - VACHAN_AI_SERVED_MODEL_URI=${VACHAN_AI_SERVED_MODEL_URI:-http://192.168.3.157:8080/v2/models}
+     - VACHAN_AI_MODEL_SETTINGS_DIR=${VACHAN_AI_MODEL_SETTINGS_DIR:-serving_models}
+     - VACHAN_AI_REQUEST_TIMEOUT=${VACHAN_AI_REQUEST_TIMEOUT:-60}
+
+     - VACHAN_AI_AWS_ACCESS_KEY=${VACHAN_AI_AWS_ACCESS_KEY}
+     - VACHAN_AI_AWS_SECRET_ACCESS_KEY=${VACHAN_AI_AWS_SECRET_ACCESS_KEY}
+     - VACHAN_AI_S3_BUCKET=${VACHAN_AI_S3_BUCKET}
+     - VACHAN_AI_AWS_ACCOUNT_REGION=${VACHAN_AI_AWS_ACCOUNT_REGION}
+     
+
+     - VACHAN_AI_DATA_PATH=${VACHAN_AI_DATA_PATH:-/var/data-vachan-ai}
+     - VACHAN_AI_POSTGRES_PORT=5433
+     - VACHAN_AI_LOGGING_LEVEL=INFO
+     - VACHAN_DOMAIN=${VACHAN_DOMAIN:-http://localhost}
+     - VACHAN_LOGGING_LEVEL=INFO
+     - VACHAN_AI_ENV=${VACHAN_AI_ENV:-Development}
+    command: uvicorn main:app --host 0.0.0.0 --port 8006
+    volumes:
+     - ${VACHAN_AI_DATA_PATH}/docker-volumes/ai-logs-vol:/app/logs
+     - ${VACHAN_AI_DATA_PATH}/cache:/root/.cache
+    restart: always
+    depends_on:
+     - vachan-api
+    profiles:
+     - local-run
+     - deployment
+    expose:
+     - 8006
+    ports:
+     - "8006:8006"
+    networks:
+     - VE-network
+    container_name: vachan_ai
+
+
  # Web Server
  web-server-local:
     image: nginx:latest
@@ -432,4 +488,6 @@ volumes:
   logs-test-vol:
   vachan-db-backup:
   kratos-db-backup:
-  vachan-tbt-ml-models-vol:
\ No newline at end of file
+  vachan-tbt-ml-models-vol:
+  ai-logs-vol:
+  cache:
\ No newline at end of file
diff --git a/docker/nginx/default.conf b/docker/nginx/default.conf
index 31a069b2..00702f47 100644
--- a/docker/nginx/default.conf
+++ b/docker/nginx/default.conf
@@ -27,6 +27,11 @@ server {
         proxy_pass http://vachan-tbt:8003;    
     }
 
+    location /v2/ai/model/ {
+        proxy_pass http://vachan_ai:8006;
+    }
+
+
     location /v2/nlp/ {
         proxy_pass http://vachan-tbt:8003;    
     }
diff --git a/docker/nginx/prod/app.conf.template b/docker/nginx/prod/app.conf.template
index c9043dff..ed397534 100644
--- a/docker/nginx/prod/app.conf.template
+++ b/docker/nginx/prod/app.conf.template
@@ -55,8 +55,14 @@ server {
     location /v2/demos/ {
         proxy_pass http://vachan-demos:8002;    
     }
+
+    location /v2/ai/model/ {
+        proxy_pass http://vachan-ai:8006;
+    }
    
     location / {
         proxy_pass http://vachan-api:8000;
     }
+
+
 }