progress

Signed-off-by: Adrian Cole <[email protected]>

Author: codefromthecrypt

example-apps/chatbot-rag-app/README.md

@@ -45,34 +45,48 @@ and configure its templated connection settings:
 
 ## Running the App
 
+This application contains two services:
+* create-index: Installs ELSER and ingests data into elasticsearch
+* api-frontend: Hosts the chatbot-rag-app application on http://localhost:4000
+
 There are two ways to run the app: via Docker or locally. Docker is advised for
 ease while locally is advised if you are making changes to the application.
 
 ### Run with docker
 
-Docker compose is the easiest way, as you get one-step to:
-* ingest data into elasticsearch
-* run the app, which listens on http://localhost:4000
+Docker compose is the easiest way to get started, as you don't need to have a
+working Python environment.
 
 **Double-check you have a `.env` file with all your variables set first!**
 
+#### Create your Elasticsearch index
+
+First, ingest the data into elasticsearch:
+```bash
+docker compose run -T --rm --pull always create-index
+```
+
+*Note*: This may take several minutes to complete
+
+#### Run the application
+
+Now, run the app, which listens on http://localhost:4000
 ```bash
-docker compose up --pull always --force-recreate
+docker compose run --rm --pull always api-frontend
 ```
 
-*Note*: First time creating the index can fail on timeout. Wait a few minutes
-and retry.
+#### Cleanup when finished
 
-Clean up when finished, like this:
+When you are done, clean up the services above like this:
 
 ```bash
 docker compose down
 ```
 
-### Run locally
+### Run with Python
 
-If you want to run this example with Python and Node.js, you need to do a few
-things listed in the [Dockerfile](Dockerfile). The below uses the same
+If you want to run this example with Python, you need to do a few things listed
+in the [Dockerfile](Dockerfile) to build it first. The below uses the same
 production mode as used in Docker to avoid problems in debug mode.
 
 **Double-check you have a `.env` file with all your variables set first!**
@@ -89,7 +103,7 @@ nvm use --lts
 (cd frontend; yarn install; REACT_APP_API_HOST=/api yarn build)
 ```
 
-#### Configure your python environment
+#### Configure your Python environment
 
 Before we can run the app, we need a working Python environment with the
 correct packages installed:
@@ -102,17 +116,16 @@ pip install "python-dotenv[cli]"
 pip install -r requirements.txt
 ```
 
-#### Run the ingest command
+#### Create your Elasticsearch index
 
 First, ingest the data into elasticsearch:
 ```bash
-FLASK_APP=api/app.py dotenv run -- flask create-index
+dotenv run -- flask create-index
 ```
 
-*Note*: First time creating the index can fail on timeout. Wait a few minutes
-and retry.
+*Note*: This may take several minutes to complete
 
-#### Run the app
+#### Run the application
 
 Now, run the app, which listens on http://localhost:4000
 ```bash
@@ -185,13 +198,14 @@ passages. Modify this script to index your own data.
 
 See [Langchain documentation][loader-docs] for more ways to load documents.
 
-### Building from source with docker
+### Running from source with Docker
 
-To build the app from source instead of using published images, pass the `--build`
-flag to Docker Compose.
+To build the app from source instead of using published images, pass the
+`--build` flag to Docker Compose instead of `--pull always`
 
+For example, to run the create-index service from source:
 ```bash
-docker compose up --build --force-recreate
+docker compose run --rm --build create-index
 ```
 
 ---

example-apps/chatbot-rag-app/data/index_data.py

@@ -1,6 +1,8 @@
 import json
 import os
+from sys import stdout
 import time
+from halo import Halo
 from warnings import warn
 
 from elasticsearch import (
@@ -135,30 +137,43 @@ def await_ml_tasks(max_timeout=600, interval=5):
         TimeoutError: If the timeout is reached and machine learning tasks are still running.
     """
     start_time = time.time()
+    ml_tasks = get_ml_tasks()
+    if not ml_tasks:
+        return  # likely a lost race on tasks
+
+    spinner = Halo(text="Awaiting ML tasks", spinner="dots")
+    if stdout.isatty():
+        spinner.start()
+    else:
+        print(f"Awaiting {len(ml_tasks)} ML tasks")
 
-    tasks = []  # Initialize tasks list
-    previous_task_count = 0  # Track the previous number of tasks
     while time.time() - start_time < max_timeout:
-        tasks = []
-        resp = es.tasks.list(detailed=True, actions=["cluster:monitor/xpack/ml/*"])
-        for node_id, node_info in resp["nodes"].items():
-            node_tasks = node_info.get("tasks", {})
-            for task_id, task_info in node_tasks.items():
-                tasks.append(task_info["action"])
-        if not tasks:
+        ml_tasks = get_ml_tasks()
+        if len(ml_tasks) == 0:
             break
-        current_task_count = len(tasks)
-        if current_task_count != previous_task_count:
-            warn(f"Awaiting {current_task_count} ML tasks")
-            previous_task_count = current_task_count
         time.sleep(interval)
 
-    if tasks:
+    if stdout.isatty():
+        spinner.stop()
+    else:
+        print(f"ML tasks complete")
+
+    if ml_tasks:
         raise TimeoutError(
-            f"Timeout reached. ML tasks are still running: {', '.join(tasks)}"
+            f"Timeout reached. ML tasks are still running: {', '.join(ml_tasks)}"
         )
 
 
+def get_ml_tasks():
+    """Return a list of ML task actions from the ES tasks API."""
+    tasks = []
+    resp = es.tasks.list(detailed=True, actions=["cluster:monitor/xpack/ml/*"])
+    for node_info in resp["nodes"].values():
+        for task_info in node_info.get("tasks", {}).values():
+            tasks.append(task_info["action"])
+    return tasks
+
+
 # Unless we run through flask, we can miss critical settings or telemetry signals.
 if __name__ == "__main__":
     main()

example-apps/chatbot-rag-app/docker-compose.yml

@@ -1,16 +1,16 @@
 name: chatbot-rag-app
 
 services:
-  ingest-data:
+  create-index:
     image: ghcr.io/elastic/elasticsearch-labs/chatbot-rag-app
     build:
       context: .
-    container_name: ingest-data
+    container_name: create-index
     restart: 'no'  # no need to re-ingest on successive runs
-    environment:
-      FLASK_APP: api/app.py
     env_file:
       - .env
+    # Add settings that allow `docker compose run` to use tty and accept Ctrl+C
+    stdin_open: true
     command: flask create-index
     volumes:
       # VertexAI uses a file for GOOGLE_APPLICATION_CREDENTIALS, not an API key
@@ -20,14 +20,16 @@ services:
 
   api-frontend:
     depends_on:
-      ingest-data:
+      create-index:
         condition: service_completed_successfully
     container_name: api-frontend
     image: ghcr.io/elastic/elasticsearch-labs/chatbot-rag-app
     build:
       context: .
     env_file:
       - .env
+    # Add settings that allow `docker compose run` to use tty and accept Ctrl+C
+    stdin_open: true
     volumes:
       # VertexAI uses a file for GOOGLE_APPLICATION_CREDENTIALS, not an API key
       - ${HOME}/.config/gcloud:/root/.config/gcloud

example-apps/chatbot-rag-app/env.example

@@ -1,5 +1,10 @@
 # Make a copy of this file with the name .env and assign values to variables
 
+# Location of the application routes
+FLASK_APP=api/app.py
+# Ensure print statements appear as they happen
+PYTHONUNBUFFERED=1
+
 # How you connect to Elasticsearch: change details to your instance
 ELASTICSEARCH_URL=http://localhost:9200
 ELASTICSEARCH_USER=elastic

example-apps/chatbot-rag-app/requirements.in

@@ -5,6 +5,7 @@ langchain-elasticsearch
 tiktoken
 flask
 flask-cors
+halo
 
 # LLM dependencies
 langchain-openai

example-apps/chatbot-rag-app/requirements.txt

@@ -22,11 +22,11 @@ attrs==25.1.0
     # via aiohttp
 blinker==1.9.0
     # via flask
-boto3==1.36.23
+boto3==1.36.24
     # via
     #   langchain-aws
     #   langtrace-python-sdk
-botocore==1.36.23
+botocore==1.36.24
     # via
     #   boto3
     #   s3transfer
@@ -46,7 +46,10 @@ click==8.1.8
 cohere==5.13.12
     # via langchain-cohere
 colorama==0.4.6
-    # via langtrace-python-sdk
+    # via
+    #   halo
+    #   langtrace-python-sdk
+    #   log-symbols
 dataclasses-json==0.6.7
     # via langchain-community
 deprecated==1.2.18
@@ -144,6 +147,8 @@ grpcio-status==1.70.0
     # via google-api-core
 h11==0.14.0
     # via httpcore
+halo==0.0.31
+    # via -r requirements.in
 httpcore==1.0.7
     # via httpx
 httpx==0.28.1
@@ -159,7 +164,7 @@ httpx-sse==0.4.0
     #   langchain-community
     #   langchain-google-vertexai
     #   langchain-mistralai
-huggingface-hub==0.28.1
+huggingface-hub==0.29.0
     # via
     #   tokenizers
     #   transformers
@@ -193,9 +198,9 @@ langchain-aws==0.2.13
     # via -r requirements.in
 langchain-cohere==0.4.2
     # via -r requirements.in
-langchain-community==0.3.17
+langchain-community==0.3.18
     # via langchain-cohere
-langchain-core==0.3.36
+langchain-core==0.3.37
     # via
     #   langchain
     #   langchain-aws
@@ -223,6 +228,8 @@ langsmith==0.3.8
     #   langchain-core
 langtrace-python-sdk==3.6.2
     # via -r requirements.in
+log-symbols==0.0.14
+    # via halo
 markupsafe==3.0.2
     # via
     #   jinja2
@@ -414,11 +421,15 @@ shapely==2.0.7
 simsimd==6.2.1
     # via elasticsearch
 six==1.17.0
-    # via python-dateutil
+    # via
+    #   halo
+    #   python-dateutil
 sniffio==1.3.1
     # via
     #   anyio
     #   openai
+spinners==0.0.24
+    # via halo
 sqlalchemy==2.0.38
     # via
     #   langchain
@@ -429,6 +440,8 @@ tenacity==9.0.0
     #   langchain
     #   langchain-community
     #   langchain-core
+termcolor==2.5.0
+    # via halo
 tiktoken==0.9.0
     # via
     #   -r requirements.in