Skip to content

Commit

Permalink
Python Conversation http Quickstart (#1150)
Browse files Browse the repository at this point in the history
* Python Conversation API - HTTP quickstart

Signed-off-by: Fernando Rocha <fernando@diagrid.io>

* Update conversation/python/http/dapr.yaml

Co-authored-by: Marc Duiker <marcduiker@users.noreply.github.com>
Signed-off-by: Fernando Rocha <fernandorsl@gmail.com>

* Update conversation/python/http/dapr.yaml

Co-authored-by: Marc Duiker <marcduiker@users.noreply.github.com>
Signed-off-by: Fernando Rocha <fernandorsl@gmail.com>

---------

Signed-off-by: Fernando Rocha <fernando@diagrid.io>
Signed-off-by: Fernando Rocha <fernandorsl@gmail.com>
Co-authored-by: Marc Duiker <marcduiker@users.noreply.github.com>
  • Loading branch information
rochabr and marcduiker authored Jan 30, 2025
1 parent 6993063 commit 7e0433e
Show file tree
Hide file tree
Showing 5 changed files with 138 additions and 0 deletions.
97 changes: 97 additions & 0 deletions conversation/python/http/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,97 @@
# Dapr Conversation API (Python HTTP)

In this quickstart, you'll send an input to a mock Large Language Model (LLM) using Dapr's Conversation API. This API is responsible for providing one consistent API entry point to talk to underlying LLM providers.

Visit [this](https://v1-15.docs.dapr.io/developing-applications/building-blocks/conversation/conversation-overview/) link for more information about Dapr and the Conversation API.

> **Note:** This example leverages HTTP `requests` only.
This quickstart includes one app:

- `app.py`, responsible for sending an input to the underlying LLM and retrieving an output.

## Run the app with the template file

This section shows how to run the application using the [multi-app run template files](https://docs.dapr.io/developing-applications/local-development/multi-app-dapr-run/multi-app-overview/) with `dapr run -f .`.

This example uses the default LLM Component provided by Dapr which simply echoes the input provided, for testing purposes. Here are other [supported Conversation components](https://v1-15.docs.dapr.io/reference/components-reference/supported-conversation/).

1. Install dependencies:

<!-- STEP
name: Install Python dependencies
-->

```bash
cd ./conversation
pip3 install -r requirements.txt
cd ..
```

2. Open a new terminal window and run the multi app run template:

<!-- STEP
name: Run multi app run template
expected_stdout_lines:
- '== APP == INFO:root:Input sent: What is dapr?'
- '== APP == INFO:root:Output response: What is dapr?'
expected_stderr_lines:
output_match_mode: substring
match_order: none
background: true
sleep: 15
timeout_seconds: 30
-->

```bash
dapr run -f .
```

The terminal console output should look similar to this, where:

- The app sends an input `What is dapr?` to the `echo` Component mock LLM.
- The mock LLM echoes `What is dapr?`.

```text
== APP - conversation == Input sent: What is dapr?
== APP - conversation == Output response: What is dapr?
```

<!-- END_STEP -->

2. Stop and clean up application processes.

<!-- STEP
name: Stop multi-app run
sleep: 5
-->

```bash
dapr stop -f .
```

<!-- END_STEP -->

## Run the app with the Dapr CLI

1. Install dependencies:

Open a terminal and run:

```bash
cd ./conversation
pip3 install -r requirements.txt
```

2. Run the application:

```bash
dapr run --app-id conversation --resources-path ../../../components -- python3 app.py
```

You should see the output:

```bash
== APP == INFO:root:Input sent: What is dapr?
== APP == INFO:root:Output response: What is dapr?
```
31 changes: 31 additions & 0 deletions conversation/python/http/conversation/app.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,31 @@
import logging
import requests
import os

logging.basicConfig(level=logging.INFO)

base_url = os.getenv('BASE_URL', 'http://localhost') + ':' + os.getenv(
'DAPR_HTTP_PORT', '3500')

CONVERSATION_COMPONENT_NAME = 'echo'

input = {
'name': 'echo',
'inputs': [{'message':'What is dapr?'}],
'parameters': {},
'metadata': {}
}

# Send input to conversation endpoint
result = requests.post(
url='%s/v1.0-alpha1/conversation/%s/converse' % (base_url, CONVERSATION_COMPONENT_NAME),
json=input
)

logging.info('Input sent: What is dapr?')

# Parse conversation output
data = result.json()
output = data["outputs"][0]["result"]

logging.info('Output response: ' + output)
1 change: 1 addition & 0 deletions conversation/python/http/conversation/requirements.txt
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
requests
7 changes: 7 additions & 0 deletions conversation/python/http/dapr.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,7 @@
version: 1
common:
resourcesPath: ../../components/
apps:
- appID: conversation
appDirPath: ./conversation/
command: ["python3", "app.py"]
2 changes: 2 additions & 0 deletions conversation/python/http/makefile
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
include ../../../docker.mk
include ../../../validate.mk

0 comments on commit 7e0433e

Please sign in to comment.