refactor demos (#398)

demos/samples_python/multi_turn_rag_agent/Dockerfile

@@ -0,0 +1,19 @@
+FROM python:3.12 AS base
+
+FROM base AS builder
+
+WORKDIR /src
+
+COPY requirements.txt /src/
+RUN pip install --prefix=/runtime --force-reinstall -r requirements.txt
+
+COPY . /src
+
+FROM python:3.12-slim AS output
+
+COPY --from=builder /runtime /usr/local
+
+COPY . /app
+WORKDIR /app
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80", "--log-level", "info"]

demos/samples_python/multi_turn_rag_agent/README.md

@@ -0,0 +1,22 @@
+# Multi-Turn Agentic Demo (RAG)
+
+This demo showcases how the **Arch** can be used to build accurate multi-turn RAG agent by just writing simple APIs.
+
+![Example of Multi-turn Interaction](mutli-turn-example.png)
+
+### Energy Source Q/A
+Provides information about various energy sources and considerations.
+
+- **Endpoint**: `/agent/energy_source`
+- **Parameters**:
+  - `energy_source` (`str`, **required**): A source of energy (e.g., `renewable`, `fossil`).
+  - `consideration` (`str`, *optional*): A specific type of consideration for an energy source (e.g., `cost`, `economic`, `technology`).
+
+# Starting the demo
+1. Please make sure the [pre-requisites](https://github.com/katanemo/arch/?tab=readme-ov-file#prerequisites) are installed correctly
+2. Start Arch
+   ```sh
+   sh run_demo.sh
+   ```
+3. Navigate to http://localhost:18080
+4. Ask "give me information about renewable energy sources"

demos/samples_python/multi_turn_rag_agent/arch_config.yaml

@@ -0,0 +1,59 @@
+version: v0.1
+
+listener:
+  address: 127.0.0.1
+  port: 10000
+  message_format: huggingface
+  connect_timeout: 0.005s
+
+endpoints:
+  rag_energy_source_agent:
+    endpoint: host.docker.internal:18083
+    connect_timeout: 0.005s
+
+llm_providers:
+  - name: gpt-4o-mini
+    access_key: $OPENAI_API_KEY
+    provider_interface: openai
+    model: gpt-4o-mini
+    default: true
+
+system_prompt: |
+  You are a helpful assistant and can offer information about energy sources.
+  You will get a JSON object with energy_source and consideration fields. Focus on answering the querstion using those fields.
+  Keep your responses to just three main points to make it easy for the reader to digest the information
+
+prompt_targets:
+  - name: get_info_for_energy_source
+    description: get information about an energy source
+    parameters:
+      - name: energy_source
+        type: str
+        description: a source of energy
+        required: true
+        enum: [renewable, fossil]
+      - name: consideration
+        type: str
+        description: a specific type of consideration for an energy source
+        enum: [cost, economic, technology]
+    endpoint:
+      name: rag_energy_source_agent
+      path: /agent/energy_source_info
+      http_method: POST
+
+  - name: default_target
+    default: true
+    description: This is the default target for all unmatched prompts.
+    endpoint:
+      name: rag_energy_source_agent
+      path: /default_target
+      http_method: POST
+    system_prompt: |
+      You are a helpful assistant! Summarize the user's request and provide a helpful response.
+    # if it is set to false arch will send response that it received from this prompt target to the user
+    # if true arch will forward the response to the default LLM
+    auto_llm_dispatch_on_response: false
+
+tracing:
+  random_sampling: 100
+  trace_arch_internal: true

demos/samples_python/multi_turn_rag_agent/docker-compose.yaml

@@ -0,0 +1,24 @@
+services:
+  rag_energy_source_agent:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - "18083:80"
+    healthcheck:
+        test: ["CMD", "curl" ,"http://localhost:80/healthz"]
+        interval: 5s
+        retries: 20
+
+  chatbot_ui:
+    build:
+      context: ../../shared/chatbot_ui
+      dockerfile: Dockerfile
+    ports:
+      - "18080:8080"
+    environment:
+      - CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:10000/v1
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    volumes:
+      - ./arch_config.yaml:/app/arch_config.yaml

demos/samples_python/multi_turn_rag_agent/main.py

@@ -0,0 +1,42 @@
+import os
+import gradio as gr
+
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from typing import Optional
+from openai import OpenAI
+
+app = FastAPI()
+
+
+# Define the request model
+class EnergySourceRequest(BaseModel):
+    energy_source: str
+    consideration: Optional[str] = None
+
+
+class EnergySourceResponse(BaseModel):
+    energy_source: str
+    consideration: Optional[str] = None
+
+
+# Post method for device summary
+@app.post("/agent/energy_source_info")
+def get_workforce(request: EnergySourceRequest):
+    """
+    Endpoint to get details about energy source
+    """
+    considertion = "You don't have any specific consideration. Feel free to talk in a more open ended fashion"
+
+    if request.consideration is not None:
+        considertion = f"Add specific focus on the following consideration when you summarize the content for the energy source: {request.consideration}"
+
+    response = {
+        "energy_source": request.energy_source,
+        "consideration": considertion,
+    }
+    return response
+
+
+if __name__ == "__main__":
+    app.run(debug=True)

demos/samples_python/multi_turn_rag_agent/requirements.txt

@@ -0,0 +1,12 @@
+fastapi
+uvicorn
+typing
+pandas
+gradio==5.3.0
+async_timeout==4.0.3
+loguru==0.7.2
+asyncio==3.4.3
+httpx==0.27.0
+python-dotenv==1.0.1
+pydantic==2.8.2
+openai==1.51.0

demos/samples_python/multi_turn_rag_agent/run_demo.sh

@@ -0,0 +1,47 @@
+#!/bin/bash
+set -e
+
+# Function to start the demo
+start_demo() {
+  # Step 1: Check if .env file exists
+  if [ -f ".env" ]; then
+    echo ".env file already exists. Skipping creation."
+  else
+    # Step 2: Create `.env` file and set OpenAI key
+    if [ -z "$OPENAI_API_KEY" ]; then
+      echo "Error: OPENAI_API_KEY environment variable is not set for the demo."
+      exit 1
+    fi
+
+    echo "Creating .env file..."
+    echo "OPENAI_API_KEY=$OPENAI_API_KEY" > .env
+    echo ".env file created with OPENAI_API_KEY."
+  fi
+
+  # Step 3: Start Arch
+  echo "Starting Arch with arch_config.yaml..."
+  archgw up arch_config.yaml
+
+  # Step 4: Start Network Agent
+  echo "Starting HR Agent using Docker Compose..."
+  docker compose up -d  # Run in detached mode
+}
+
+# Function to stop the demo
+stop_demo() {
+  # Step 1: Stop Docker Compose services
+  echo "Stopping HR Agent using Docker Compose..."
+  docker compose down -v
+
+  # Step 2: Stop Arch
+  echo "Stopping Arch..."
+  archgw down
+}
+
+# Main script logic
+if [ "$1" == "down" ]; then
+  stop_demo
+else
+  # Default action is to bring the demo up
+  start_demo
+fi