Skip to main content
This guide walks you through building a multilingual FAQ bot powered by Retrieval-Augmented Generation (RAG) and a Routing Engine on Orq.ai. The bot retrieves answers from a knowledge base in real-time and adapts responses to different languages based on user input. Instead of managing multiple versions of your bot with hardcoded if-else statements, Orq.ai’s Routing Engine offers a centralized way to handle various chatbot variants. With the Routing Engine, you can: ✅ Organize multiple chatbot variants (e.g., different languages or knowledge bases) ✅ Direct users to the right variant based on input parameters like locale or person ✅ Easily update your bot logic without modifying your code By centralizing your routing logic, the Routing Engine makes your FAQ bot more scalable and adaptable to evolving business needs.

​
Step 1: Install Dependencies

Before starting, ensure you have an Orq account. If not, sign up first. Additionally, we’ve prepared a Google Colab file that you can copy and run immediately, simplifying the setup process. Just replace the API key, and you’re ready to go For more advanced topics, check out the Orq documentation. Start by installing the required packages to use the Orq SDK and manage your knowledge base 
pip install orq-ai-sdk

​
Step 2: Contact Tracking (Optional)

Contacts in Orq.ai help track user interactions and API usage across your application. They can represent users, teams, or projects and enable better analytics and budget management. Create a contact through the Orq.ai Studio:
  1. Go to Contact Analytics in your workspace
  2. Click Create a Contact
  3. Add the user details (name, email, external ID)
  4. Set optional metadata and budget limits
Learn more about creating contacts, see Creating a Contact.

​
Step 3: Set Up the Orq Client

Next, set up the Orq client using your API key. Replace the placeholder with your actual API key. 
import os
from orq_ai_sdk import Orq

client = Orq(
    api_key=os.environ.get("ORQ_API_KEY", "your-api-key-here"),
    contact_id="your_contact_id"  # Optional: add contact ID from Studio for tracking
)

​
Step 4: Setting Up a Knowledge Base in Orq.ai

To power the FAQ bot, you’ll need a knowledge base containing relevant documents. In Orq.ai, knowledge bases are built using vector embeddings, enabling the bot to retrieve the most relevant information for any query. For this setup, we scraped our technical documentation and uploaded it to the knowledge base via the Orq platform. Keep in mind that this approach does not ensure continuous updates — any changes to your documentation will need to be manually re-uploaded. To upload a knowledge base in Orq.ai:
  1. Create a New Knowledge Base in the Orq workspace.
  2. Upload Documents by dragging files.
  3. Process the Files to generate vector embeddings, making your content searchable by the bot.
For a more detailed explanation, see the Creating a Knowledge Base documentation.

​
Step 5: Orq FAQ Chat Prompt

This prompt defines the behavior of Orq.ai’s FAQ bot, ensuring responses are accurate, context-driven, and based only on the provided knowledge base. The assistant acts as a customer service agent, delivering factual answers while avoiding speculation. The prompt includes clear instructions to maintain professionalism: ✅ Use only the knowledge base for answers ✅ Express uncertainty when information is unclear ✅ Avoid opinions or assumptions ✅ Break down complex topics into simple explanations ✅ Use objective, neutral language This ensures reliable and well-supported answers for users across various contexts. This is the general prompt in Orq.ai: 
### Role
You are a customer service assistant working for Orq.ai specialized in answering questions as accurately and factually as possible given all provided context. If there is no provided context, don’t answer the question but say: “sorry I don’t have information to answer your question”. Your goal is to provide clear, concise, and well-supported answers based on information from a knowledge base.

### Instructions
When responding:
* Express uncertainty on unclear or debatable topics
* Avoid speculation or personal opinions
* Break down complex topics into understandable explanations
* Use objective, neutral language

When asked a question:
ONLY use the following data coming from a knowledge base to answer your question:

<data_you_can_use>
{{orq_technical_docs}}
</data_you_can_use>

​
Step 6: Setting Up a Routing Engine

The Routing Engine in Orq.ai lets you direct user queries to different bot variants based on inputs like locale or person. Each variant can have unique configurations, prompts, or parameters. To set it up:
  1. Create Variants in the Routing panel (e.g., orq_FAQ_bot_english).
  2. Define Rules to map input fields (like language) to the right variant.
But Orq.ai’s routing goes beyond simple rule-matching—it integrates best practices from software engineering, like CI/CD and canary releases, into AI deployment. That means:
  • No more endless if-else statements—easily route different prompts to different models for specific use cases without cluttering your code.
  • Flexible decision-making—define an unlimited number of routing parameters (e.g., user segments, environments, languages, or even custom metadata) to fit your use case.
  • Controlled rollouts—test and iterate AI variants safely before pushing them to production. This setup keeps your bot scalable, adaptable, and easy to manage.
This setup keeps your bot scalable and adaptable without hardcoding logic. For more details, visit the Deployment Routing documentation.

​
Step 7: Define the Interaction Function

The bot will need a function to handle user input, manage conversation memory, and invoke the RAG deployment. Here’s a sample function: 
def chat_with_deployment(message, conv_memory, language):
    conv_memory.append({"role": "user", "content": message})
    
    generation = client.deployments.invoke(
        key="orqai_FAQ_bot_RAGAS",
        context={
            "language": [language],
            "environments": ["production"],
        },
        metadata={"custom-field-name": "custom-metadata-value"},
        messages=conv_memory,
    )
    
    response = generation.choices[0].message.content
    conv_memory.append({"role": "assistant", "content": response})
    
    return response
Keeping memory of the conversation
Here we use the variable conv_memory as a way to keep track of previous conversations. This array of messages is appended with all new user messages and sent as context within the messages variable within the payload to invoke.

​
Step 8: Customize the FAQ Bot for Multilingual Support

To ensure the bot responds in different languages, you’ll need to prompt users for their language preference: 
language = input("Enter a value for 'language' (e.g., 'english', 'french', 'german'): ")

​
Step 9: Run Your FAQ Bot

Now you’re ready to run the FAQ bot! Use the following interaction loop to start chatting with the deployment: 
conv_memory = []

print("\nYou can now start chatting! Type 'exit' or 'quit' to end the chat.\n")
while True:
    user_input = input("You: ")
    if user_input.lower() in ["exit", "quit"]:
        print("Ending chat.")
        break
    response = chat_with_deployment(user_input, conv_memory, language)
    print(f"Assistant: {response}")

​
Feedback Collection (Optional)

Feedback in Orq.ai helps track response quality and identify areas for improvement. You can collect user ratings, defect classifications, and corrections to continuously enhance your application. Provide feedback through the Orq.ai Studio:
  1. Go to Logs in your workspace
  2. Find the specific deployment invocation
  3. Use the feedback interface to rate responses
  4. Add defect classifications or corrections as needed
You can also collect feedback programmatically via the API if needed.

​
Next Steps

Great job! You’ve set up a multilingual FAQ bot using Orq.ai, powered by RAG and managed centrally with the Routing Engine. To further enhance your bot:
  • Add more knowledge base variants to support additional use cases or languages.
  • Refine your prompts and routing rules to improve bot accuracy and personalization.
For more resources and advanced features, visit the Orq.ai Documentation.