# Get started with Qualcomm AI Inference Suite SDK The Qualcomm AI Inference Suite SDK is a Python package with Open AI compatible APIs that let you create generative AI applications. You can develop applications such as chatbots, generative question-answering, summarization, and workflow automation using the `python-imagine-sdk` package and Python AI frameworks like [LangChain](https://www.langchain.com%3E) and [CrewAI](https://docs.crewai.com/). This page provides a basic example of how to start a chat with a large language model (LLM) and generate a response. ## Prerequisites - Python 3.9 or higher. - Install one of the following versions of the Qualcomm AI Inference Suite SDK: - To install the latest version with basic functionality, do the following: pip install python-imagine-sdk Copy to clipboard - To install the latest version with basic functionality plus LangChain support, do the following: pip install python-imagine-sdk[langchain] Copy to clipboard - To install the latest version with basic functionality plus CrewAI support, do the following: pip install python-imagine-sdk[crewai] Copy to clipboard - If you don’t already have an Imagine API key and an endpoint URL, do the following: - For cloud applications, see the [Inference Cloud playground](https://aisuite.cirrascale.com/imagine-api-docs#tag/qualcomm-ai100-inference---imagine-apis). - Fo on-premise inferencing using the [Qualcomm AI On-Prem Appliance Solution](https://docs.qualcomm.com/nav/home?product=626615100779122971), use the generated local API key and `http://localhost:5050/v2` for the endpoint. - Set the API key and endpoint URL. All examples in this documentation require a valid Imagine API key and endpoint URL. 1. Set the environment variable `IMAGINE_API_KEY` to your personal Imagine API key. Alternatively, you can pass your API key directly to the client with `ImagineClient(api_key="my-api-key")`. 2. Set the environment variable `IMAGINE_ENDPOINT_URL` to the endpoint you are using. Alternatively, you can pass your endpoint directly to the client with `ImagineClient(endpoint="https://my-endpoint/api/v2")`. Danger Never share your personal Imagine API keys with anyone. Never commit your personal Imagine API keys to any git repository ## Start a chat and generate text with the LLM The following example shows how to use the Qualcomm AI Inference Suite SDK to start a chat and generate text with a large language model (LLM). The code in the example instantiates the [`ImagineClient`](https://docs.qualcomm.com/doc/80-88545-1/topic/1_0_basic_usage.html) and starts a chat by sending a `ChatMessage` with a user question. The `model` parameter specifies which LLM to use and, finally, the `chat_response` prints the model’s reply. - Run the following example in a development environment with access to the Imagine client, your API key, and API endpoint URL. from imagine import ChatMessage, ImagineClient client = ImagineClient() chat_response = client.chat( messages=[ChatMessage(role="user", content="What is the best Spanish cheese?")], model="Llama-3.1-8B", ) print(chat_response.first_content) Copy to clipboard The AI generates a response similar to the following: Spain is renowned for its rich variety of cheeses, each with its unique flavor profile and texture. The "best" Spanish cheese is subjective and often depends on personal taste preferences. However, here are some of the most popular and highly-regarded Spanish cheeses: 1. Manchego: A firm, crumbly cheese made from sheep's milk, Manchego is a classic Spanish cheese with a nutty, slightly sweet flavor. 2. Mahon: A semi-soft cheese from the island of Minorca, Mahon has a mild, creamy flavor and a smooth texture. 3. Idiazabal: A smoked cheese from the Basque region, Idiazabal has a strong, savory flavor and a firm texture. 4. Garrotxa: A soft, creamy cheese from Catalonia, Garrotxa has a mild, buttery flavor and a delicate aroma. ... Copy to clipboard ## Next steps - [Stream a chat response](https://docs.qualcomm.com/doc/80-88545-1/topic/1_0_basic_usage.html#stream-chat-response). - [Translate text](https://docs.qualcomm.com/doc/80-88545-1/topic/1_0_basic_usage.html#translate-text). Last Published: Apr 17, 2026 [Previous Topic Qualcomm AI Inference Suite SDK documentation](https://docs.qualcomm.com/bundle/publicresource/80-88545-1/topics/landing.md) [Next Topic Examples](https://docs.qualcomm.com/bundle/publicresource/80-88545-1/topics/index_tutorials.md)