Simple RAG Consumption with Pinecone > Using the Simple RAG Consumption with Pinecone recipe > Invoking the process

Invoking the process

When you invoke the Query LLM With Context Using Embeddings Model process, the user sees the answer matching the context that was used in the LLM request.

You can run the process using one of the following options:

•REST or SOAP API endpoints in any API client such as cURL, Postman, SOAP UI, or any programming language
•Web browser by passing the input parameters