Step 5. Configure and publish the processes
Configure the LLM model and authorization access, and then publish the processes.
- 1To publish the following processes, click Actions in the row that contains the process and select Publish.
- - Get Embeddings
- - Query Pinecone
- - Generate Embeddings Model
- - Query LLM with Context using NVIDIA NIM
- 2Open the Query LLM with Context using Embeddings Model process.
- 3In the Set LLM Models step, in the Assignments tab, enter the values in the Set_Content_Model, Set_Embedding_Model, and Index_Host fields.
You can find the list of models in
NVIDIA LLM API documentation.
- 4Save and publish the process.
- 5Open the RAG Consumption with NVIDIA NIM process.
- 6On the Start tab of the Start step, select Allow anonymous access.
- 7Save and publish the process.
- 8Click Actions > Properties Details > Copy Service URL.
You must copy the service URL to the webhook configuration in Slack. For more information, see
Step 6. Create webhooks in Slack.