Introduction to IBM watsonx.ai as a Service Using IBM watsonx.ai as a Service APIs, you can run text inference, prompt tuning and more on Large Language Models LLM. If you are looking for the IBM wats
| Method | Path | Summary |
|---|---|---|
| Create a new AI service | ||
| Retrieve the AI services | ||
| Retrieve the AI service | ||
| Update the AI service | ||
| Delete the AI service | ||
| Upload the AI service code | ||
| Download the AI service code | ||
| Create a new AI service revision | ||
| Retrieve the AI service revisions | ||
| Transcribe audio | ||
| Upload file | ||
| List files | ||
| Retrieve file | ||
| Create batch | ||
| List batches | ||
| Retrieve batch | ||
| Cancel batch | ||
| Create a new AutoAI RAG run | ||
| Retrieve the AutoAI RAG runs | ||
| Get an AutoAI RAG run | ||
| Cancel or delete an AutoAI RAG run | ||
| Retrieve the custom foundation models | ||
| Create a new watsonx.ai deployment | ||
| Retrieve the deployments | ||
| Retrieve the deployment details | ||
| Update the deployment metadata | ||
| Delete the deployment | ||
| Infer text | ||
| Infer text event stream | ||
| Infer chat completions | ||
| Infer text chat | ||
| Infer text chat event stream | ||
| Time series forecast | ||
| Execute AI service | ||
| Execute AI service stream | ||
| Create a fine tuning job | ||
| Retrieve the list of fine tuning jobs | ||
| Get a fine tuning job | ||
| Cancel or delete a fine tuning job | ||
| List the available foundation models | ||
| List the supported tasks | ||
| Create a new notebook. | ||
| Retrieve the details of a large number of notebooks inside a project. | ||
| Delete a particular notebook, including the notebook asset. | ||
| Revert the main notebook to a version. | ||
| Update a particular notebook. | ||
| Promote a notebook from project to space. | ||
| Create a new version. | ||
| List the versions of a notebook. | ||
| Retrieve a notebook version. | ||
| Delete a notebook version. | ||
| Create a new prompt / prompt template | ||
| Get a prompt | ||
| Update a prompt | ||
| Delete a prompt | ||
| Prompt lock modifications | ||
| Get current prompt lock status | ||
| Get the inference input string for a given prompt | ||
| Add a new chat item to a prompt | ||
| Create a new prompt session | ||
| Get a prompt session | ||
| Update a prompt session | ||
| Delete a prompt session | ||
| Add a new prompt to a prompt session | ||
| Get entries for a prompt session | ||
| Add a new chat item to a prompt session entry | ||
| Prompt session lock modifications | ||
| Get current prompt session lock status | ||
| Get a prompt session entry | ||
| Delete a prompt session entry | ||
| Create a batch job | ||
| Get batch jobs | ||
| Get a batch job | ||
| Cancel or delete a batch job | ||
| Download the content of a result batch file | ||
| Chat Completions | ||
| Infer text | ||
| Infer text event stream | ||
| Start a text classification request | ||
| Retrieve the text classification requests | ||
| Get the results of the request | ||
| Delete the request | ||
| Start a create schema request | ||
| Retrieve the create schema requests | ||
| Get the results of the request | ||
| Delete the request | ||
| Start a improve schema request | ||
| Retrieve the improve schema requests | ||
| Get the results of the request | ||
| Delete the request | ||
| Start a merge schema request | ||
| Retrieve the merge schema requests | ||
| Get the results of the request | ||
| Delete the request | ||
| Start a cluster schema request | ||
| Retrieve the cluster schema requests | ||
| Get the results of the request | ||
| Delete the request | ||
| HAP and PII detection for text | ||
| Detection task on input content based on context documents | ||
| Detection task performing detection on prompt and generated text | ||
| Generate embeddings | ||
| Start a text extraction request | ||
| Retrieve the text extraction requests | ||
| Get the results of the request | ||
| Delete the request | ||
| Infer text | ||
| Infer text event stream | ||
| Generate rerank | ||
| Text tokenization | ||
| Time series forecast | ||
| Create a new watsonx.ai training | ||
| Retrieve the list of trainings | ||
| Retrieve the training | ||
| Cancel or delete the training | ||
| Create a vector index. | ||
| Get a vector index | ||
| Update a vector index | ||
| Delete a vector index | ||
| Vector Index attachments modifications | ||
| Create a vector index. | ||
| Update a vector index | ||
| Get status of a vector index | ||
| Create a synthetic unstructured data generation job | ||
| Create Speech | ||
| Create Chat Completions | ||
| Create Text Completions | ||
| Create Embeddings | ||
| Create Image Generations | ||
| List All Models | ||
| Get Existing Model | ||
| Delete Existing Model | ||
| Get Current Tenant | ||
| Replace Current Tenant | ||
| Update Current Tenant | ||
| Create Tenant JWT | ||
| List All Policies | ||
| Create New Policy | ||
| Get Specific Policy | ||
| Update Existing Policy | ||
| Delete Existing Policy | ||
| List All Providers | ||
| Create New Anthropic Provider | ||
| Create New Azure OpenAI Provider | ||
| Create New AWS Bedrock Provider | ||
| Create New Cerebras Provider | ||
| Create New Cohere Provider | ||
| Create New Gemini Provider | ||
| Create New Groq Provider | ||
| Create New Mistral Provider | ||
| Create New Nvidia NIM Provider | ||
| Create New Ollama Provider | ||
| Create New OpenAI Provider | ||
| Find Existing Providers | ||
| Validate Provider Credentials | ||
| Create New IBM Watsonx.ai Provider | ||
| Create New xAI Provider | ||
| Get Existing Provider | ||
| Delete Existing Provider | ||
| Replace Existing Anthropic Provider | ||
| Replace Existing Azure OpenAI Provider | ||
| Replace Existing AWS Bedrock Provider | ||
| Replace Existing Cerebras Provider | ||
| Replace Existing Cohere Provider | ||
| Replace Existing Gemini Provider | ||
| Replace Existing Groq Provider | ||
| Replace Existing Mistral Provider | ||
| Replace Existing Ollama Provider | ||
| List Provider Models | ||
| Create New Model | ||
| Replace Existing Model | ||
| Update Existing Model | ||
| Delete Existing Model | ||
| List Available Models | ||
| Replace Existing Nvidia NIM Provider | ||
| Replace Existing OpenAI Provider | ||
| Replace Existing IBM Watsonx.ai Provider | ||
| Replace Existing xAI Provider | ||
| List Load Balancers | ||
| Create Load Balancer | ||
| Get Load Balancer | ||
| Update Load Balancer | ||
| Delete Load Balancer | ||
| List Backends | ||
| Create Backend | ||
| Get Load Balancer Backend | ||
| Replace Load Balancer Backend | ||
| Delete Load Balancer Backend | ||
| List Rate Limit Configurations | ||
| Create Rate Limit Configuration | ||
| Get Rate Limit Configuration | ||
| Replace Rate Limit Configuration | ||
| Delete Rate Limit Configuration | ||
| Create Response | ||
| Get Tenant Usage | ||
| Get User Usage |