Supported Third-Party Provider Operations and Endpoints

Review a list of both the public and local, third-party providers and REST endpoints that are supported for vector generation, summarization, and text generation operations.

• Public or Remote REST Endpoint Providers

• Local REST Endpoint Provider

• REST Operations

• REST Endpoints

Public or Remote REST Endpoint Providers

You can use the following publicly-hosted, third-party REST endpoint providers that are supported to perform a range of REST operations:

• Cohere

• Google AI

• Hugging Face

• Oracle Cloud Infrastructure (OCI) Generative AI

• OpenAI

• Vertex AI

Local REST Endpoint Provider

You can use Ollama as a third-party REST endpoint provider, locally and privately on your Linux, Windows, and macOS systems.

Ollama is a free and open-source command-line interface tool that allows you to run open LLMs, such as Llama 3, Phi 3, Mistral, and Gemma 2. You can access Ollama using SQL and PL/SQL commands.

You can download and install Ollama on your local host as a service that runs in the background, from https://ollama.com/download. For detailed installation-specific steps, see Ollama Documentation.

REST Operations

The allowed REST operations and corresponding APIs for all REST providers are:

Operation	Provider	API
Generate embedding: You can convert textual documents and images to one or more vector embeddings.	For text input: All supported public and local providers For image input: Vertex AI	DBMS_VECTOR.UTL_TO_EMBEDDING and DBMS_VECTOR.UTL_TO_EMBEDDINGS DBMS_VECTOR_CHAIN.UTL_TO_EMBEDDING and DBMS_VECTOR_CHAIN.UTL_TO_EMBEDDINGS
Generate summary: You can extract a brief and comprehensive summary from textual documents.	All supported public and local providers	DBMS_VECTOR_CHAIN.UTL_TO_SUMMARY
Generate text: You can retrieve a descriptive response for textual prompts and images through conversations with LLMs.	For text input: All supported public and local providers For image input: Google AI, Hugging Face, OpenAI, Ollama, and Vertex AI	DBMS_VECTOR.UTL_TO_GENERATE_TEXT DBMS_VECTOR_CHAIN.UTL_TO_GENERATE_TEXT
Rerank results: You can reassess and reorder search results to retrieve a more relevant output.	Cohere and Vertex AI	DBMS_VECTOR.RERANK DBMS_VECTOR_CHAIN.RERANK

REST Endpoints

The supported REST endpoints and corresponding APIs for all REST providers are:

API	Provider	Endpoint
UTL_TO_EMBEDDING UTL_TO_EMBEDDINGS	Cohere	https://api.cohere.ai/v1/embed
	Google AI	https://generativelanguage.googleapis.com/v1beta/models/
	Hugging Face	https://api-inference.huggingface.co/pipeline/feature-extraction/
	Generative AI	https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/20231130/actions/embedText
	OpenAI	https://api.openai.com/v1/embeddings
	Ollama	http://localhost:11434/api/embeddings
	Vertex AI	https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/publishers/google/models/
UTL_TO_SUMMARY	Cohere	https://api.cohere.ai/v1/summarize
	Google AI	https://generativelanguage.googleapis.com/v1beta/models/
	Hugging Face	https://api-inference.huggingface.co/models/
	Generative AI	https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/20231130/actions/chat https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/20231130/actions/summarizeText
	Ollama	http://localhost:11434/api/generate
	OpenAI	https://api.openai.com/v1/chat/completions https://api.openai.com/v1/completions
	Vertex AI	https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/publishers/google/models/
UTL_TO_GENERATE_TEXT	Cohere	https://api.cohere.ai/v1/chat https://api.cohere.ai/v1/generate
	Google AI	https://generativelanguage.googleapis.com/v1beta/models/
	Hugging Face	https://api-inference.huggingface.co/models/
	Generative AI	https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/20231130/actions/chat https://inference.generativeai.us-chicago-1.oci.oraclecloud.com/20231130/actions/generateText
	Ollama	http://localhost:11434/api/generate
	OpenAI	https://api.openai.com/v1/chat/completions https://api.openai.com/v1/completions
	Vertex AI	https://LOCATION-aiplatform.googleapis.com/v1/projects/PROJECT/locations/LOCATION/publishers/google/models/
RERANK	Cohere	https://api.cohere.com/v1/rerank
	Vertex AI	https://discoveryengine.googleapis.com/v1/projects/PROJECT/locations/global/rankingConfigs/default_ranking_config:rank