These configuration settings determine the default selection of which Large Language Model (LLM) and Embedding Model will be used if enabled for different sub-systems in the AO Platform as well as which Vector Store has been integrated as the default.
If a commercial LLM is enabled (compared to an Open Source LLM), then each transaction (API request) will incur a transaction fee.
Properties
Label
Defaults
Description
Default LLM Model
Open AI Chat GPT 4.0 Turbo 1106
Use the dropdown to select from available Large Language Model (LLM) configurations. This selection will become the default for any LLM-enabled functionality, including Text2SQL transformations, and Quick Insights Summarizations.
Anthropic Claude 3 Haiku 20240307
Anthropic Claude Haiku 3.5
Anthropic Claude Opus 3
Anthropic Claude Opus 4 20250514
Anthropic Claude Sonnet 3 20240229
Anthropic Claude Sonnet 3.5 20240620
Anthropic Claude Sonnet 3.5 v2
Anthropic Claude Sonnet 3.7
Anthropic Claude Sonnet 4 20250514
Azure OpenAI ChatGPT 4o
DeepSeek Chat
DeepSeek R1 14B
DeepSeek R1 7B
DeepSeek R1 8B
Google Gemini 1.5 Pro 001
Google Gemini 1.5 Pro 002
Google Gemini 2.0 Flash
Google Gemini 2.0 Flash Lite Preview 02-05
Google Gemini Pro
Meta Llama 13B
Meta Llama 3 70B Instruct
Meta Llama 3 70B Instruct Run Pod Version
Meta Llama 3 8B Instruct
Meta Llama 70B
Mistral 7B Instruct v0.2
Mistral 8x7B Instruct v0.1
Mistral 8x7B v0.1
OpenAI ChatGPT 3.5 Turbo 1106
OpenAI ChatGPT 4.0
OpenAI ChatGPT 4.0 Omni
OpenAI ChatGPT 4.0 Omni for Vision
OpenAI ChatGPT 4.0 Omni Mini
OpenAI ChatGPT 4.0 Omni Mini for Vision
OpenAI ChatGPT 4.0 Omni-2024-08-06
OpenAI ChatGPT 4.0 Turbo 1106
OpenAI ChatGPT 4.1
OpenAI ChatGPT 4.1 Mini
OpenAI ChatGPT 4.1 Nano
OpenAI ChatGPT o1-mini Reasoning
OpenAI ChatGPT o1 Reasoning
OpenAI ChatGPT o3-mini Reasoning
OpenAI ChatGPT o3 Reasoning
OpenAI ChatGPT o4-mini Reasoning
Default Embedding Model
Text Embedding ADA 2
An LLM Embedding Model transforms words into numerical vectors, capturing the semantic meaning and relationships, enabling LLMs to understand and process information more effectively. Use the dropdown to select an Embedding Model from the available configurations. This selection will be used as the default for interpreting questions in Easy Answers and Chatbot if LLM is enabled on the Text2SQL page.
All Minilm L6 V2
All Mpnet Base V2
BGE Large English
bge-m3
clip-vit-large-patch14-336
stella_en_1.5B_v5
Text Embedding 3 Large (1014)
Text Embedding 3 Large (256)
Text Embedding 3 Large (3072)
Text Embedding 3 Small (1536)
Text Embedding 3 Small (512)
Text Embedding ADA 2
Universal Sentence Encoder 4
Default Repository Embedding Model
BGE Large English
An LLM Embedding Model transforms words and sentences into numerical vectors, capturing the semantic meaning and relationships, enabling LLMs to understand and process information more effectively. Use the dropdown to select an Embedding Model from the available configurations. This selection will be used as the default for interpreting questions in Easy Answers against a Content Repository.
All Minilm L6 V2
All Mpnet Base V2
BGE Large English
bge-m3
clip-vit-large-patch14-336
stella_en_1.5B_v5
Text Embedding 3 Large (1014)
Text Embedding 3 Large (256)
Text Embedding 3 Large (3072)
Text Embedding 3 Small (1536)
Text Embedding 3 Small (512)
Text Embedding ADA 2
Universal Sentence Encoder 4
Default Vector Store
Weaviate DB
Select a Vector Store to use. This selection will be considered the default Vector Store used to provide alternative question suggestions in Easy Answers if the question the user is asking isn’t fully understood. The use of a Vector Store will need to be enabled on the Text2SQL page in the Vector Store Settings section. Options include:
Weaviate DB
Pinecone DB
Default Data Summarization Model
Open AI Chat GPT 4.1
Use the dropdown to select from available Large Language Model (LLM) configurations. This selection will become the default for any LLM-enabled functionality, including Text2SQL transformations, and Quick Insights Summarizations.
