Skip to content

Use OpenAI models with DataZoneStandard deployment type #270

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
StefanTroost merged 2 commits into from
Feb 20, 2026
Merged

Use OpenAI models with DataZoneStandard deployment type #270

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
2694745
update due to old models
Feb 19, 2026
e44747c
removal of old models from options
Feb 20, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
26 changes: 8 additions & 18 deletions settings_template.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -116,37 +116,27 @@
# LLM_PROVIDER must be "azureopenai" in case of using the Azure OpenAI Services API
LLM_PROVIDER = "azureopenai"

# - If LLM_PROVIDER is "openai", LLM_MODEL must be one of:
# "gpt-3.5-turbo", context window size = 4097 tokens (equivalent to ~3000 words)
# "gpt-3.5-turbo-16k", context window size = 16385 tokens
# "gpt-4", context window size = 8192 tokens
# "gpt-4o", context window size = 128000 tokens
# The default llm is "gpt-3.5-turbo"
# - If LLM_PROVIDER is "openai", LLM_MODEL must be one of the OpenAI LLM models, e.g. "gpt-4o" or "gpt-4o-mini":
# - if LLM_PROVIDER is "huggingface", LLM_MODEL should be one of the models as defined on Huggingface,
# e.g. one of: "meta-llama/Llama-2-7b-chat-hf", "google/flan-t5-base"
# See Huggingface documentation for context window sizes
# note: "meta-llama/Llama-2-7b-chat-hf" requires Huggingface Pro Account and access to the llama2 model,
# see https://huggingface.co/meta-llama/Llama-2-7b-chat-hf
# - If LLM_PROVIDER is "ollama", LLM_MODEL must be one of your Ollama downloaded models, e.g.
# "llama3"
# "orca-mini"
# "zephyr"
# - If LLM_PROVIDER is "ollama", LLM_MODEL must be one of your Ollama downloaded models, e.g. "llama3", "orca-mini" or "zephyr"
# See also https://ollama.ai/library
# - LLM_PROVIDER is "azureopenai":
# "gpt-4", context window size = 8192 tokens, cost: $30.00 / $60.00 per 1M tokens
# - If LLM_PROVIDER is "azureopenai", LLM_MODEL must be one of the LLM models deployed, e.g.:
# "gpt-4o", context window size = 128000 tokens
# "gpt-4o-mini", context window size = 128000 tokens

# LLM_MODEL must be one of the LLM models deployed, e.g.:
# "gpt-35-turbo", context window size = 4097 tokens, cost: $0.50 / $1.50 per 1M tokens
# "gpt-4o", context window size = 128000 tokens, cost: $2.50 / $10.00 per 1M tokens
# LLM_MODEL must be one of the LLM models deployed
LLM_MODEL = "gpt-4o"

# AZURE_LLM_DEPLOYMENT_MAP represents a dictionary of Azure LLM model deployments
# with key the model name and value the deployment name\
# Adjust for your own Azure model deployments
AZURE_LLM_DEPLOYMENT_MAP = {
"gpt-35-turbo": "pbl-openai-a-cd-openai",
"gpt-4": "pbl-openai-a-cd-openai4",
"gpt-4o": "pbl-openai-a-cd-openai4o"
"gpt-4o": "gpt-4o-DataZoneStandard",
"gpt-4o-mini": "gpt-4o-mini-DataZoneStandard",
}

# AZURE_OPENAI_ENDPOINT represents the Azure OpenAI endpoint used for connecting to Azure OpenAI API
Expand Down
Loading