Skip to content
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.

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

Update model references from gpt-35-turbo to gpt-4o #1080

Merged
merged 21 commits into from
Jul 25, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
6 changes: 3 additions & 3 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -30,7 +30,7 @@ You will need the following items to run the sample:

| AI Service | Requirement |
| ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Azure OpenAI | - [Access](https://aka.ms/oai/access)<br>- [Resource](https://learn.microsoft.com/azure/ai-services/openai/how-to/create-resource?pivots=web-portal#create-a-resource)<br>- [Deployed models](https://learn.microsoft.com/azure/ai-services/openai/how-to/create-resource?pivots=web-portal#deploy-a-model) (`gpt-35-turbo` and `text-embedding-ada-002`) <br>- [Endpoint](https://learn.microsoft.com/azure/ai-services/openai/tutorials/embeddings?tabs=command-line#retrieve-key-and-endpoint)<br>- [API key](https://learn.microsoft.com/azure/ai-services/openai/tutorials/embeddings?tabs=command-line#retrieve-key-and-endpoint) |
| Azure OpenAI | - [Access](https://aka.ms/oai/access)<br>- [Resource](https://learn.microsoft.com/azure/ai-services/openai/how-to/create-resource?pivots=web-portal#create-a-resource)<br>- [Deployed models](https://learn.microsoft.com/azure/ai-services/openai/how-to/create-resource?pivots=web-portal#deploy-a-model) (`gpt-4o` and `text-embedding-ada-002`) <br>- [Endpoint](https://learn.microsoft.com/azure/ai-services/openai/tutorials/embeddings?tabs=command-line#retrieve-key-and-endpoint)<br>- [API key](https://learn.microsoft.com/azure/ai-services/openai/tutorials/embeddings?tabs=command-line#retrieve-key-and-endpoint) |
| OpenAI | - [Account](https://platform.openai.com/docs/overview)<br>- [API key](https://platform.openai.com/api-keys) |

# Instructions
Expand Down Expand Up @@ -66,7 +66,7 @@ You will need the following items to run the sample:
- `API_KEY`: The `API key` for Azure OpenAI or for OpenAI.
- `AZURE_OPENAI_ENDPOINT`: The Azure OpenAI resource `Endpoint` address. This is only required when using Azure OpenAI, omit `-Endpoint` if using OpenAI.

- > **IMPORTANT:** For `AzureOpenAI`, if you deployed models `gpt-35-turbo` and `text-embedding-ada-002` with custom names (instead of the default names), also use the parameters:
- > **IMPORTANT:** For `AzureOpenAI`, if you deployed models `gpt-4o` and `text-embedding-ada-002` with custom names (instead of the default names), also use the parameters:

```powershell
-CompletionModel {DEPLOYMENT_NAME} -EmbeddingModel {DEPLOYMENT_NAME}
Expand Down Expand Up @@ -142,7 +142,7 @@ You will need the following items to run the sample:
- `AZURE_OPENAI_ENDPOINT`: The Azure OpenAI resource `Endpoint` address.
- `API_KEY`: The `API key` for Azure OpenAI.

**IMPORTANT:** If you deployed models `gpt-35-turbo` and `text-embedding-ada-002`
**IMPORTANT:** If you deployed models `gpt-4o` and `text-embedding-ada-002`
with custom names (instead of the default names), you need to specify
the deployment names with three additional parameters:

Expand Down
8 changes: 4 additions & 4 deletions memorypipeline/appsettings.json
Original file line number Diff line number Diff line change
Expand Up @@ -141,15 +141,15 @@
// - Auth is the authentication type: "APIKey" or "AzureIdentity".
// - APIKey is the key generated to access the service.
// - Endpoint is the service endpoint url.
// - Deployment is a completion model (e.g., gpt-35-turbo, gpt-4).
// - Deployment is a completion model (e.g., gpt-4, gpt-4o).
// - APIType is the type of completion model: "ChatCompletion" or "TextCompletion".
// - MaxRetries is the maximum number of retries for a failed request.
//
"AzureOpenAIText": {
"Auth": "ApiKey",
//"APIKey": "", // dotnet user-secrets set "SemanticMemory:Services:AzureOpenAIText:APIKey" "MY_AZUREOPENAI_KEY"
"Endpoint": "",
"Deployment": "gpt-35-turbo",
"Deployment": "gpt-4o",
"APIType": "ChatCompletion",
"MaxRetries": 10
},
Expand All @@ -158,7 +158,7 @@
// - Auth is the authentication type: "APIKey" or "AzureIdentity".
// - APIKey is the key generated to access the service.
// - Endpoint is the service endpoint url.
// - Deployment is a embedding model (e.g., gpt-35-turbo, gpt-4).
// - Deployment is an embedding model (e.g., text-embedding-ada-002).
//
"AzureOpenAIEmbedding": {
"Auth": "ApiKey",
Expand All @@ -168,7 +168,7 @@
},
//
// AI completion and embedding configuration for OpenAI services.
// - TextModel is a completion model (e.g., gpt-35-turbo, gpt-4).
// - TextModel is a completion model (e.g., gpt-4, gpt-4o).
// - EmbeddingModelSet is an embedding model (e.g., "text-embedding-ada-002").
// - APIKey is the key generated to access the service.
// - OrgId is the optional OpenAI organization id/key.
Expand Down
4 changes: 2 additions & 2 deletions scripts/.env
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Default environment file to be read by scripts

# Default values
ENV_COMPLETION_MODEL_OPEN_AI="gpt-3.5-turbo"
ENV_COMPLETION_MODEL_AZURE_OPEN_AI="gpt-35-turbo"
ENV_COMPLETION_MODEL_OPEN_AI="gpt-4o"
ENV_COMPLETION_MODEL_AZURE_OPEN_AI="gpt-4o"
ENV_EMBEDDING_MODEL="text-embedding-ada-002"
ENV_ASPNETCORE="Development"
ENV_INSTANCE="https://login.microsoftonline.com"
Expand Down
4 changes: 2 additions & 2 deletions scripts/Variables.ps1
Original file line number Diff line number Diff line change
@@ -1,8 +1,8 @@
# Default environment file to be read by scripts

# Default values
$varCompletionModelOpenAI = "gpt-3.5-turbo"
$varCompletionModelAzureOpenAI = "gpt-35-turbo"
$varCompletionModelOpenAI = "gpt-4o"
$varCompletionModelAzureOpenAI = "gpt-4o"
$varEmbeddingModel = "text-embedding-ada-002"
$varASPNetCore = "Development"
$varInstance = "https://login.microsoftonline.com"
Expand Down
2 changes: 1 addition & 1 deletion scripts/deploy/main.bicep
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ param webSearcherPackageUri string = 'https://aka.ms/copilotchat/websearcher/lat
param aiService string = 'AzureOpenAI'

@description('Model to use for chat completions')
param completionModel string = 'gpt-35-turbo'
param completionModel string = 'gpt-4o'

@description('Model to use for text embeddings')
param embeddingModel string = 'text-embedding-ada-002'
Expand Down
4 changes: 2 additions & 2 deletions scripts/deploy/main.json
Original file line number Diff line number Diff line change
Expand Up @@ -5,7 +5,7 @@
"_generator": {
"name": "bicep",
"version": "0.28.1.47646",
"templateHash": "7267170677416144946"
"templateHash": "18195377528136882013"
}
},
"parameters": {
Expand Down Expand Up @@ -67,7 +67,7 @@
},
"completionModel": {
"type": "string",
"defaultValue": "gpt-35-turbo",
"defaultValue": "gpt-4o",
"metadata": {
"description": "Model to use for chat completions"
}
Expand Down
2 changes: 1 addition & 1 deletion webapi/appsettings.json
Original file line number Diff line number Diff line change
Expand Up @@ -309,7 +309,7 @@
// - Auth is the authentication type: "APIKey" or "AzureIdentity".
// - APIKey is the key generated to access the service.
// - Endpoint is the service endpoint url.
// - Deployment is a embedding model (e.g., gpt-35-turbo, gpt-4).
// - Deployment is an embedding model (e.g., text-embedding-ada-002).
//
"AzureOpenAIEmbedding": {
"Auth": "ApiKey",
Expand Down
Loading