diff --git a/README.md b/README.md index b45863c7..9339c575 100644 --- a/README.md +++ b/README.md @@ -109,8 +109,8 @@ VISUAL_MODE: True, # Whether to use the visual mode API_TYPE: "openai" , # The API type, "openai" for the OpenAI API. API_BASE: "https://api.openai.com/v1/chat/completions", # The the OpenAI API endpoint. API_KEY: "sk-", # The OpenAI API key, begin with sk- -API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default -API_MODEL: "gpt-4-vision-preview", # The only OpenAI model +API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default +API_MODEL: "gpt-4o-mini", # The OpenAI model name, "gpt-4o-mini" by default. You may also use "gpt-4o" for using the GPT-4O model. ``` #### Azure OpenAI (AOAI) @@ -119,8 +119,8 @@ VISUAL_MODE: True, # Whether to use the visual mode API_TYPE: "aoai" , # The API type, "aoai" for the Azure OpenAI. API_BASE: "YOUR_ENDPOINT", # The AOAI API address. Format: https://{your-resource-name}.openai.azure.com API_KEY: "YOUR_KEY", # The aoai API key -API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default -API_MODEL: "gpt-4-vision-preview", # The only OpenAI model +API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default +API_MODEL: "gpt-4o-mini", # The OpenAI model name, "gpt-4o-mini" by default. You may also use "gpt-4o" for using the GPT-4O model. API_DEPLOYMENT_ID: "YOUR_AOAI_DEPLOYMENT", # The deployment id for the AOAI API ``` You can also non-visial model (e.g., GPT-4) for each agent, by setting `VISUAL_MODE: False` and proper `API_MODEL` (openai) and `API_DEPLOYMENT_ID` (aoai). You can also optionally set an backup LLM engine in the field of `BACKUP_AGENT` if the above engines failed during the inference. diff --git a/documents/docs/configurations/pricing_configuration.md b/documents/docs/configurations/pricing_configuration.md index 5bdac7d2..25f2017e 100644 --- a/documents/docs/configurations/pricing_configuration.md +++ b/documents/docs/configurations/pricing_configuration.md @@ -18,6 +18,8 @@ PRICES: { "openai/gpt-4-turbo": {"input":0.01,"output": 0.03}, "openai/gpt-4o": {"input": 0.005,"output": 0.015}, "openai/gpt-4o-2024-05-13": {"input": 0.005, "output": 0.015}, + "openai/gpt-4o-mini": {"input": 0.00015,"output": 0.0006}, + "openai/gpt-4o-mini-2024-07-18": {"input": 0.00015,"output": 0.0006}, "openai/gpt-3.5-turbo-0125": {"input": 0.0005, "output": 0.0015}, "openai/gpt-3.5-turbo-1106": {"input": 0.001, "output": 0.002}, "openai/gpt-3.5-turbo-instruct": {"input": 0.0015, "output": 0.002}, diff --git a/documents/docs/configurations/user_configuration.md b/documents/docs/configurations/user_configuration.md index 9bdc3ca1..157c64ab 100644 --- a/documents/docs/configurations/user_configuration.md +++ b/documents/docs/configurations/user_configuration.md @@ -14,8 +14,8 @@ Below are the configuration options for the LLMs, using OpenAI and Azure OpenAI | `API_TYPE` | The API type: "openai" for the OpenAI API, "aoai" for the AOAI API. | String | "openai" | | `API_BASE` | The API endpoint for the LLM | String | "https://api.openai.com/v1/chat/completions" | | `API_KEY` | The API key for the LLM | String | "sk-" | -| `API_VERSION` | The version of the API | String | "2024-02-15-preview" | -| `API_MODEL` | The LLM model name | String | "gpt-4-vision-preview" | +| `API_VERSION` | The version of the API | String | "gpt-4o-mini-2024-07-18" | +| `API_MODEL` | The LLM model name | String | "gpt-4o-mini" | ### For Azure OpenAI (AOAI) API The following additional configuration option is available for the AOAI API: diff --git a/documents/docs/getting_started/quick_start.md b/documents/docs/getting_started/quick_start.md index 6f0b6c65..913cec65 100644 --- a/documents/docs/getting_started/quick_start.md +++ b/documents/docs/getting_started/quick_start.md @@ -24,8 +24,8 @@ VISUAL_MODE: True, # Whether to use the visual mode API_TYPE: "openai" , # The API type, "openai" for the OpenAI API. API_BASE: "https://api.openai.com/v1/chat/completions", # The the OpenAI API endpoint. API_KEY: "sk-", # The OpenAI API key, begin with sk- -API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default -API_MODEL: "gpt-4-vision-preview", # The OpenAI model +API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default +API_MODEL: "gpt-4o-mini", # The OpenAI model name, "gpt-4o-mini" by default. You may also use "gpt-4o" for using the GPT-4O model. ``` @@ -35,8 +35,8 @@ VISUAL_MODE: True, # Whether to use the visual mode API_TYPE: "aoai" , # The API type, "aoai" for the Azure OpenAI. API_BASE: "YOUR_ENDPOINT", # The AOAI API address. Format: https://{your-resource-name}.openai.azure.com API_KEY: "YOUR_KEY", # The aoai API key -API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default -API_MODEL: "gpt-4-vision-preview", # The OpenAI model +API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default +API_MODEL: "gpt-4o-mini", # The OpenAI model name, "gpt-4o-mini" by default. You may also use "gpt-4o" for using the GPT-4O model. API_DEPLOYMENT_ID: "YOUR_AOAI_DEPLOYMENT", # The deployment id for the AOAI API ``` You can also non-visial model (e.g., GPT-4) for each agent, by setting `VISUAL_MODE: False` and proper `API_MODEL` (openai) and `API_DEPLOYMENT_ID` (aoai). You can also optionally set an backup LLM engine in the field of `BACKUP_AGENT` if the above engines failed during the inference. The `API_MODEL` can be any GPT models that can accept images as input. diff --git a/documents/docs/supported_models/azure_openai.md b/documents/docs/supported_models/azure_openai.md index 964f9c38..eb05cc01 100644 --- a/documents/docs/supported_models/azure_openai.md +++ b/documents/docs/supported_models/azure_openai.md @@ -11,8 +11,8 @@ VISUAL_MODE: True, # Whether to use visual mode to understand screenshots and ta API_TYPE: "aoai" , # The API type, "openai" for the OpenAI API, "aoai" for the AOAI API, 'azure_ad' for the ad authority of the AOAI API. API_BASE: "YOUR_ENDPOINT", # The AOAI API address. Format: https://{your-resource-name}.openai.azure.com API_KEY: "YOUR_KEY", # The aoai API key -API_VERSION: "2024-02-15-preview", # The version of the API, "2024-02-15-preview" by default -API_MODEL: "gpt-4-vision-preview", # The OpenAI model name, "gpt-4-vision-preview" by default. You may also use "gpt-4o" for using the GPT-4O model. +API_VERSION: "gpt-4o-mini-2024-07-18", # The version of the API, "gpt-4o-mini-2024-07-18" by default +API_MODEL: "gpt-4o-mini", # The OpenAI model name, "gpt-4o-mini" by default. You may also use "gpt-4o" for using the GPT-4O model. API_DEPLOYMENT_ID: "YOUR_AOAI_DEPLOYMENT", # The deployment id for the AOAI API ``` diff --git a/documents/docs/supported_models/openai.md b/documents/docs/supported_models/openai.md index 8e704c65..e07ffe26 100644 --- a/documents/docs/supported_models/openai.md +++ b/documents/docs/supported_models/openai.md @@ -13,8 +13,8 @@ VISUAL_MODE: True, # Whether to use visual mode to understand screenshots and ta API_TYPE: "openai" , # The API type, "openai" for the OpenAI API, "aoai" for the AOAI API, 'azure_ad' for the ad authority of the AOAI API. API_BASE: "https://api.openai.com/v1/chat/completions", # The the OpenAI API endpoint, "https://api.openai.com/v1/chat/completions" for the OpenAI API. API_KEY: "sk-", # The OpenAI API key, begin with sk- -API_VERSION: "2024-02-15-preview", # The version of the API, "2024-02-15-preview" by default -API_MODEL: "gpt-4-vision-preview", # The OpenAI model name, "gpt-4-vision-preview" by default. You may also use "gpt-4o" for using the GPT-4O model. +API_VERSION: "gpt-4o-mini-2024-07-18", # The version of the API, "gpt-4o-mini-2024-07-18" by default +API_MODEL: "gpt-4o-mini", # The OpenAI model name, "gpt-4o-mini" by default. You may also use "gpt-4o" for using the GPT-4O model. ``` !!! tip diff --git a/ufo/config/config.yaml.template b/ufo/config/config.yaml.template index 8b223019..b0b0ba6a 100644 --- a/ufo/config/config.yaml.template +++ b/ufo/config/config.yaml.template @@ -4,15 +4,15 @@ HOST_AGENT: { API_TYPE: "openai" , # The API type, "openai" for the OpenAI API, "aoai" for the AOAI API, 'azure_ad' for the ad authority of the AOAI API. API_BASE: "https://api.openai.com/v1/chat/completions", # The the OpenAI API endpoint, "https://api.openai.com/v1/chat/completions" for the OpenAI API. API_KEY: "sk-", # The OpenAI API key, begin with sk- - API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default - API_MODEL: "gpt-4-vision-preview", # The only OpenAI model by now that accepts visual input + API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default + API_MODEL: "gpt-4o-mini", # The OpenAI model name, "gpt-4o-mini" by default. You may also use "gpt-4o" for using the GPT-4O model. ### Comment above and uncomment these if using "aoai". # API_TYPE: "aoai" , # The API type, "openai" for the OpenAI API, "aoai" for the Azure OpenAI. # API_BASE: "YOUR_ENDPOINT", # The the OpenAI API endpoint, "https://api.openai.com/v1/chat/completions" for the OpenAI API. As for the aoai, it should be https://{your-resource-name}.openai.azure.com # API_KEY: "YOUR_KEY", # The aoai API key - # API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default + # API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default # API_MODEL: "YOUR_MODEL", # The only OpenAI model by now that accepts visual input # API_DEPLOYMENT_ID: "gpt-4-visual-preview", # The deployment id for the AOAI API @@ -28,15 +28,15 @@ APP_AGENT: { API_TYPE: "openai" , # The API type, "openai" for the OpenAI API, "aoai" for the AOAI API, 'azure_ad' for the ad authority of the AOAI API. API_BASE: "https://api.openai.com/v1/chat/completions", # The the OpenAI API endpoint, "https://api.openai.com/v1/chat/completions" for the OpenAI API. API_KEY: "sk-", # The OpenAI API key, begin with sk- - API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default - API_MODEL: "gpt-4-vision-preview", # The only OpenAI model by now that accepts visual input + API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default + API_MODEL: "gpt-4o-mini", # The OpenAI model name, "gpt-4o-mini" by default. You may also use "gpt-4o" for using the GPT-4O model. ### Comment above and uncomment these if using "aoai". # API_TYPE: "aoai" , # The API type, "openai" for the OpenAI API, "aoai" for the Azure OpenAI. # API_BASE: "YOUR_ENDPOINT", # The the OpenAI API endpoint, "https://api.openai.com/v1/chat/completions" for the OpenAI API. As for the aoai, it should be https://{your-resource-name}.openai.azure.com # API_KEY: "YOUR_KEY", # The aoai API key - # API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default + # API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default # API_MODEL: "YOUR_MODEL", # The only OpenAI model by now that accepts visual input # API_DEPLOYMENT_ID: "gpt-4-visual-preview", # The deployment id for the AOAI API @@ -52,15 +52,15 @@ BACKUP_AGENT: { API_TYPE: "openai" , # The API type, "openai" for the OpenAI API, "aoai" for the AOAI API, 'azure_ad' for the ad authority of the AOAI API. API_BASE: "https://api.openai.com/v1/chat/completions", # The the OpenAI API endpoint, "https://api.openai.com/v1/chat/completions" for the OpenAI API. API_KEY: "sk-", # The OpenAI API key, begin with sk- - API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default - API_MODEL: "gpt-4-vision-preview", # The only OpenAI model by now that accepts visual input + API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default + API_MODEL: "gpt-4o-mini", # The OpenAI model name, "gpt-4o-mini" by default. You may also use "gpt-4o" for using the GPT-4O model. ### Comment above and uncomment these if using "aoai". # API_TYPE: "aoai" , # The API type, "openai" for the OpenAI API, "aoai" for the Azure OpenAI. # API_BASE: "YOUR_ENDPOINT", # The the OpenAI API endpoint, "https://api.openai.com/v1/chat/completions" for the OpenAI API. As for the aoai, it should be https://{your-resource-name}.openai.azure.com # API_KEY: "YOUR_KEY", # The aoai API key - # API_VERSION: "2024-02-15-preview", # "2024-02-15-preview" by default + # API_VERSION: "gpt-4o-mini-2024-07-18", # "gpt-4o-mini-2024-07-18" by default # API_MODEL: "YOUR_MODEL", # The only OpenAI model by now that accepts visual input # API_DEPLOYMENT_ID: "gpt-4-visual-preview", # The deployment id for the AOAI API