diff --git a/docs/docs/gpt-researcher/llms/llms.md b/docs/docs/gpt-researcher/llms/llms.md index c8035a9ef..3ba344423 100644 --- a/docs/docs/gpt-researcher/llms/llms.md +++ b/docs/docs/gpt-researcher/llms/llms.md @@ -61,24 +61,39 @@ EMBEDDING="custom:your_embedding" ## Azure OpenAI -See also the documentation in the Langchain [Azure OpenAI](https://api.python.langchain.com/en/latest/chat_models/langchain_openai.chat_models.azure.AzureChatOpenAI.html) page. +In Azure OpenAI you have to chose which models you want to use and make deployments for each model. You do this on the [Azure OpenAI Portal](https://portal.azure.com/). -On Azure OpenAI you will need to create deployments for each model you want to use. Please also specify the model names/deployment names in your `.env` file: +In January 2025 the models that are recommended to use are: -Required Embedding Model: -To ensure optimal performance, GPT Researcher requires the text-embedding-3-large model. Please deploy this specific model to your Azure Endpoint. +- gpt-4o-mini +- gpt-4o +- o1-preview or o1-mini (You might need to request access to these models before you can deploy them). -```bash -AZURE_OPENAI_API_KEY=[Your Key] -AZURE_OPENAI_ENDPOINT=https://{your-endpoint}.openai.azure.com/ -OPENAI_API_VERSION=2024-05-01-preview +Please then specify the model names/deployment names in your `.env` file. + +**Required Precondition** -# note that the deployment name must be the same as the model name -FAST_LLM=azure_openai:gpt-4o-mini -SMART_LLM=azure_openai:gpt-4o -STRATEGIC_LLM=azure_openai:o1-preview +- Ypur endpoint can have any valid name. +- A model's deployment name *must be the same* as the model name. +- You need to deploy an *Embedding Model*: To ensure optimal performance, GPT Researcher requires the 'text-embedding-3-large' model. Please deploy this specific model to your Azure Endpoint. +**Recommended**: +- Quota increase: You should also request a quota increase especially for the embedding model, as the default quota is not sufficient. + +```bash +# set the azure api key and deployment as you have configured it in Azure Portal. There is no default access point unless you configure it yourself! +AZURE_OPENAI_API_KEY="[Your Key]" +AZURE_OPENAI_ENDPOINT="https://{your-endpoint}.openai.azure.com/" +OPENAI_API_VERSION="2024-05-01-preview" + +# each string is "azure_openai:deployment_name". ensure that your deployment have the same name as the model you use! +FAST_LLM="azure_openai:gpt-4o-mini" +SMART_LLM="azure_openai:gpt-4o" +STRATEGIC_LLM="azure_openai:o1-preview" + +# specify embedding +EMBEDDING="azure_openai:text-embedding-3-large" ```