DeepResearch has a strong multi-model support capability, and is currently compatible with the following four major types of large language models:
1. Cloud API model
- Google Gemini: Suitable for scenarios requiring up-to-date knowledge
- OpenAI GPT Series: Balancing performance and cost choices
- Azure OpenAI: the first choice for enterprise-level security needs
2. Aggregation service models
- OpenRouter: Support dozens of models for unified access
3. Local deployment model
- Ollama: Fully offline privacy protection program
Model Selection Recommendations:
- Emphasis on timeliness: Choice of Gemini or GPT-4-turbo
- Cost-conscious: OpenRouter's Mixtral and other open source models
- data-sensitive: Local deployment of Llama2/3 or Mistral
- Chinese Studies: Preference for ERNIE or GPT-4
Configuration method: set the corresponding API key in the .env file, or switch the model provider directly in the interface. The response speed and quality of different models may vary, so it is recommended to conduct a small-scale test first.
This answer comes from the articleDeepResearch: a fully open source AI assistant for automated deep researchThe
May not be reproduced without permission:AI productivity tools " What big language models does DeepResearch support? How to choose the most suitable model?
