Models
Introduction to different models in Langdock.
One of our core-values is to build a tool which is model-agnostic. That means, that we do not want to trap the user in one model, but give the choice which model to use. Each model has different strengths and we encourage you to test the different models to find the best models for your specific need.
Selecting a model
- Whenever you start a new chat, you can use the model you want to work with at the top left.
- You can still change the model at the top left if you have already started a chat. For example, you can start with GPT-4-Turbo and, after three messages, switch to Claude-2.
- When you switch models in an ongoing chat, the entire context of the previous chat history and your data (documents, texts, websites) is always passed to the selected model. So, you don’t need to worry about keeping the context when switching models.
- As no data is ever stored in the models, the system provides all context to the model with every request you make.
- You can also set your personal default model in the account settings here. The default for new users is GPT-3.5-Turbo.
Model overview
Here is a description of the most-used models:
GPT-3.5 Turbo
The most-used model Langdock provides is GPT-3.5 by OpenAI. It has the highest speed and a sufficient quality in its responses for many use cases. Its knowledge reaches until September 2021.
GPT-4 Turbo
The newer, larger model from OpenAI provides the highest quality of responses at the moment. The downside is that it is slower than other models. Its knowledge cutoff date is April 2023.
GPT-4 is also the only model we have which is capable of analysing images (see image analysis in our chat guide).
Mistral Large
Mistral Large is the latest model by the French company Mistral. They claim Mistral large is outperforming GPT-4 in some reasoning tasks.
Claude 3 (coming soon)
Many users ask us when Claude 3 by Anthropic will be added to Langdock. We are waiting for it to be released by AWS in the EU and will add it immediately.
Claude 3 is supposed to be good with coding-related tasks and can avoid hallucinations better than GPT-4.
Was this page helpful?