DeepGen is an all-in-one generative AI platform integrating a wide range of models, agents, and Composite AIs. It eliminates the hassle of juggling multiple subscriptions by offering a single subscription or credit pack providing access to all. The platform offers multiple convenient interfaces, including web-based chat, Slack, Messenger, and email. Additionally, the agents offered by DeepGen can be customized to meet your specific needs.
model
?A model in the context of generative AI, such as ChatGPT or Midjourney, is a computer program that has been trained on a large amount of data. This training allows the model to generate new content, like text or images, that is similar to the data it was trained on. The model uses machine learning algorithms to understand patterns in the data and then generate new content based on those patterns. The quality and capabilities of the generated content depend on the size and quality of the training data, as well as the sophistication of the machine learning algorithms used to create the model.
agent
?Agents are a key feature of the DeepGen platform. Agents are designed to address the limitations of traditional GenAI, which is often focused on simple two-step interactions, by enabling more complex problem-solving and workflow automation. Agents decompose complex prompts into multiple sequential steps or queries, allowing for advanced reasoning, including math, research, and logical reasoning supported by real-time search of web and news sources. Furthermore, agents can be specialized, leveraging curated knowledge bases tailored to specific domains or tasks.
composite AI
?A composite AI is a selection of the best artificial intelligence models combined to perform a specific task. When queried, a composite AI provides answers from one or more of these individual models simultaneously, allowing for comparison and analysis of their responses. This approach enables users to evaluate the strengths and weaknesses of each model and potentially detect hallucinations or inaccuracies in their outputs.
Yes, custom agents can be developed by DeepGen and made publicly available, either using your website as a source for the knowledge base or by implementing Retrieval-Augmented Generation (RAG) on your knowledge base. The purpose of custom AIs is to provide AI-powered solutions that are specialized and optimized for your unique requirements, leveraging your own data and information.
DeepGen credits are used to generate responses from our AI models. For instance, asking a question to a model like GPT-4o typically costs around 1 DeepGen credit. However, the exact cost can be significantly higher or lower depending on the specific model and the number of tokens used. To keep track of your credit usage, simply navigate to the Account menu on the Chat page, where you can monitor your credit balance
Tokens can be thought of as pieces of words. Before the API processes the prompts, the input is broken down into tokens. These tokens are not cut up exactly where the words start or end - tokens can include trailing spaces and even sub-words. Here are some helpful rules of thumb for understanding tokens in terms of lengths: - 1 token ~= 4 chars in English - 1 token ~= ¾ words - 100 tokens ~= 75 words - 1-2 sentence ~= 30 tokens - 1 paragraph ~= 100 tokens - 1,500 words ~= 2048 tokens To get additional context on how tokens stack up, consider this: Wayne Gretzky’s quote "You miss 100% of the shots you don't take" contains 11 tokens. The transcript of the US Declaration of Independence contains 1,695 tokens. How words are split into tokens is also language-dependent. For example ‘Cómo estás’ (‘How are you’ in Spanish) contains 5 tokens (for 10 chars). The higher token-to-char ratio can make it more expensive to implement the API for languages other than English.
DeepGen is developed by Deepiks, an French AI company incubated at Ecole Polytechnique.
Support is provided exclusively by email at support@deepgen.app. Depending on the question, the answer is given by an AI within a few minutes or a human within 24 hours.
Deepiks is the company developing the DeepGen platform
Deepiks is proudly located in Paris Saclay, at the heart of one of Europe's most vibrant and innovative technology and research ecosystems. The mail address is: Deepiks SAS, 21 Rue Jean Rostand, 91400 Orsay, France.
Support is provided exclusively by email at support@deepgen.app. For other questions, you can contact Deepiks by email at contact@deepgen.app, or call the Paris Office at +33 9 71 42 79 39.