Last updated
Graphlit now supports multi-turn summarization of text with the reviseText mutation. You can provide an LLM prompt and text string, along with an optional specification. This can be used for summarizing any raw text and having a multi-turn conversation with the LLM to revise the output from the LLM. (Colab Notebook Example)
Graphlit now supports image descriptions using vision LLMs, without needing to ingest the image first. With the new describeImage mutation, which takes a URI, and describeEncodedImage mutation, which takes a Base-64 encoded image and MIME type, you can use any vision LLM to prompt an image description. These mutations accept an optional specification, where you can select your vision LLM. If not provided, OpenAI GPT-4o will be used. (Colab Notebook Example)
