# November 16: Support for image description, multi-turn text summarization ### New Features * :bulb: 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](https://colab.research.google.com/github/graphlit/graphlit-samples/blob/main/python/Notebook%20Examples/Graphlit_2024_11_11_Multi_turn_Summarization.ipynb)) * :bulb: 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](https://colab.research.google.com/github/graphlit/graphlit-samples/blob/main/python/Notebook%20Examples/Graphlit_2024_11_16_Describe_Image_with_Vision_LLM.ipynb)) --- # Agent Instructions: Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://changelog.graphlit.dev/november-2024/november-16-support-for-image-description-multi-turn-text-summarization.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.