From b7523f0b2af107c55c9cc167f0cdb3aee154aba6 Mon Sep 17 00:00:00 2001 From: Han Xiao Date: Wed, 8 May 2024 13:30:28 +0200 Subject: [PATCH] Update README.md --- README.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 0b46888..67847d7 100644 --- a/README.md +++ b/README.md @@ -14,6 +14,7 @@ Reader converts any URL to an **LLM-friendly** input with a simple prefix `https ## Updates +- **2024-05-08**: Image capion is off by default for better latency. To turn it on, set `x-with-generated-alt` in the request header. - **2024-05-03**: We finally resolved a DDoS attack since April 29th. Now our API is much more reliable and scalable than ever! - **2024-04-24**: You now have more fine-grained control over Reader API [using headers](#using-request-headers), e.g. forwarding cookies, using HTTP proxy. - **2024-04-15**: Reader now supports image reading! It captions all images at the specified URL and adds `Image [idx]: [caption]` as an alt tag (if they initially lack one). This enables downstream LLMs to interact with the images in reasoning, summarizing etc. [See example here](https://x.com/JinaAI_/status/1780094402071023926). @@ -72,7 +73,7 @@ As you have already seen above, one can control the behavior of the Reader API u - `x-respond-with: screenshot` returns the URL of the webpage's screenshot - You can specify a proxy server via the `x-proxy-url` header. - You can bypass the cached page (lifetime 300s) via the `x-no-cache` header. -- You can enable alt-text generation feature via the `x-with-generated-alt` header. +- You can enable the image caption feature via the `x-with-generated-alt` header. ### JSON mode (super early beta)