Spaces:
Build error
Build error
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ Reader converts any URL to an **LLM-friendly** input with a simple prefix `https
|
|
| 14 |
|
| 15 |
## Updates
|
| 16 |
|
| 17 |
-
- **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.
|
| 18 |
- **2024-05-03**: We finally resolved a DDoS attack since April 29th. Now our API is much more reliable and scalable than ever!
|
| 19 |
- **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.
|
| 20 |
- **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).
|
|
@@ -64,6 +64,7 @@ Note that in terms of completeness: `... > streamContent3 > streamContent2 > str
|
|
| 64 |
|
| 65 |
As you have already seen above, one can control the behavior of the Reader API using request headers. Here is a complete list of supported headers.
|
| 66 |
|
|
|
|
| 67 |
- You can ask the Reader API to forward cookies settings via the `x-set-cookie` header.
|
| 68 |
- Note that requests with cookies will not be cached.
|
| 69 |
- You can bypass `readability` filtering via the `x-respond-with` header, specifically:
|
|
@@ -73,7 +74,7 @@ As you have already seen above, one can control the behavior of the Reader API u
|
|
| 73 |
- `x-respond-with: screenshot` returns the URL of the webpage's screenshot
|
| 74 |
- You can specify a proxy server via the `x-proxy-url` header.
|
| 75 |
- You can bypass the cached page (lifetime 300s) via the `x-no-cache` header.
|
| 76 |
-
|
| 77 |
|
| 78 |
### JSON mode (super early beta)
|
| 79 |
|
|
|
|
| 14 |
|
| 15 |
## Updates
|
| 16 |
|
| 17 |
+
- **2024-05-08**: Image capion is off by default for better latency. To turn it on, set `x-with-generated-alt: true` in the request header.
|
| 18 |
- **2024-05-03**: We finally resolved a DDoS attack since April 29th. Now our API is much more reliable and scalable than ever!
|
| 19 |
- **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.
|
| 20 |
- **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).
|
|
|
|
| 64 |
|
| 65 |
As you have already seen above, one can control the behavior of the Reader API using request headers. Here is a complete list of supported headers.
|
| 66 |
|
| 67 |
+
- You can enable the image caption feature via the `x-with-generated-alt: true` header.
|
| 68 |
- You can ask the Reader API to forward cookies settings via the `x-set-cookie` header.
|
| 69 |
- Note that requests with cookies will not be cached.
|
| 70 |
- You can bypass `readability` filtering via the `x-respond-with` header, specifically:
|
|
|
|
| 74 |
- `x-respond-with: screenshot` returns the URL of the webpage's screenshot
|
| 75 |
- You can specify a proxy server via the `x-proxy-url` header.
|
| 76 |
- You can bypass the cached page (lifetime 300s) via the `x-no-cache` header.
|
| 77 |
+
|
| 78 |
|
| 79 |
### JSON mode (super early beta)
|
| 80 |
|