Zhaofeng Miao

> The researchgate link shows either empty content or "verify you are a human" content. If the website has anti-crawler mechnism, then unfortunatelly there is nothing we can do. :...

It's supported now. You can either pass `referer` in POST request body ``` curl --location 'https://r.jina.ai' \ --header 'Content-Type: application/json' \ --data '{ "url": "https://www.academia.edu/download/51627580/A_Generalized_Reinforcement-Learning_Mod20170203-31871-44ae37.pdf?hl=en&sa=T&oi=ggp&ct=res&cd=13&d=7556059458401941712&ei=IcXCZpzRGPCz6rQP5oSLmQM", "referer": "https://scholar.google.com/", "noCache": true }'...

Hi @timtensor Indeed it's not convenient to load the pdf in google drive (because of google's complex authentication and the path you mentioned) and in your local machine. Do you...

> @mapleeit yes that would be extremely helpful . If I understand with the api end point from jina reader we could actually parse pdfs locally without the need to...

> Do you think if that satisfies your need if we provide an API endpoint that supports you to upload your local pdf? The API is ready, here is the...

Hi @MaSchVam thanks for the suggestion and sorry for the late reply. It's indeed a nice idea. Let me check what I can do.

@nomagick I guess we need to separate stream response and non-stream response, here is what I'm thinking: - For stream response, use a separated event in the end to indicate...

Hi, I'm Jina AI's engineer. After some checking with @pprp We found the place that made the confusion: the credentials of **DataSource**, **Model(Provider)**, **Tools** are managed separately. And Jina have...

Hello @escapedcat didn't see much progress on this one. Just kindly asking, do you still consider adding this feature?