# Converting PDFs to PNG and sending into OpenAI API **URL:** \ **Category:** Questions\ **Tags:** open-ai\ **Created:** [June 12, 2024, 7:28am UTC](https://community.make.com/t/converting-pdfs-to-png-and-sending-into-openai-api/41386 "2024-06-12T07:28:04Z")\ **Posts on this page:** 4\ **Page:** 1
**Author:** ![Finn\_Erpff](https://avatars.discourse-cdn.com/v4/letter/f/a9adbd/32.png) [@Finn\_Erpff](https://community.make.com/u/Finn_Erpff)\ **Post date:** [June 12, 2024, 7:28am UTC](https://community.make.com/t/converting-pdfs-to-png-and-sending-into-openai-api/41386/1 "2024-06-12T07:28:04Z")
We are trying to build a process where OpenAI puts out the data from PDF documents with different page length, containing analysis data. Therefore the PDFs are uploaded into a google drive, converted to a PNG and sent to the OpenAI API. The result is then sent into a google docs for further processing. Our challenge as of right now is to ensure that the PNGs generated from a PDF are forwarded as a bundle to the OpenAI API. As of right now the process is not running smooth and we are trying to figure out what to improve. (Sorry for the bad description, we are new to Make.) Anyone already built the PDF to Open AI process? Happy to hear from you. ![image](https://europe1.discourse-cdn.com/flex013/uploads/make/original/3X/f/3/f32f80bf79702b92998c6653231d6e23e69438ab.png) ---
**Author:** ![samliew](https://dub1.discourse-cdn.com/flex013/user_avatar/community.make.com/samliew/32/13327_2.png) [@samliew](https://community.make.com/u/samliew)\ **Post date:** [June 12, 2024, 8:02am UTC](https://community.make.com/t/converting-pdfs-to-png-and-sending-into-openai-api/41386/2 "2024-06-12T08:02:16Z")
Welcome to the Make community! You may want to try - [Convert PDF to Images - #2 by samliew](https://community.make.com/t/convert-pdf-to-images/21278/2) - [Extract text from the image/PDF](https://community.make.com/t/extract-text-from-the-image-pdf/26366) - [Search results for 'parse pdf' - Make Community](https://community.make.com/search?q=parse%20pdf) - [Search results for 'extract pdf' - Make Community](https://community.make.com/search?q=extract%20pdf) Also, every result (item/record) from a search/match/convert module will output a bundle. To “combine” them into a single structure, you’ll need to use an aggregator of some sort. [Aggregators](https://www.make.com/en/help/modules/aggregator.html) are modules that accumulate **multiple bundles into one single bundle**. An example of a commonly-used aggregator module is the [Array aggregator](https://www.make.com/en/help/tools/flow-control.html#array-aggregator) module. The next popular aggregator is the [Text Aggregator](https://www.make.com/en/help/tools/tools.html#text-aggregator) which is very flexible and has applies to many use-cases. So, my guess is you need an aggregator somewhere, and even another module to convert the image to text, or convert PDF directly to text (so you can do away with an aggregator)! [samliew](https://samliew.com/services) – [request private consultation](https://samliew.com/request-quote?ServiceType=Automation%20Consultation&Referrer=Make) > ### Join the [Make Fans](https://samliew.com/make-discord-invite) Discord server to [chat](https://samliew.com/make-discord-invite) with other makers! ---
**Author:** ![Finn\_Erpff](https://avatars.discourse-cdn.com/v4/letter/f/a9adbd/32.png) [@Finn\_Erpff](https://community.make.com/u/Finn_Erpff)\ **Post date:** [June 12, 2024, 9:05am UTC](https://community.make.com/t/converting-pdfs-to-png-and-sending-into-openai-api/41386/3 "2024-06-12T09:05:47Z")
Thank you! I am taking inspiration out of this! Need to do some testing now. 🙂 ---
**Author:** ![Make\_Bot](https://dub1.discourse-cdn.com/flex013/user_avatar/community.make.com/make_bot/32/14661_2.png) [@Make\_Bot](https://community.make.com/u/Make_Bot)\ **Post date:** [September 10, 2024, 9:06am UTC](https://community.make.com/t/converting-pdfs-to-png-and-sending-into-openai-api/41386/4 "2024-09-10T09:06:15Z")