Hi Gaurav, Good article! Well done. However, I have some observations. As the code has been presented in parts, the use of these code parts goes in different places of a page? Also the integration with the GUI part is not presented. For example, what GUI Items need to be created on the page where I would like to use this code - for example: an image capture item, and image display item etc. Also the final HTML piece of code is not being mentioned how all the code parts are being used. And I have a question: I have a page developed in Oracle APEX to take a snap. This page uses the Java Script code to access the media to capture the image, store it in the DB and show the image on the page (check this: https://b1r1mryygmx24ne-phi.adb.us-ashburn-1.oraclecloudapps.com/ords/r/phi/propiedad-horizontal-inteligente/photo-flipper). So if I want to use this code you are using (with JavaScript+React) is it possible to use? Regards and once again congrats on the write-up. Ravi

Hi there! Good writeup. I am wondering whether you can give me some clues for these questions: While using the APEX AI Assistant there are literally no other controls what so ever for the end user. For example, a) I only want a user to ask a maximum of 5 questions. b) I only want a user chat interaction should last for a maximum 5 minutes c) There is no "User Consent" acceptance mechanism to this interface so as to show some disclaimer or a compliance note, so as to cover any applicable Data Privacy laws GDPR/HIPAA/etc. Once the chat bot is invoked, except from tuning the "system prompt" there are no other hard controls. These kind of controls seem to be necessary so as that some vicious user won't overwhelm the system, or I would like to control the budget for my backend OpenAI/Cohere/OCI paid services. Even Windows Copilot on my PC has 30 questions per session! Do you think, these kind of controls be acheived using the da.ai.xxxx mechanism? Can you throw any light on that? 2) Apart from using the AI Assistant from DA, did you happen to use the APEX_AI.GENERATE method via Server-side Script? Because that API is offering some methods on user consent; however when tried to use them I got stumbled because literally there is "NO" documentation what so ever on this aspect. Can you elaborate on this ? Regards Ravi

Hi there Thanks for your reply. For just a lab environment its doing "ok-ishh". The VM instance I used is the smallest one (1 CPU + 16GB RAM) in OCI. After trying to pull more than one model with ollama, I found out that even the default disk size is also not enough and I had to increase that. :-) During my testing phase there were some hiccups because I monitored that the ollama was thriving for both CPU and RAM and meanwhile the OCI API Gateway gets timed out. So, for a real world scenario, one must go with a GPU based instance, a baremetal instance or at least an instance with considerable amout of resources so that the things work consistently. My next adventure would be adding the RAG for this architecture...I might post the whole thing once I get things working. Regards. Ravi

Hi There. Don't bother...I got it working..!! Thanks for your post though, I got the idea of using open source local LLMs with APEX using my own OCI Instance and OCI API Gateways. Regards

Hi Jon Good Day and congrats for such an enriching blog. Do you have any implementation oriented article with the same philosophy..creating an OCI API Gateway for a local service? Regards

Hi Plamen, Good Day and congrats for such an enriching blog. Everything worked as your blog says (at least the very first time) and then onwards ngrok started giving troubles; may be because of the free account they might limit the traffic etc., but no issues. I have created an Oracle Linux instance in the OCI Tenancy (because my APEX app is there) and completed the OLLAMA setup successfully. Checked that the ollama service is getting accessed through internet; checked that I could access the OLLMA service over internet using postman as well as curl ang got results correctly. However, when tried to use the same URL (with the bare public IP that worked with cURL and Postman) APEX errored out saying taht the requested URL is prohibited. I created an API Gateway in OCI and trying to pass through it to reach the OLLAM service, however the AP Gateway is throwing error. If you are interested in probing and tweaking in to this architecture (accessing OLLAMA securely via OCI API Gateway) I am open to mutual colaboration. Regards