Is There a Way to Pass Pdf Files to Vertex Ai Without Uploading to Google Storage?

Question

is there a way to pass pdf files to vertexai without uploading to google storage? Their sdk supports it, was wondering how to do it with portkey
https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/inference

sega · Answer

the restriction is from vertex itself, can you confirm if you're actually able to use a public document with the sdk without uploading it to google storage?

Harold Senzei · Answer

from google import genai
from google.genai import types
import pathlib
import httpx client = genai.Client() doc_url = "https://discovery.ucl.ac.uk/id/eprint/10089234/1/343019_3_art_0_py4t4l_convrt.pdf" # Replace with the actual URL of your PDF # Retrieve and encode the PDF byte
filepath = pathlib.Path('file.pdf')
filepath.write_bytes(httpx.get(doc_url).content) prompt = "Summarize this document"
response = client.models.generate_content( model="gemini-1.5-flash", contents=[ types.Part.from_bytes( data=filepath.read_bytes(), mime_type='application/pdf', ), prompt])
print(response.text)https://ai.google.dev/gemini-api/docs/document-processing?lang=python@sega

sega · Answer

This is an example with pdf as base64 right? that should work with portkey too, but wasn't your query was about passing public url directly?

Harold Senzei · Answer

It works now thanks

Welcome to Portkey Forum

Is There a Way to Pass Pdf Files to Vertex Ai Without Uploading to Google Storage?