Gemini API로 문서 처리 기능 살펴보기

import httpx
import base64

model = genai.GenerativeModel("gemini-1.5-flash")
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
doc_data = base64.standard_b64encode(httpx.get(doc_url).content).decode("utf-8")

prompt = "Summarize this document"

response = model.generate_content([{'mime_type':'application/pdf', 'data': doc_data}, prompt])
print(response.text)

import base64

model = genai.GenerativeModel("gemini-1.5-flash")
doc_path = "/path/to/file.pdf" # Replace with the actual path to your local PDF

# Read and encode the local file
with open(doc_path, "rb") as doc_file:
    doc_data = base64.standard_b64encode(doc_file.read()).decode("utf-8")

prompt = "Summarize this document"

response = model.generate_content([{'mime_type': 'application/pdf', 'data': doc_data}, prompt])

print(response.text)

import io
import httpx

model = genai.GenerativeModel("gemini-1.5-flash")
long_context_pdf_path = "https://www.nasa.gov/wp-content/uploads/static/history/alsj/a17/A17_FlightPlan.pdf" # Replace with the actual URL of your large PDF

# Retrieve and upload the PDF using the File API
doc_data = io.BytesIO(httpx.get(long_context_pdf_path).content)
sample_doc = genai.upload_file(data=doc_data, mime_type='application/pdf')

prompt = "Summarize this document"

response = model.generate_content([sample_doc, prompt])
print(response.text)

import google.generativeai as genai

model = genai.GenerativeModel("gemini-1.5-flash")
sample_pdf = genai.upload_file(media / "test.pdf")
response = model.generate_content(["Give me a summary of this pdf file.", sample_pdf])
print(response.text)
files.py

import google.generativeai as genai

myfile = genai.upload_file(media / "poem.txt")
file_name = myfile.name
print(file_name)  # "files/*"

myfile = genai.get_file(file_name)
print(myfile)
files.py

import io
import httpx

model = genai.GenerativeModel("gemini-1.5-flash")

doc_url_1 = "https://arxiv.org/pdf/2312.11805" # Replace with the URL to your first PDF
doc_url_2 = "https://arxiv.org/pdf/2403.05530" # Replace with the URL to your second PDF

# Retrieve and upload both PDFs using the File API
doc_data_1 = io.BytesIO(httpx.get(doc_url_1).content)
doc_data_2 = io.BytesIO(httpx.get(doc_url_2).content)

sample_pdf_1 = genai.upload_file(data=doc_data_1, mime_type='application/pdf')
sample_pdf_2 = genai.upload_file(data=doc_data_2, mime_type='application/pdf')

prompt = "What is the difference between each of the main benchmarks between these two papers? Output these in a table."

response = model.generate_content([sample_pdf_1, sample_pdf_2, prompt])
print(response.text)

import google.generativeai as genai

print("My files:")
for f in genai.list_files():
    print("  ", f.name)
files.py

import google.generativeai as genai

myfile = genai.upload_file(media / "poem.txt")

myfile.delete()

try:
    # Error.
    model = genai.GenerativeModel("gemini-1.5-flash")
    result = model.generate_content([myfile, "Describe this file."])
except google.api_core.exceptions.PermissionDenied:
    pass
files.py

import os
from google.generativeai import caching
import io
import httpx

# Define the path to the PDF document (or use a URL)
long_context_pdf_path = "https://www.nasa.gov/wp-content/uploads/static/history/alsj/a17/A17_FlightPlan.pdf" # Replace with the URL of your large PDF
doc_data = io.BytesIO(httpx.get(long_context_pdf_path).content)

# Upload the PDF document using the File API
document = genai.upload_file(data=doc_data, mime_type='application/pdf')

# Specify the model name and system instruction for caching
model_name = "gemini-1.5-flash-002" # Ensure this matches the model you intend to use
system_instruction = "You are an expert analyzing transcripts."

# Create a cached content object
cache = caching.CachedContent.create(
    model=model_name,
    system_instruction=system_instruction,
    contents=[document], # The document(s) and other content you wish to cache
)

# Display the cache details
print(cache)

# Initialize a generative model from the cached content
model = genai.GenerativeModel.from_cached_content(cache)

# Generate content using the cached prompt and document
response = model.generate_content("Please summarize this transcript")

# (Optional) Print usage metadata for insights into the API call
print(response.usage_metadata)

# Print the generated text
print(response.text)

for c in caching.CachedContent.list():
  print(c)

import datetime

cache.update(ttl=datetime.timedelta(hours=2))

cache.delete()