import vertexai
from vertexai.preview import rag

vertexai.init(project="{project_id}", location="{region}")

# Approach A: List ALL (Automatic Pagination)
# The SDK's Pager iterates through all pages for you.
all_corpora = list(rag.list_corpora())
print(f"Found {len(all_corpora)} corpora in total.")
for c in all_corpora:
    print(f"Corpus Name: {c.name} | Display Name: {c.display_name}")

# Approach B: Manual Pagination (for very large projects)
pager = rag.list_corpora(page_size=10)
# Process first page
for c in pager:
    print(f"Corpus: {c.display_name}")

# Get next page if needed
if pager.next_page_token:
    second_page = rag.list_corpora(
        page_size=10, page_token=pager.next_page_token
    )

import vertexai
from vertexai.preview import rag

vertexai.init(project="{project_id}", location="{region}")
corpus_name = (
    "projects/{project_id}/locations/{region}/ragCorpora/{corpus_id}"
)

# List files with automatic pagination
files = list(rag.list_files(corpus_name=corpus_name))
print(f"Found {len(files)} files.")

for f in files:
    # High-level SDK RagFile objects usually have name, display_name,
    # description
    print(f"File: {f.display_name} | Resource: {f.name}")
    # Tip: Check extension to understand file type (PDF, TXT, etc.)
    if f.display_name.lower().endswith(".pdf"):
        print("  Type: PDF")
    elif f.display_name.lower().endswith(".txt"):
        print("  Type: Plain Text")

import vertexai
from vertexai.preview import rag

vertexai.init(project="{project_id}", location="{region}")

# To get details of a specific corpus
corpus_name = (
    "projects/{project_id}/locations/{region}/ragCorpora/{corpus_id}"
)
corpus = rag.get_corpus(name=corpus_name)
print(f"Corpus Name: {corpus.name}")
print(f"Display Name: {corpus.display_name}")

import vertexai
from vertexai.preview import rag

vertexai.init(project="{project_id}", location="{region}")

corpus_name = (
    "projects/{project_id}/locations/{region}/ragCorpora/{corpus_id}"
)
query = "What is the speed of light?"

# Retrieve contexts
response = rag.retrieval_query(
    rag_corpora=[corpus_name],
    text=query,
    similarity_top_k=3
)

for context in response.contexts.contexts:
    print(f"Context text: {context.text}")
    print(f"Source: {context.source_uri}")

from google import genai
from google.genai import types

client = genai.Client(enterprise=True, project="{project_id}", location="{region}")
corpus_name = (
    "projects/{project_id}/locations/{region}/ragCorpora/{corpus_id}"
)

# Define the Agent Platform RAG Engine tool pointing to the corpus
rag_tool = types.Tool(
    retrieval=types.Retrieval(
        vertex_rag_store=types.VertexRagStore(
            rag_resources=[types.VertexRagStoreRagResource(rag_corpus=corpus_name)],
            rag_retrieval_config=types.RagRetrievalConfig(
                top_k=3,
                filter=types.RagRetrievalConfigFilter(
                    vector_similarity_threshold=0.5,
                ),
            ),
        )
    )
)

# Generate content using the RAG Engine tool
response = client.models.generate_content(
    model="gemini-2.5-flash",
    contents="What is the speed of light?",
    config=types.GenerateContentConfig(
        tools=[rag_tool]
    )
)
print(response.text)