ベクトル・ストアとOCI生成AI APIキーによるドキュメントの検索

STORE_RESPONSE=$(curl --fail-with-body --silent --show-error \
  --request POST "$VECTOR_STORES_URL" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  --header 'Content-Type: application/json' \
  --data '{"name":"document-search-demo","expires_after":{"anchor":"last_active_at","days":1}}')

printf '%s\n' "$STORE_RESPONSE" | jq '{id, name, status}'
VECTOR_STORE_ID=$(printf '%s' "$STORE_RESPONSE" | jq -er '.id')

store = client.vector_stores.create(
    name="document-search-demo",
    expires_after={"anchor": "last_active_at", "days": 1},
)
print("Created store:", store.id, store.status)

curl --fail-with-body --silent --show-error \
  "$VECTOR_STORES_URL/$VECTOR_STORE_ID" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  | jq '{id, name, status}'

store = client.vector_stores.retrieve(store.id)
deadline = time.monotonic() + 120
while store.status == "in_progress":
    if time.monotonic() >= deadline:
        raise TimeoutError(f"Store creation is still in progress: {store.id}")
    time.sleep(2)
    store = client.vector_stores.retrieve(store.id)

if store.status != "completed":
    raise RuntimeError(f"Store is not ready: {store.id}, {store.status}")
print("Store is ready:", store.id)

curl --fail-with-body --silent --show-error \
  "$VECTOR_STORES_URL?limit=10" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  | jq '.data[] | {id, name, status}'

for item in client.vector_stores.list(limit=10).data:
    print(item.id, item.name, item.status)

FILE_RESPONSE=$(curl --fail-with-body --silent --show-error \
  --request POST "$FILES_URL" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  --header "OpenAI-Project: $GENAI_PROJECT_ID" \
  --form 'purpose=assistants' \
  --form 'file=@sample-document.txt')

printf '%s\n' "$FILE_RESPONSE" | jq '{id, filename}'
FILE_ID=$(printf '%s' "$FILE_RESPONSE" | jq -er '.id')

with open("sample-document.txt", "rb") as document:
    uploaded_file = client.files.create(
        file=document,
        purpose="assistants",
        extra_headers={"OpenAI-Project": PROJECT_ID},
    )
print("Uploaded file:", uploaded_file.id, uploaded_file.filename)

BATCH_RESPONSE=$(curl --fail-with-body --silent --show-error \
  --request POST "$VECTOR_STORES_URL/$VECTOR_STORE_ID/file_batches" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  --header 'Content-Type: application/json' \
  --data "$(jq -n --arg file_id "$FILE_ID" '{file_ids:[$file_id]}')")

printf '%s\n' "$BATCH_RESPONSE" | jq '{id, status, file_counts}'
BATCH_ID=$(printf '%s' "$BATCH_RESPONSE" | jq -er '.id')

curl --fail-with-body --silent --show-error \
  "$VECTOR_STORES_URL/$VECTOR_STORE_ID/file_batches/$BATCH_ID" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  | jq '{id, status, file_counts}'

batch = client.vector_stores.file_batches.create(
    vector_store_id=store.id,
    file_ids=[uploaded_file.id],
)
print("Ingestion batch:", batch.id)

deadline = time.monotonic() + 120
while batch.status == "in_progress":
    if time.monotonic() >= deadline:
        raise TimeoutError(f"Document ingestion is still in progress: {batch.id}")
    time.sleep(2)
    batch = client.vector_stores.file_batches.retrieve(
        batch.id, vector_store_id=store.id,
    )

counts = batch.file_counts
if (
    batch.status != "completed"
    or counts.completed != 1
    or counts.failed
    or counts.cancelled
):
    raise RuntimeError(
        f"Ingestion did not succeed: {batch.id}, {batch.status}, {counts}"
    )
print("Document is ready to search.")

curl --fail-with-body --silent --show-error \
  --request POST "$VECTOR_STORES_URL/$VECTOR_STORE_ID/search" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  --header 'Content-Type: application/json' \
  --data '{"query":"How long do I have to return a purchase?","max_num_results":3}' \
  | jq '.data[] | {filename, score, text:[.content[] | select(.type == "text") | .text]}'

query = "How long do I have to return a purchase?"
results = client.vector_stores.search(
    vector_store_id=store.id,
    query=query,
    max_num_results=3,
)

print("Question:", query)
if not results.data:
    print("No matching passages found.")
for result in results.data:
    print(f"\n{result.filename} (score: {result.score:.3f})")
    for content in result.content:
        if content.type == "text":
            print(content.text)

curl --fail-with-body --silent --show-error \
  --request POST "$VECTOR_STORES_URL/$VECTOR_STORE_ID" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  --header 'Content-Type: application/json' \
  --data '{"name":"document-search-demo-updated"}' \
  | jq '{id, name, status}'

store = client.vector_stores.update(
    store.id, name="document-search-demo-updated",
)
deadline = time.monotonic() + 120
while store.status == "in_progress":
    if time.monotonic() >= deadline:
        raise TimeoutError(f"Store update is still in progress: {store.id}")
    time.sleep(2)
    store = client.vector_stores.retrieve(store.id)

if store.status != "completed":
    raise RuntimeError(f"Store update did not complete: {store.id}, {store.status}")
print("Updated store:", store.id, store.name)

curl --fail-with-body --silent --show-error \
  --request DELETE "$VECTOR_STORES_URL/$VECTOR_STORE_ID" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  | jq '{id, deleted}'

curl --fail-with-body --silent --show-error \
  --request DELETE "$FILES_URL/$FILE_ID" \
  --header "Authorization: Bearer $GENAI_API_KEY" \
  --header "opc-compartment-id: $GENAI_COMPARTMENT_ID" \
  --header "OpenAI-Project: $GENAI_PROJECT_ID" \
  | jq '{id, deleted}'

deleted_store = client.vector_stores.delete(store.id)
print("Store deleted:", deleted_store.id, deleted_store.deleted)

deleted_file = client.files.delete(
    uploaded_file.id,
    extra_headers={"OpenAI-Project": PROJECT_ID},
)
print("File deleted:", deleted_file.id, deleted_file.deleted)
client.close()