AI/ragflow
1
0
Fork 0
mirror of https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git synced 2025-04-23 14:40:03 +08:00
Code Issues Packages Projects Releases Wiki Activity

Test: Add list chunk checkpoint for the add chunk API (#6482)

Browse Source 
### What problem does this PR solve?

Add list chunk checkpoint for the add chunk API

### Type of change

- [x] update test cases
This commit is contained in:
liu an 2025-03-25 10:36:21 +08:00 committed by GitHub
parent 05997e8215
commit 27989eb9a5
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 26 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
sdk/python/test/test_http_api/common.py
View File

@ -191,8 +191,8 @@ def list_chunks(auth, dataset_id, document_id, params=None):
def batch_add_chunks(auth, dataset_id, document_id, num):
ids = []
chunk_ids = []
for i in range(num):
res = add_chunk(auth, dataset_id, document_id, {"content": f"ragflow test {i}"})
ids.append(res["data"]["chunk"]["id"])
return ids
chunk_ids.append(res["data"]["chunk"]["id"])
return chunk_ids

24
sdk/python/test/test_http_api/test_chunk_management_within_dataset/test_add_chunk.py
View File

@ -16,7 +16,7 @@
from concurrent.futures import ThreadPoolExecutor
import pytest
from common import INVALID_API_TOKEN, add_chunk, delete_documnet
from common import INVALID_API_TOKEN, add_chunk, delete_documnet, list_chunks
from libs.auth import RAGFlowHttpApiAuth
@ -69,10 +69,14 @@ class TestAddChunk:
)
def test_content(self, get_http_api_auth, get_dataset_id_and_document_id, payload, expected_code, expected_message):
dataset_id, document_id = get_dataset_id_and_document_id
res = list_chunks(get_http_api_auth, dataset_id, document_id)
chunks_count = res["data"]["doc"]["chunk_count"]
res = add_chunk(get_http_api_auth, dataset_id, document_id, payload)
assert res["code"] == expected_code
if expected_code == 0:
validate_chunk_details(dataset_id, document_id, payload, res)
res = list_chunks(get_http_api_auth, dataset_id, document_id)
assert res["data"]["doc"]["chunk_count"] == chunks_count + 1
else:
assert res["message"] == expected_message
@ -93,10 +97,14 @@ class TestAddChunk:
)
def test_important_keywords(self, get_http_api_auth, get_dataset_id_and_document_id, payload, expected_code, expected_message):
dataset_id, document_id = get_dataset_id_and_document_id
res = list_chunks(get_http_api_auth, dataset_id, document_id)
chunks_count = res["data"]["doc"]["chunk_count"]
res = add_chunk(get_http_api_auth, dataset_id, document_id, payload)
assert res["code"] == expected_code
if expected_code == 0:
validate_chunk_details(dataset_id, document_id, payload, res)
res = list_chunks(get_http_api_auth, dataset_id, document_id)
assert res["data"]["doc"]["chunk_count"] == chunks_count + 1
else:
assert res["message"] == expected_message
@ -118,10 +126,14 @@ class TestAddChunk:
)
def test_questions(self, get_http_api_auth, get_dataset_id_and_document_id, payload, expected_code, expected_message):
dataset_id, document_id = get_dataset_id_and_document_id
res = list_chunks(get_http_api_auth, dataset_id, document_id)
chunks_count = res["data"]["doc"]["chunk_count"]
res = add_chunk(get_http_api_auth, dataset_id, document_id, payload)
assert res["code"] == expected_code
if expected_code == 0:
validate_chunk_details(dataset_id, document_id, payload, res)
res = list_chunks(get_http_api_auth, dataset_id, document_id)
assert res["data"]["doc"]["chunk_count"] == chunks_count + 1
else:
assert res["message"] == expected_message
@ -169,13 +181,19 @@ class TestAddChunk:
def test_repeated_add_chunk(self, get_http_api_auth, get_dataset_id_and_document_id):
payload = {"content": "a"}
dataset_id, document_id = get_dataset_id_and_document_id
res = list_chunks(get_http_api_auth, dataset_id, document_id)
chunks_count = res["data"]["doc"]["chunk_count"]
res = add_chunk(get_http_api_auth, dataset_id, document_id, payload)
assert res["code"] == 0
validate_chunk_details(dataset_id, document_id, payload, res)
res = list_chunks(get_http_api_auth, dataset_id, document_id)
assert res["data"]["doc"]["chunk_count"] == chunks_count + 1
res = add_chunk(get_http_api_auth, dataset_id, document_id, payload)
assert res["code"] == 0
validate_chunk_details(dataset_id, document_id, payload, res)
res = list_chunks(get_http_api_auth, dataset_id, document_id)
assert res["data"]["doc"]["chunk_count"] == chunks_count + 2
def test_add_chunk_to_deleted_document(self, get_http_api_auth, get_dataset_id_and_document_id):
dataset_id, document_id = get_dataset_id_and_document_id
@ -188,6 +206,8 @@ class TestAddChunk:
def test_concurrent_add_chunk(self, get_http_api_auth, get_dataset_id_and_document_id):
chunk_num = 50
dataset_id, document_id = get_dataset_id_and_document_id
res = list_chunks(get_http_api_auth, dataset_id, document_id)
chunks_count = res["data"]["doc"]["chunk_count"]
with ThreadPoolExecutor(max_workers=5) as executor:
futures = [
@ -202,3 +222,5 @@ class TestAddChunk:
]
responses = [f.result() for f in futures]
assert all(r["code"] == 0 for r in responses)
res = list_chunks(get_http_api_auth, dataset_id, document_id)
assert res["data"]["doc"]["chunk_count"] == chunks_count + chunk_num