xparse-client 0.3.0b9__py3-none-any.whl → 0.3.0b10__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- example/1_basic_api_usage.py +3 -3
- example/2_async_job.py +2 -1
- {xparse_client-0.3.0b9.dist-info → xparse_client-0.3.0b10.dist-info}/METADATA +22 -18
- {xparse_client-0.3.0b9.dist-info → xparse_client-0.3.0b10.dist-info}/RECORD +7 -7
- {xparse_client-0.3.0b9.dist-info → xparse_client-0.3.0b10.dist-info}/WHEEL +0 -0
- {xparse_client-0.3.0b9.dist-info → xparse_client-0.3.0b10.dist-info}/licenses/LICENSE +0 -0
- {xparse_client-0.3.0b9.dist-info → xparse_client-0.3.0b10.dist-info}/top_level.txt +0 -0
example/1_basic_api_usage.py
CHANGED
|
@@ -95,9 +95,9 @@ def example_2_extract_structured_data():
|
|
|
95
95
|
)
|
|
96
96
|
|
|
97
97
|
print("\n✅ 提取成功!")
|
|
98
|
-
# Extract API 返回的数据在
|
|
99
|
-
if result.
|
|
100
|
-
print(f" 提取的数据: {result.
|
|
98
|
+
# Extract API 返回的数据在 result.result 中
|
|
99
|
+
if result.result:
|
|
100
|
+
print(f" 提取的数据: {result.result}")
|
|
101
101
|
else:
|
|
102
102
|
print(" 未提取到数据")
|
|
103
103
|
|
example/2_async_job.py
CHANGED
|
@@ -52,7 +52,8 @@ def example_1_create_and_wait():
|
|
|
52
52
|
print(f" - 任务 ID: {result.job_id}")
|
|
53
53
|
print(f" - 文件 ID: {result.file_id}")
|
|
54
54
|
print(f" - 结果 URL: {result.result_url}")
|
|
55
|
-
print("\n 💡 提示:
|
|
55
|
+
print("\n 💡 提示: 异步任务只返回 result_url,需要另外下载来获取解析结果")
|
|
56
|
+
print(" result_url 是一个可以下载的 JSON 文件 URL")
|
|
56
57
|
elif result.is_failed:
|
|
57
58
|
print(f"\n❌ 任务失败: {result.error_message}")
|
|
58
59
|
else:
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: xparse-client
|
|
3
|
-
Version: 0.3.
|
|
3
|
+
Version: 0.3.0b10
|
|
4
4
|
Summary: 面向 Agent 和 RAG 的文档处理 Pipeline 客户端
|
|
5
5
|
Author-email: INTSIG-TEXTIN <support@textin.com>
|
|
6
6
|
License-Expression: MIT
|
|
@@ -223,6 +223,7 @@ with open("document.pdf", "rb") as f:
|
|
|
223
223
|
extract_config=ExtractConfig(schema=schema)
|
|
224
224
|
)
|
|
225
225
|
|
|
226
|
+
# Extract API 返回的结构化数据在 result.result 中
|
|
226
227
|
print(result.result)
|
|
227
228
|
```
|
|
228
229
|
|
|
@@ -277,22 +278,11 @@ result = client.parse.wait_for_result(
|
|
|
277
278
|
poll_interval=5.0
|
|
278
279
|
)
|
|
279
280
|
|
|
280
|
-
|
|
281
|
-
|
|
282
|
-
|
|
283
|
-
|
|
284
|
-
|
|
285
|
-
```python
|
|
286
|
-
# 同步调用(适合小文件)
|
|
287
|
-
result = client.parse.partition(file=f, filename="doc.pdf")
|
|
288
|
-
|
|
289
|
-
# 异步调用(相同接口,加上 _async 后缀)
|
|
290
|
-
import asyncio
|
|
291
|
-
|
|
292
|
-
async def main():
|
|
293
|
-
result = await client.parse.partition_async(file=f, filename="doc.pdf")
|
|
294
|
-
|
|
295
|
-
asyncio.run(main())
|
|
281
|
+
if result.is_completed:
|
|
282
|
+
print(f"任务完成,结果 URL: {result.result_url}")
|
|
283
|
+
print("💡 异步任务返回的是 result_url,需要另外下载来获取解析结果")
|
|
284
|
+
elif result.is_failed:
|
|
285
|
+
print(f"任务失败: {result.error_message}")
|
|
296
286
|
```
|
|
297
287
|
|
|
298
288
|
---
|
|
@@ -326,7 +316,17 @@ result = client.pipeline.execute(
|
|
|
326
316
|
|
|
327
317
|
### 📊 详细的处理统计
|
|
328
318
|
|
|
319
|
+
Pipeline API 返回详细的处理统计信息:
|
|
320
|
+
|
|
329
321
|
```python
|
|
322
|
+
# 使用 Pipeline API 时可以获取统计信息
|
|
323
|
+
result = client.pipeline.execute(
|
|
324
|
+
file=f,
|
|
325
|
+
filename="document.pdf",
|
|
326
|
+
stages=[ParseStage(...), ChunkStage(...), EmbedStage(...)]
|
|
327
|
+
)
|
|
328
|
+
|
|
329
|
+
# 访问统计信息
|
|
330
330
|
print(f"原始元素: {result.stats.original_elements}")
|
|
331
331
|
print(f"分块后: {result.stats.chunked_elements}")
|
|
332
332
|
print(f"向量化: {result.stats.embedded_elements}")
|
|
@@ -750,11 +750,15 @@ job = client.parse.create_async_job(file=f, filename="large.pdf")
|
|
|
750
750
|
|
|
751
751
|
# 方式 1:自动等待完成
|
|
752
752
|
result = client.parse.wait_for_result(job_id=job.job_id, timeout=300)
|
|
753
|
+
if result.is_completed:
|
|
754
|
+
print(f"任务完成,结果 URL: {result.result_url}")
|
|
755
|
+
# 注意:异步任务返回的是 result_url,需要另外下载来获取解析结果
|
|
753
756
|
|
|
754
757
|
# 方式 2:手动轮询
|
|
755
758
|
while True:
|
|
756
759
|
status = client.parse.get_result(job_id=job.job_id)
|
|
757
|
-
if status.
|
|
760
|
+
if status.is_completed:
|
|
761
|
+
print(f"结果 URL: {status.result_url}")
|
|
758
762
|
break
|
|
759
763
|
time.sleep(5)
|
|
760
764
|
```
|
|
@@ -1,5 +1,5 @@
|
|
|
1
|
-
example/1_basic_api_usage.py,sha256=
|
|
2
|
-
example/2_async_job.py,sha256=
|
|
1
|
+
example/1_basic_api_usage.py,sha256=wUng_3X-6v_dEWD0CvTKzoYUhvNkYlCML0PE2gCPC1Q,5700
|
|
2
|
+
example/2_async_job.py,sha256=n_2nv_GJPJ1t2-6yHGWK1K7uHd8InG63s8C6bL96iS8,6313
|
|
3
3
|
example/3_local_workflow.py,sha256=ZxoT8N0Nz4_s-bkLF0l6UDqBJk_eZZi99WUtUhJseXs,8980
|
|
4
4
|
example/4_advanced_workflow.py,sha256=KH6gmzoKi6oeHIPDv9snw1YehynHTDqWVq1WFtoqGws,10156
|
|
5
5
|
example/README.md,sha256=d-DumaZwbV96K6ZTEryAlDSk9HUhRBg0gG_Yekx9PqA,2336
|
|
@@ -61,8 +61,8 @@ xparse_client/models/local.py,sha256=hqKmyWTU_EhPk6qybtBzmbLybBBaiasTpqM4_zP-ipo
|
|
|
61
61
|
xparse_client/models/parse.py,sha256=COgxroHkJce_S7d2HGd_1zBYhkpCutGtmjyLnpI2_eI,3154
|
|
62
62
|
xparse_client/models/pipeline.py,sha256=24bDzhrVotQ8St6VLEJLvG2cZF0G2AMioKI34I_hJXI,3297
|
|
63
63
|
xparse_client/models/workflows.py,sha256=BivMdGOAmhP6oYLQSGAAN7yml2xb7vHHrpzwLgN_Afk,1754
|
|
64
|
-
xparse_client-0.3.
|
|
65
|
-
xparse_client-0.3.
|
|
66
|
-
xparse_client-0.3.
|
|
67
|
-
xparse_client-0.3.
|
|
68
|
-
xparse_client-0.3.
|
|
64
|
+
xparse_client-0.3.0b10.dist-info/licenses/LICENSE,sha256=7iuki7DyWMGB8PBzsht7PUt0YjdIcPjrcXNyUFgMJsw,1070
|
|
65
|
+
xparse_client-0.3.0b10.dist-info/METADATA,sha256=SV-pasi2iASwYXsWFRdLli2uGIQpGAeBfqE5eXM-HMg,25873
|
|
66
|
+
xparse_client-0.3.0b10.dist-info/WHEEL,sha256=wUyA8OaulRlbfwMtmQsvNngGrxQHAvkKcvRmdizlJi0,92
|
|
67
|
+
xparse_client-0.3.0b10.dist-info/top_level.txt,sha256=oQGc_qysOmnSAaLjwB72wH8RBHRAmxB-_qb-Uj6u56o,28
|
|
68
|
+
xparse_client-0.3.0b10.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|
|
File without changes
|