haiku.rag/tests/cassettes/test_converters/TestDoclingServeConverterIntegration.test_convert_text_real_service.yaml

511 lines
12 KiB
YAML

interactions:
- request:
body: "--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition: form-data; name=\"to_formats\"\r\n\r\njson\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition:
form-data; name=\"do_ocr\"\r\n\r\ntrue\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition: form-data; name=\"force_ocr\"\r\n\r\nfalse\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition:
form-data; name=\"ocr_engine\"\r\n\r\nauto\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition: form-data;
name=\"do_table_structure\"\r\n\r\ntrue\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition: form-data; name=\"table_mode\"\r\n\r\naccurate\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition:
form-data; name=\"table_cell_matching\"\r\n\r\ntrue\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition: form-data;
name=\"images_scale\"\r\n\r\n2.0\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition: form-data; name=\"image_export_mode\"\r\n\r\nembedded\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition:
form-data; name=\"include_images\"\r\n\r\nfalse\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition: form-data;
name=\"do_picture_description\"\r\n\r\nfalse\r\n--b76818aa08785867d7feea5e663b3613\r\nContent-Disposition: form-data;
name=\"files\"; filename=\"content.md\"\r\nContent-Type: text/markdown\r\n\r\n# Test Document\n\nThis is a test.\r\n--b76818aa08785867d7feea5e663b3613--\r\n"
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
content-length:
- '1300'
content-type:
- multipart/form-data; boundary=b76818aa08785867d7feea5e663b3613
host:
- localhost:5001
method: POST
uri: http://localhost:5001/v1/convert/file/async
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 2
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 2
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '152'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: 1
task_status: pending
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/status/poll/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '155'
content-type:
- application/json
parsed_body:
error_message: null
task_id: 1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
task_meta: null
task_position: null
task_status: success
task_type: convert
status:
code: 200
message: OK
- request:
body: ''
headers:
accept:
- '*/*'
accept-encoding:
- gzip, deflate, zstd
connection:
- keep-alive
host:
- localhost:5001
method: GET
uri: http://localhost:5001/v1/result/1ad62ce1-5260-4fdb-aab7-e17f7adc8ee5
response:
headers:
content-length:
- '1226'
content-type:
- application/json
parsed_body:
document:
doctags_content: null
filename: content.md
html_content: null
json_content:
body:
children:
- $ref: '#/texts/0'
- $ref: '#/texts/1'
content_layer: body
label: unspecified
meta: null
name: _root_
parent: null
self_ref: '#/body'
form_items: []
furniture:
children: []
content_layer: furniture
label: unspecified
meta: null
name: _root_
parent: null
self_ref: '#/furniture'
groups: []
key_value_items: []
name: content
origin:
binary_hash: 18149311266811077188
filename: content.md
mimetype: text/markdown
uri: null
pages: {}
pictures: []
schema_name: DoclingDocument
tables: []
texts:
- children: []
content_layer: body
formatting: null
hyperlink: null
label: title
meta: null
orig: Test Document
parent:
$ref: '#/body'
prov: []
self_ref: '#/texts/0'
text: Test Document
- children: []
content_layer: body
formatting: null
hyperlink: null
label: text
meta: null
orig: This is a test.
parent:
$ref: '#/body'
prov: []
self_ref: '#/texts/1'
text: This is a test.
version: 1.10.0
md_content: null
text_content: null
errors: []
processing_time: 0.003092042010393925
status: success
timings: {}
status:
code: 200
message: OK
version: 1