Skip to content

Document the new async feature in the Python SDK #251

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 22 commits into from
Oct 7, 2024
Merged

Document the new async feature in the Python SDK #251

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
22 commits
Select commit Hold shift + click to select a range
d396124
Remove old deprecation warning
awalker4 Sep 23, 2024
b2e84c9
Add an example snippet for the new TypedDict interface
awalker4 Sep 23, 2024
a5a4fd1
Add a section about `partition_async`
awalker4 Sep 23, 2024
ae11711
Remove some whitespace
awalker4 Sep 23, 2024
4dfaa17
Update output filename in async example
awalker4 Sep 30, 2024
5bb108e
Add breaking change notes
awalker4 Sep 30, 2024
1657230
Try moving section
awalker4 Sep 30, 2024
719c15b
Minor updates
awalker4 Sep 30, 2024
61cf08a
Remove unneeded example params
awalker4 Sep 30, 2024
614da21
Move breaking change notes
awalker4 Oct 1, 2024
8d15254
Fix anchor link
awalker4 Oct 1, 2024
74f538d
Fix code indentation
awalker4 Oct 1, 2024
3c271fa
Clean up old SDK usage
awalker4 Oct 1, 2024
f940a58
Change use-ingest-instead guidance
awalker4 Oct 1, 2024
235e489
Update api-reference/api-services/sdk-python.mdx
awalker4 Oct 1, 2024
8f7bcb4
Update api-reference/api-services/sdk-python.mdx
awalker4 Oct 1, 2024
892be56
Update api-reference/api-services/sdk-python.mdx
awalker4 Oct 1, 2024
9515f6d
Apply suggestions from code review
awalker4 Oct 4, 2024
0646ecc
Add split pdf configuration back to sample code
awalker4 Oct 4, 2024
fe7ee5a
Remove migration guide sub header and use bold for sections
awalker4 Oct 4, 2024
29dd371
Add punctuation to code comments
awalker4 Oct 4, 2024
c9566eb
Remove duplicated param
awalker4 Oct 4, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
144 changes: 77 additions & 67 deletions api-reference/api-services/examples.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,7 +99,7 @@ The `hi_res` strategy supports different models, and the default is `layout_v1.1
import os

from unstructured_client import UnstructuredClient
from unstructured_client.models import shared
from unstructured_client.models import operations, shared
from unstructured_client.models.errors import SDKError

client = UnstructuredClient(
Expand All @@ -109,21 +109,23 @@ The `hi_res` strategy supports different models, and the default is `layout_v1.1

filename = "sample-docs/layout-parser-paper.pdf"
file = open(filename, "rb")
req = shared.PartitionParameters(
# Note that this currently only supports a single file
files=shared.Files(
content=file.read(),
file_name=filename,
),
strategy=shared.Strategy.HI_RES,
hi_res_model_name="layout_v1.1.0",
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
req = operations.PartitionRequest(
partition_parameters=shared.PartitionParameters(
# Note that this currently only supports a single file.
files=shared.Files(
content=file.read(),
file_name=filename,
),
strategy=shared.Strategy.HI_RES,
hi_res_model_name="layout_v1.1.0",
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
)
)

try:
res = client.general.partition(req)
res = client.general.partition(request=req)
print(res.elements[0])
except SDKError as e:
print(e)
Expand Down Expand Up @@ -248,7 +250,7 @@ For better OCR results, you can specify what languages your document is in using
import os

from unstructured_client import UnstructuredClient
from unstructured_client.models import shared
from unstructured_client.models import operations, shared
from unstructured_client.models.errors import SDKError

client = UnstructuredClient(
Expand All @@ -258,21 +260,23 @@ For better OCR results, you can specify what languages your document is in using

filename = "sample-docs/korean.png"
file = open(filename, "rb")
req = shared.PartitionParameters(
# Note that this currently only supports a single file
files=shared.Files(
content=file.read(),
file_name=filename,
),
strategy=shared.Strategy.OCR_ONLY,
languages=["kor"],
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
)
req = operations.PartitionRequest(
partition_parameters=shared.PartitionParameters(
# Note that this currently only supports a single file.
files=shared.Files(
content=file.read(),
file_name=filename,
),
strategy=shared.Strategy.OCR_ONLY,
languages=["kor"],
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
)
)

try:
res = client.general.partition(req)
res = client.general.partition(request=req)
print(res.elements[0])
except SDKError as e:
print(e)
Expand Down Expand Up @@ -394,7 +398,7 @@ Set the `coordinates` parameter to `true` to add this field to the elements in t
import os

from unstructured_client import UnstructuredClient
from unstructured_client.models import shared
from unstructured_client.models import operations, shared
from unstructured_client.models.errors import SDKError

client = UnstructuredClient(
Expand All @@ -404,21 +408,23 @@ Set the `coordinates` parameter to `true` to add this field to the elements in t

filename = "sample-docs/layout-parser-paper.pdf"
file = open(filename, "rb")
req = shared.PartitionParameters(
# Note that this currently only supports a single file
files=shared.Files(
content=file.read(),
file_name=filename,
),
strategy=shared.Strategy.HI_RES,
coordinates=True,
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
req = operations.PartitionRequest(
partition_parameters=shared.PartitionParameters(
# Note that this currently only supports a single file.
files=shared.Files(
content=file.read(),
file_name=filename,
),
strategy=shared.Strategy.HI_RES,
coordinates=True,
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
)
)

try:
res = client.general.partition(req)
res = client.general.partition(request=req)
print(res.elements[0])
except SDKError as e:
print(e)
Expand Down Expand Up @@ -543,7 +549,7 @@ This can be helpful if you'd like to use the IDs as a primary key in a database,
import os

from unstructured_client import UnstructuredClient
from unstructured_client.models import shared
from unstructured_client.models import operations, shared
from unstructured_client.models.errors import SDKError

client = UnstructuredClient(
Expand All @@ -553,21 +559,23 @@ This can be helpful if you'd like to use the IDs as a primary key in a database,

filename = "sample-docs/layout-parser-paper-fast.pdf"
file = open(filename, "rb")
req = shared.PartitionParameters(
# Note that this currently only supports a single file
files=shared.Files(
content=file.read(),
file_name=filename,
),
unique_element_ids=True,
strategy=shared.Strategy.HI_RES,
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
req = operations.PartitionRequest(
partition_parameters=shared.PartitionParameters(
# Note that this currently only supports a single file.
files=shared.Files(
content=file.read(),
file_name=filename,
),
unique_element_ids=True,
strategy=shared.Strategy.HI_RES,
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
)
)

try:
res = client.general.partition(req)
res = client.general.partition(request=req)
print(res.elements[0])
except SDKError as e:
print(e)
Expand Down Expand Up @@ -698,7 +706,7 @@ By default, the `chunking_strategy` is set to `None`, and no chunking is perform
import os

from unstructured_client import UnstructuredClient
from unstructured_client.models import shared
from unstructured_client.models import operations, shared
from unstructured_client.models.errors import SDKError

client = UnstructuredClient(
Expand All @@ -708,22 +716,24 @@ By default, the `chunking_strategy` is set to `None`, and no chunking is perform

filename = "sample-docs/layout-parser-paper-fast.pdf"
file = open(filename, "rb")
req = shared.PartitionParameters(
# Note that this currently only supports a single file
files=shared.Files(
content=file.read(),
file_name=filename,
),
chunking_strategy="by_title",
max_characters=1024,
strategy=shared.Strategy.HI_RES,
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
req = operations.PartitionRequest(
partition_parameters=shared.PartitionParameters(
# Note that this currently only supports a single file.
files=shared.Files(
content=file.read(),
file_name=filename,
),
chunking_strategy="by_title",
max_characters=1024,
strategy=shared.Strategy.HI_RES,
split_pdf_page=True,
split_pdf_allow_failed=True,
split_pdf_concurrency_level=15
)
)

try:
res = client.general.partition(req)
res = client.general.partition(request=req)
print(res.elements[0])
except SDKError as e:
print(e)
Expand Down
Loading