fix API-297: List parameters incorrectly passed to API requests (#3154)

In two places parameters passed to the python client when using either
Ingest workflow and `partition_via_api` function directly we parse the
parameters with list values to strings e.g.
```python
extract_image_block_types=["image"] -> extract_image_block_types='["image"]'
```
as of now these parameters are parsed incorrectly when given as strings
and correctly when given as lists.

This PR removes parsing from `PartitionConfig` and `partition_via_api`.

---------

Co-authored-by: Filip Knefel <filip@unstructured.io>

CHANGELOG.md

@@ -5,6 +5,7 @@
 ### Features
 
 ### Fixes
+* **Fix passing parameters to python-client** - Remove parsing list arguments to strings in passing arguments to python-client in Ingest workflow and `partition_via_api`
 
 **table metric bug fix** get_element_level_alignment()now will find all the matched indices in predicted table data instead of only returning the first match in the case of multiple matches for the same gt string.
 

test_unstructured/partition/test_api.py

@@ -249,10 +249,12 @@ def test_partition_via_api_pass_list_type_parameters(monkeypatch):
         ANY,
         data=ANY,
         files=[
-            ["extract_image_block_types", [None, '["image", "table"]']],
+            ["extract_image_block_types[]", [None, "image"]],
+            ["extract_image_block_types[]", [None, "table"]],
             ["files", ANY],
-            ["languages", [None, '["eng"]']],
+            ["languages[]", [None, "eng"]],
-            ["skip_infer_table_types", [None, '["pdf", "docx"]']],
+            ["skip_infer_table_types[]", [None, "pdf"]],
+            ["skip_infer_table_types[]", [None, "docx"]],
             ["strategy", [None, "hi_res"]],
         ],
         headers=ANY,

unstructured/ingest/interfaces.py

@@ -574,14 +574,11 @@ class BaseSingleIngestDoc(BaseIngestDoc, IngestDocJsonMixin, ABC):
 
             logger.debug(f"Using remote partition ({endpoint})")
 
-            passthrough_partition_kwargs = {
-                k: str(v) for k, v in partition_kwargs.items() if v is not None
-            }
             elements = partition_via_api(
                 filename=str(self.filename),
                 api_key=partition_config.api_key,
                 api_url=endpoint,
-                **passthrough_partition_kwargs,
+                **partition_kwargs,
             )
             # TODO: add m_data_source_metadata to unstructured-api pipeline_api and then
             # pass the stringified json here

unstructured/partition/api.py

@@ -1,7 +1,6 @@
 from __future__ import annotations
 
 import contextlib
-import json
 from typing import IO, Optional
 
 import requests
@@ -84,13 +83,6 @@ def partition_via_api(
             )
         files = shared.Files(content=file, file_name=metadata_filename)
 
-    # NOTE(christine): Converts all list type parameters to JSON formatted strings
-    # (e.g. ["image", "table"] -> '["image", "table"]')
-    # This can be removed if "speakeasy" supports passing list type parameters to FastAPI.
-    for k, v in request_kwargs.items():
-        if isinstance(v, list):
-            request_kwargs[k] = json.dumps(v)
-
     req = shared.PartitionParameters(files=files, **request_kwargs)
     response = sdk.general.partition(req)