fix: accept JSON schemas in structured output parser

Author: Iams4kura

scrapegraphai/utils/output_parser.py

@@ -5,8 +5,8 @@
 from typing import Any, Callable, Dict, List, Type, Union
 
 from langchain_core.exceptions import OutputParserException
-from langchain_core.outputs import Generation
 from langchain_core.output_parsers import JsonOutputParser
+from langchain_core.outputs import Generation
 from pydantic import BaseModel as BaseModelV2
 from pydantic.v1 import BaseModel as BaseModelV1
 
@@ -58,6 +58,9 @@ def get_structured_output_parser(
     Returns:
         Callable: The output parser function.
     """
+    if isinstance(schema, dict):
+        return _dict_output_parser
+
     if issubclass(schema, BaseModelV1):
         return _base_model_v1_output_parser
 

tests/utils/output_parser_test.py

@@ -5,6 +5,7 @@
 from scrapegraphai.utils.output_parser import (
     TolerantJsonOutputParser,
     _strip_doubled_braces,
+    get_structured_output_parser,
 )
 
 
@@ -22,6 +23,19 @@ def test_strip_doubled_braces_ignores_unbalanced():
     assert _strip_doubled_braces(text) == text
 
 
+def test_structured_output_parser_accepts_json_schema():
+    schema = {
+        "title": "Person",
+        "type": "object",
+        "properties": {"name": {"type": "string"}},
+    }
+    output = {"name": "Ada"}
+
+    parser = get_structured_output_parser(schema)
+
+    assert parser(output) == output
+
+
 def test_tolerant_parser_parses_clean_json_unchanged():
     parser = TolerantJsonOutputParser()
     assert parser.parse('{"content": "hi"}') == {"content": "hi"}