LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Python ai-agentsdata-engineeringdocument-aigenerative-aiidpjson-extractionllmmcp-serverocrpdf-extractionprompt-engineeringstructured-output
fix: Classifier fix to get extracted text, bumped version to 0.0.24 (#443)
Chandrasekharan Mfa3f2b4f2887
diff --git a/tools/classifier/src/config/properties.json b/tools/classifier/src/config/properties.jsonindex 992d3ca61..3dc3a6550 100644--- a/tools/classifier/src/config/properties.json+++ b/tools/classifier/src/config/properties.json@@ -2,7 +2,7 @@"schemaVersion": "0.0.1","displayName": "File Classifier","functionName": "classify",- "toolVersion": "0.0.23",+ "toolVersion": "0.0.24","description": "Classifies a file into a bin based on its contents","input": {"description": "File to be classified"diff --git a/tools/classifier/src/helper.py b/tools/classifier/src/helper.pyindex f3906fcc2..dd7e4ac65 100644--- a/tools/classifier/src/helper.py+++ b/tools/classifier/src/helper.py@@ -5,7 +5,7 @@ from unstract.sdk.constants import ToolEnvfrom unstract.sdk.llm import LLMfrom unstract.sdk.tool.base import BaseToolfrom unstract.sdk.utils import ToolUtils-from unstract.sdk.x2txt import X2Text+from unstract.sdk.x2txt import TextExtractionResult, X2Textclass ClassifierHelper:@@ -48,7 +48,10 @@ class ClassifierHelper:self.tool.stream_log("Adapter created")try:- extracted_text: str = x2text.process(input_file_path=file)+ extraction_result: TextExtractionResult = x2text.process(+ input_file_path=file+ )+ extracted_text: str = extraction_result.extracted_textreturn extracted_textexcept Exception as e:self.tool.stream_log(f"Adapter error: {e}")