LLM-Driven Extraction of Unstructured Data — Built for API Deployments & ETL Pipeline Workflows
Python ai-agentsdata-engineeringdocument-aigenerative-aiidpjson-extractionllmmcp-serverocrpdf-extractionprompt-engineeringstructured-output
PR comments addressed sdk version update in requirements ocr_adapter.process() used to write output readme updated tools json typo fix
vishnuszipstack8484bf602c78
diff --git a/tools/ocr/README.md b/tools/ocr/README.mdindex 4ba66babb..5b0d49411 100644--- a/tools/ocr/README.md+++ b/tools/ocr/README.md@@ -72,15 +72,14 @@ python main.py --command VARIABLES#### Run RUN command-The format of the jsons required for settings and params can be found by running the SPEC command and the PROPERTIES-command respectively. Alternatively if you have access to the code base, it is located in the `config` folder-as `spec.json` and `properties.json`.+The schema of the JSON required for settings can be found by running the [SPEC](#run-spec-command) command. Alternatively if you have access to the code base, it is located in the `config` folder as `spec.json`.```commandlinepython main.py \--command RUN \--settings '{+ "ocrAdapterId": "<ocr_adapter_id of adapter>"}' \--workflow-id '00000000-0000-0000-0000-000000000000' \--log-level DEBUG@@ -90,7 +89,7 @@ python main.py \Build the tool docker image from the folder containing the `Dockerfile` with```commandline-docker build -t unstract/tool-example:0.0.1 .+docker build -t unstract/tool-ocr:0.0.1 .```Make sure the directory pointed by `TOOL_DATA_DIR` has the required information for the tool to run and@@ -102,9 +101,10 @@ docker run -it \--network unstract-network \--env-file .env \-v "$(pwd)"/data_dir:/app/data_dir \- unstract/tool-example:0.0.1 \+ unstract/tool-ocr:0.0.1 \--command RUN \--settings '{+ "ocrAdapterId": "<ocr_adapter_id of adapter>"}' \--workflow-id '00000000-0000-0000-0000-000000000000' \--log-level DEBUGdiff --git a/tools/ocr/requirements.txt b/tools/ocr/requirements.txtindex cfbb98360..1d381f5ee 100644--- a/tools/ocr/requirements.txt+++ b/tools/ocr/requirements.txt@@ -6,4 +6,4 @@ requests==2.31.0pillow~=10.2.0# Required for all unstract tools-unstract-sdk==0.12.0+unstract-sdk~=0.12.1diff --git a/tools/ocr/src/config/properties.json b/tools/ocr/src/config/properties.jsonindex a34a5bc81..4c8c7554e 100644--- a/tools/ocr/src/config/properties.json+++ b/tools/ocr/src/config/properties.json@@ -8,7 +8,7 @@"description": "The file on which OCR operation is to be performed"},"output": {- "description": "Places the file into a folder (bin) that its OCR opertation performed into."+ "description": "Places the file into a folder (bin) that its OCR operation performed into."},"result": {"type": "JSON",diff --git a/tools/ocr/src/main.py b/tools/ocr/src/main.pyindex dd2127917..2f4fef7a2 100644--- a/tools/ocr/src/main.py+++ b/tools/ocr/src/main.py@@ -85,11 +85,7 @@ class UnstractOCR(BaseTool):self.stream_log("Writing tool output")source_name = self.get_exec_metadata.get(MetadataKey.SOURCE_NAME)output_path = Path(output_dir) / f"{Path(source_name).stem}.txt"- try:- with open(output_path, "w", encoding="utf-8") as f:- f.write(result_text)- except Exception as e:- self.stream_error_and_exit(f"Error creating output file: {e}")+ ocr_adapter.process(input_file_path=input_file, output_file_path=output_path)# Log outputif len(result_text) > 1000:diff --git a/unstract/tool-registry/src/unstract/tool_registry/public_tools.json b/unstract/tool-registry/src/unstract/tool_registry/public_tools.jsonindex 31b00467b..045c57343 100644--- a/unstract/tool-registry/src/unstract/tool_registry/public_tools.json+++ b/unstract/tool-registry/src/unstract/tool_registry/public_tools.json@@ -659,7 +659,7 @@"description": "The file on which OCR operation is to be performed"},"output": {- "description": "Places the file into a folder (bin) that its OCR opertation performed into."+ "description": "Places the file into a folder (bin) that its OCR operation performed into."},"result": {"type": "JSON",