yujunjun/haystack
1
0
Fork 0
mirror of https://github.com/deepset-ai/haystack.git synced 2025-12-04 19:06:44 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update LLMMetaDataExtractor to properly retrigger document ID creation after adding new metadata to docs

Browse Source
This commit is contained in:
Sebastian Husch Lee 2025-06-25 14:17:00 +02:00
parent 1d1c13a8bc
commit 380f1f396c
2 changed files with 28 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

33
haystack/components/extractors/llm_metadata_extractor.py
View File

@ -5,6 +5,7 @@
import copy
import json
from concurrent.futures import ThreadPoolExecutor
from dataclasses import replace
from typing import Any, Dict, List, Optional, Union
from jinja2 import meta
@ -319,23 +320,31 @@ class LLMMetadataExtractor:
failed_documents = []
for document, result in zip(documents, results):
if "error" in result:
document.meta["metadata_extraction_error"] = result["error"]
document.meta["metadata_extraction_response"] = None
failed_documents.append(document)
new_meta = {
**document.meta,
"metadata_extraction_error": result["error"],
"metadata_extraction_response": None,
}
# We set id to an empty string to retrigger new id creation
failed_documents.append(replace(document, meta=new_meta, id=""))
continue
parsed_metadata = self._extract_metadata(result["replies"][0].text)
if "error" in parsed_metadata:
document.meta["metadata_extraction_error"] = parsed_metadata["error"]
document.meta["metadata_extraction_response"] = result["replies"][0]
failed_documents.append(document)
new_meta = {
**document.meta,
"metadata_extraction_error": parsed_metadata["error"],
"metadata_extraction_response": result["replies"][0],
}
# We set id to an empty string to retrigger new id creation
failed_documents.append(replace(document, meta=new_meta, id=""))
continue
for key in parsed_metadata:
document.meta[key] = parsed_metadata[key]
# Remove metadata_extraction_error and metadata_extraction_response if present from previous runs
document.meta.pop("metadata_extraction_error", None)
document.meta.pop("metadata_extraction_response", None)
successful_documents.append(document)
new_meta = {**document.meta, **parsed_metadata}
# Remove metadata_extraction_error and metadata_extraction_response if present from previous runs
new_meta.pop("metadata_extraction_error", None)
new_meta.pop("metadata_extraction_response", None)
# We set id to an empty string to retrigger new id creation
successful_documents.append(replace(document, meta=new_meta, id=""))
return {"documents": successful_documents, "failed_documents": failed_documents}

9
test/components/extractors/test_llm_metadata_extractor.py
View File

@ -244,12 +244,12 @@ class TestLLMMetadataExtractor:
assert len(result["failed_documents"]) == 2
failed_doc_none = result["failed_documents"][0]
assert failed_doc_none.id == doc_with_none_content.id
assert failed_doc_none.id != doc_with_none_content.id
assert "metadata_extraction_error" in failed_doc_none.meta
assert failed_doc_none.meta["metadata_extraction_error"] == "Document has no content, skipping LLM call."
failed_doc_empty = result["failed_documents"][1]
assert failed_doc_empty.id == doc_with_empty_content.id
assert failed_doc_empty.id != doc_with_empty_content.id
assert "metadata_extraction_error" in failed_doc_empty.meta
assert failed_doc_empty.meta["metadata_extraction_error"] == "Document has no content, skipping LLM call."
@ -322,3 +322,8 @@ output:
assert len(doc_store_docs) == 2
assert "entities" in doc_store_docs[0].meta
assert "entities" in doc_store_docs[1].meta
# Check that IDs of documents in doc store are different from the original documents
doc_store_doc_ids = {doc.id for doc in doc_store_docs}
original_doc_ids = {doc.id for doc in docs}
assert doc_store_doc_ids != original_doc_ids