langchain/libs/community/langchain_community/document_loaders/parsers/doc_intelligence.py
Fabrizio Ruocco f12cb0bea4
community[patch]: Microsoft Azure Document Intelligence updates (#16932)
- **Description:** Update Azure Document Intelligence implementation by
Microsoft team and RAG cookbook with Azure AI Search

---------

Co-authored-by: Lu Zhang (AI) <luzhan@microsoft.com>
Co-authored-by: Yateng Hong <yatengh@microsoft.com>
Co-authored-by: teethache <hongyateng2006@126.com>
Co-authored-by: Lu Zhang <44625949+luzhang06@users.noreply.github.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-03-26 23:36:59 -07:00

112 lines
4.0 KiB
Python

import logging
from typing import Any, Iterator, List, Optional
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseBlobParser
from langchain_community.document_loaders.blob_loaders import Blob
logger = logging.getLogger(__name__)
class AzureAIDocumentIntelligenceParser(BaseBlobParser):
"""Loads a PDF with Azure Document Intelligence
(formerly Forms Recognizer)."""
def __init__(
self,
api_endpoint: str,
api_key: str,
api_version: Optional[str] = None,
api_model: str = "prebuilt-layout",
mode: str = "markdown",
analysis_features: Optional[List[str]] = None,
):
from azure.ai.documentintelligence import DocumentIntelligenceClient
from azure.ai.documentintelligence.models import DocumentAnalysisFeature
from azure.core.credentials import AzureKeyCredential
kwargs = {}
if api_version is not None:
kwargs["api_version"] = api_version
if analysis_features is not None:
_SUPPORTED_FEATURES = [
DocumentAnalysisFeature.OCR_HIGH_RESOLUTION,
]
analysis_features = [
DocumentAnalysisFeature(feature) for feature in analysis_features
]
if any(
[feature not in _SUPPORTED_FEATURES for feature in analysis_features]
):
logger.warning(
f"The current supported features are: "
f"{[f.value for f in _SUPPORTED_FEATURES]}. "
"Using other features may result in unexpected behavior."
)
self.client = DocumentIntelligenceClient(
endpoint=api_endpoint,
credential=AzureKeyCredential(api_key),
headers={"x-ms-useragent": "langchain-parser/1.0.0"},
features=analysis_features,
**kwargs,
)
self.api_model = api_model
self.mode = mode
assert self.mode in ["single", "page", "markdown"]
def _generate_docs_page(self, result: Any) -> Iterator[Document]:
for p in result.pages:
content = " ".join([line.content for line in p.lines])
d = Document(
page_content=content,
metadata={
"page": p.page_number,
},
)
yield d
def _generate_docs_single(self, result: Any) -> Iterator[Document]:
yield Document(page_content=result.content, metadata={})
def lazy_parse(self, blob: Blob) -> Iterator[Document]:
"""Lazily parse the blob."""
with blob.as_bytes_io() as file_obj:
poller = self.client.begin_analyze_document(
self.api_model,
file_obj,
content_type="application/octet-stream",
output_content_format="markdown" if self.mode == "markdown" else "text",
)
result = poller.result()
if self.mode in ["single", "markdown"]:
yield from self._generate_docs_single(result)
elif self.mode in ["page"]:
yield from self._generate_docs_page(result)
else:
raise ValueError(f"Invalid mode: {self.mode}")
def parse_url(self, url: str) -> Iterator[Document]:
from azure.ai.documentintelligence.models import AnalyzeDocumentRequest
poller = self.client.begin_analyze_document(
self.api_model,
AnalyzeDocumentRequest(url_source=url),
# content_type="application/octet-stream",
output_content_format="markdown" if self.mode == "markdown" else "text",
)
result = poller.result()
if self.mode in ["single", "markdown"]:
yield from self._generate_docs_single(result)
elif self.mode in ["page"]:
yield from self._generate_docs_page(result)
else:
raise ValueError(f"Invalid mode: {self.mode}")