| 1 | import asyncio |
| 2 | |
| 3 | from helpers.tool import Tool, Response |
| 4 | from plugins._document_query.helpers.document_query import DocumentQueryHelper |
| 5 | |
| 6 | |
| 7 | class DocumentQueryTool(Tool): |
| 8 | |
| 9 | async def execute(self, **kwargs): |
| 10 | document_uri = kwargs.get("document") |
| 11 | document_uris = [] |
| 12 | |
| 13 | if isinstance(document_uri, list): |
| 14 | document_uris = document_uri |
| 15 | elif isinstance(document_uri, str): |
| 16 | document_uris = [document_uri] |
| 17 | |
| 18 | if not document_uris: |
| 19 | return Response(message="Error: no document provided", break_loop=False) |
| 20 | |
| 21 | queries = ( |
| 22 | kwargs["queries"] |
| 23 | if "queries" in kwargs |
| 24 | else [kwargs["query"]] |
| 25 | if ("query" in kwargs and kwargs["query"]) |
| 26 | else [] |
| 27 | ) |
| 28 | try: |
| 29 | progress = [] |
| 30 | |
| 31 | def progress_callback(msg): |
| 32 | progress.append(msg) |
| 33 | self.log.update(progress="\n".join(progress)) |
| 34 | |
| 35 | helper = DocumentQueryHelper(self.agent, progress_callback) |
| 36 | if not queries: |
| 37 | gather_timeout = helper.config.get("gather_timeout", 120) |
| 38 | try: |
| 39 | contents = await asyncio.wait_for( |
| 40 | asyncio.gather( |
| 41 | *[helper.document_get_content(uri) for uri in document_uris] |
| 42 | ), |
| 43 | timeout=gather_timeout, |
| 44 | ) |
| 45 | except asyncio.TimeoutError: |
| 46 | return Response( |
| 47 | message=f"Error: document processing timed out after {gather_timeout}s", |
| 48 | break_loop=False, |
| 49 | ) |
| 50 | content = "\n\n---\n\n".join(contents) |
| 51 | else: |
| 52 | _, content = await helper.document_qa(document_uris, queries) |
| 53 | return Response(message=content, break_loop=False) |
| 54 | except Exception as e: # pylint: disable=broad-exception-caught |
| 55 | return Response(message=f"Error processing document: {e}", break_loop=False) |