Move doc details line (#856)

Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>
Co-authored-by: James Braza <[email protected]>

Author: 3 people

paperqa/agents/search.py

@@ -441,34 +441,35 @@ async def query(
 def fetch_kwargs_from_manifest(
     file_location: str, manifest: dict[str, Any], manifest_fallback_location: str
 ) -> dict[str, Any]:
-    manifest_entry: DocDetails | None = manifest.get(file_location) or manifest.get(
+    manifest_entry: dict[str, Any] | None = manifest.get(file_location) or manifest.get(
         manifest_fallback_location
     )
     if manifest_entry:
-        return manifest_entry.model_dump()
+        return DocDetails(**manifest_entry).model_dump()
     return {}
 
 
 async def maybe_get_manifest(
     filename: anyio.Path | None = None,
-) -> dict[str, DocDetails]:
+) -> dict[str, dict[str, Any]]:
     if not filename:
         return {}
     if filename.suffix == ".csv":
         try:
             async with await anyio.open_file(filename, mode="r") as file:
                 content = await file.read()
-            records = [DocDetails(**r) for r in csv.DictReader(content.splitlines())]
             file_loc_to_records = {
-                str(r.file_location): r for r in records if r.file_location
+                str(r.get("file_location")): r
+                for r in csv.DictReader(content.splitlines())
+                if r.get("file_location")
             }
             if not file_loc_to_records:
                 raise ValueError(  # noqa: TRY301
                     "No mapping of file location to details extracted from manifest"
                     f" file {filename}."
                 )
             logger.debug(
-                f"Found manifest file at {filename}, read {len(records)} records"
+                f"Found manifest file at {filename}, read {len(file_loc_to_records)} records"
                 f" from it, which maps to {len(file_loc_to_records)} locations."
             )
         except FileNotFoundError:

paperqa/agents/task.py

@@ -96,7 +96,7 @@ def __init__(
         self._rewards = rewards
 
     async def validate_sources(
-        self, manifest_or_index: dict[str, DocDetails] | SearchIndex | None = None
+        self, manifest_or_index: dict[str, dict[str, Any]] | SearchIndex | None = None
     ) -> None:
         """Validate the sources can be found in the input manifest or index."""
         if not self.sources: