apunkt/PageIndex
1
0
Fork 0
mirror of https://github.com/VectifyAI/PageIndex.git synced 2026-06-24 20:28:12 +02:00
Code Issues Projects Releases Packages Wiki Activity

fix(demo): register all example documents

Browse source
This commit is contained in:
BukeLy 2026-05-26 19:10:56 +08:00
parent 30830fc19e
commit b6587350a3
1 changed files with 13 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

27
examples/pifs_demo.py
View file

@ -7,9 +7,10 @@ tools. The agent receives one read-only bash-like PIFS tool and must retrieve
evidence through commands such as ls, tree, find, grep, search-summary, evidence through commands such as ls, tree, find, grep, search-summary,
cat <path> --structure, cat <path> --page, and cat <path> --node. cat <path> --structure, cat <path> --page, and cat <path> --node.
The demo uses PDFs under examples/documents. When a matching The demo registers supported files under examples/documents. When a matching
examples/documents/results/*_structure.json file exists, it is loaded into the examples/documents/results/*_structure.json file exists, it is loaded into the
PIFS workspace's PageIndexClient cache so register() does not rebuild the tree. PIFS workspace's PageIndexClient cache. Files without a cache exercise the
normal PageIndexClient.index() path during register().
Requirements: Requirements:
pip install openai-agents pip install openai-agents
@ -168,22 +169,20 @@ def require_runtime_environment(*, metadata_provider: str, embedding_provider: s
) )
def discover_cached_documents(documents_dir: Path) -> list[Path]: SUPPORTED_DOCUMENT_SUFFIXES = {".pdf", ".md", ".markdown", ".txt", ".text"}
results_dir = documents_dir / "results"
paths: list[Path] = []
for structure_path in sorted(results_dir.glob("*_structure.json")): def discover_documents(documents_dir: Path) -> list[Path]:
stem = structure_path.name.removesuffix("_structure.json") return sorted(
for suffix in (".pdf", ".md", ".markdown"): path
candidate = documents_dir / f"{stem}{suffix}" for path in documents_dir.iterdir()
if candidate.exists(): if path.is_file() and path.suffix.lower() in SUPPORTED_DOCUMENT_SUFFIXES
paths.append(candidate) )
break
return paths
def resolve_requested_documents(documents_dir: Path, requested: list[str]) -> list[Path]: def resolve_requested_documents(documents_dir: Path, requested: list[str]) -> list[Path]:
if not requested: if not requested:
return discover_cached_documents(documents_dir) return discover_documents(documents_dir)
paths: list[Path] = [] paths: list[Path] = []
for item in requested: for item in requested:
path = Path(item).expanduser() path = Path(item).expanduser()