mirror of
https://github.com/VectifyAI/PageIndex.git
synced 2026-05-19 18:35:16 +02:00
feat(collection): scoped query mode and experimental multi-doc warning
- get_agent_tools branches on doc_ids:
- scoped (doc_ids=[...]): drops list_documents and hard-enforces a
whitelist on the remaining tools; system prompt switches to
SCOPED_SYSTEM_PROMPT (no list_documents instruction); doc list +
summaries are prepended to the user message via wrap_with_doc_context.
- open (doc_ids=None): unchanged 4-tool agent loop.
- list_documents now exposes doc_description (sqlite + cloud).
- Collection.query emits UserWarning when doc_ids is None and the
collection holds >1 documents; PAGEINDEX_EXPERIMENTAL_MULTIDOC=1
silences it. Single-doc collections skip the warning; empty
collections raise ValueError.
- Agents SDK tracing upload disabled by default (avoids SSL timeouts);
PAGEINDEX_AGENTS_TRACING=1 re-enables it.
- README: new SDK Usage section covering local/cloud quick start,
streaming, multi-doc as experimental, and runnable examples.
This commit is contained in:
parent
cbea31d1a2
commit
d7b36aaf3f
8 changed files with 348 additions and 25 deletions
|
|
@ -216,7 +216,12 @@ class CloudBackend:
|
|||
params["folder_id"] = folder_id
|
||||
data = self._request("GET", "/docs/", params=params)
|
||||
return [
|
||||
{"doc_id": d.get("id", ""), "doc_name": d.get("name", ""), "doc_type": "pdf"}
|
||||
{
|
||||
"doc_id": d.get("id", ""),
|
||||
"doc_name": d.get("name", ""),
|
||||
"doc_description": d.get("description", ""),
|
||||
"doc_type": "pdf",
|
||||
}
|
||||
for d in data.get("documents", [])
|
||||
]
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue