feat: local mode for the PageIndex SDK (v0.2.9)

.github/workflows/publish.yml

@@ -0,0 +1,81 @@
+name: Publish to PyPI
+
+# Release flow (the git tag IS the version — nothing to bump in the repo):
+#   1. git tag -a v0.2.9 -m "Release 0.2.9"
+#   2. git push origin v0.2.9
+#   3. This workflow derives the version from the tag, injects it into
+#      pyproject.toml, builds, publishes to PyPI via OIDC trusted publishing
+#      (no stored secret), and creates a GitHub Release with generated notes.
+#
+# The tag must be a PEP 440 version with a leading `v`:
+#   v0.2.9   v0.2.9rc1   v0.2.9.dev1
+# PyPI rejects duplicate version uploads, so each tag must be a new version.
+# Plain `pip install pageindex` skips dev/rc pre-releases — install one
+# explicitly with `pip install pageindex==0.2.9.dev1`.
+#
+# One-time setup this workflow depends on:
+#   - PyPI: add a Trusted Publisher on the `pageindex` project pointing at
+#     repo VectifyAI/PageIndex, workflow `publish.yml`, environment `pypi`.
+#   - GitHub: create an Environment named `pypi` (Settings -> Environments).
+
+on:
+  push:
+    tags:
+      - "v*"
+
+jobs:
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        python-version: ["3.10", "3.13"]
+    name: test py${{ matrix.python-version }}
+    timeout-minutes: 15
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+      - uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
+        with:
+          python-version: ${{ matrix.python-version }}
+          cache: pip
+      - run: pip install -r requirements.txt pytest
+      - run: python -m pytest -q
+
+  publish:
+    needs: test
+    runs-on: ubuntu-latest
+    environment: pypi
+    permissions:
+      id-token: write   # OIDC trusted publishing to PyPI
+      contents: write   # create the GitHub Release
+    steps:
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+
+      - uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
+        with:
+          python-version: "3.12"
+
+      - name: Set version from tag and build
+        run: |
+          set -euo pipefail
+          python -m pip install --upgrade build packaging
+          VERSION="${GITHUB_REF_NAME#v}"
+          echo "Publishing version: $VERSION"
+          # Fail early on a malformed tag instead of publishing a junk version.
+          python -c "from packaging.version import Version; Version('$VERSION')"
+          # The git tag is the single source of truth; overwrite the static
+          # placeholder in [tool.poetry] so the built artifacts carry $VERSION.
+          sed -i "s/^version = .*/version = \"$VERSION\"/" pyproject.toml
+          grep '^version = ' pyproject.toml
+          python -m build
+
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@cef221092ed1bacb1cc03d23a2d87d1d172e277b  # release/v1.14.0
+
+      - name: Create GitHub Release
+        uses: softprops/action-gh-release@718ea10b132b3b2eba29c1007bb80653f286566b  # v3.0.1
+        with:
+          tag_name: ${{ github.ref_name }}
+          name: ${{ github.ref_name }}
+          generate_release_notes: true
+          files: dist/*

.gitignore

@@ -4,3 +4,5 @@ __pycache__
 .env*
 .venv/
 logs/
+.pageindex/
+dist/

README.md

@@ -207,6 +207,33 @@ python3 run_pageindex.py --md_path /path/to/your/document.md
 >
 > Add `--optimize` to refine the tree structure for more efficient retrieval (with an LLM expansion pass).
 
+## 🐍 Python SDK: Cloud & Local
+
+The `pageindex` package on PyPI is the Python SDK for the [PageIndex API](https://docs.pageindex.ai) — and the same client now also runs fully **locally**, powered by this repo's indexing pipeline (including Flash).
+
+```bash
+pip3 install --upgrade pageindex   # local mode ships in pageindex >= 0.2.9; earlier versions are cloud-only
+```
+
+```python
+from pageindex import PageIndexClient
+
+client = PageIndexClient(api_key="YOUR_PAGEINDEX_API_KEY")  # cloud: managed OCR, tree building, retrieval
+client = PageIndexClient()                                  # local: same methods on your machine, using your LLM key (e.g. OPENAI_API_KEY)
+
+doc_id = client.submit_document("doc.pdf")["doc_id"]        # local mode blocks until indexing finishes
+doc_id = client.submit_document("doc.pdf", mode="flash")["doc_id"]  # local mode with PageIndex Flash
+
+tree = client.get_tree(doc_id, node_summary=True)["result"]
+
+answer = client.chat_completions(
+    messages=[{"role": "user", "content": "Summarize the key findings"}],
+    doc_id=doc_id,
+)["choices"][0]["message"]["content"]
+```
+
+Local documents are stored as plain JSON under `./.pageindex` (configurable via `storage_path`). Local mode supports PDFs; folders, `beta_headers`, `enable_citations`, and the deprecated retrieval API (`submit_query`/`get_retrieval`) remain cloud-only — each method's docstring spells out the differences. To pin the mode at construction instead of inferring it from `api_key`, use `PageIndexCloudClient` (fails without a real key) or `PageIndexLocalClient` (has no key parameter).
+
 ## 🚀 Agentic Vectorless RAG: An Example
 
 For a simple, end-to-end **agentic vectorless RAG** example using **self-hosted PageIndex** (with OpenAI Agents SDK), see [`examples/agentic_vectorless_rag_demo.py`](examples/agentic_vectorless_rag_demo.py).

examples/agentic_vectorless_rag_demo.py

@@ -1,22 +1,22 @@
 """
 Agentic Vectorless RAG with PageIndex - Demo
 
-A simple example of building a document QA agent with self-hosted PageIndex
-and the OpenAI Agents SDK. Instead of vector similarity search and chunking,
-PageIndex builds a hierarchical tree index and uses agentic LLM reasoning for
-human-like, context-aware retrieval.
+A simple example of building a document QA agent with the PageIndex SDK in
+local mode and the OpenAI Agents SDK. Instead of vector similarity search and
+chunking, PageIndex builds a hierarchical tree index and uses agentic LLM
+reasoning for human-like, context-aware retrieval.
 
 Agent tools:
   - get_document()           — document metadata (status, page count, etc.)
   - get_document_structure() — tree structure index of a document
   - get_page_content()       — retrieve text content of specific pages
 
 Steps:
-  1 — Index a PDF and view its tree structure index
+  1 — Index a PDF locally and view its tree structure index
   2 — View document metadata
   3 — Ask a question (agent reasons over the index and auto-calls tools)
 
-Requirements: pip install openai-agents
+Requirements: pip install openai-agents; OPENAI_API_KEY in the environment.
 """
 import sys
 import json
@@ -39,19 +39,34 @@
 
 _EXAMPLES_DIR = Path(__file__).parent
 PDF_PATH = _EXAMPLES_DIR / "documents" / "attention-residuals.pdf"
-WORKSPACE = _EXAMPLES_DIR / "workspace"
+STORAGE_PATH = _EXAMPLES_DIR / ".pageindex"
 
 AGENT_SYSTEM_PROMPT = """
 You are PageIndex, a document QA assistant.
 TOOL USE:
-- Call get_document() first to confirm status and page/line count.
+- Call get_document() first to confirm status and page count.
 - Call get_document_structure() to identify relevant page ranges.
 - Call get_page_content(pages="5-7") with tight ranges; never fetch the whole document.
 - Before each tool call, output one short sentence explaining the reason.
 Answer based only on tool output. Be concise.
 """
 
 
+def _parse_pages(pages: str) -> list[int]:
+    """Parse a pages string like '5-7', '3,8', or '12' into a list of ints."""
+    result = []
+    for part in pages.split(","):
+        part = part.strip()
+        if "-" in part:
+            start, end = (int(x) for x in part.split("-", 1))
+            if start > end:
+                raise ValueError(f"Invalid range '{part}': start must be <= end")
+            result.extend(range(start, end + 1))
+        else:
+            result.append(int(part))
+    return sorted(set(result))
+
+
 def query_agent(client: PageIndexClient, doc_id: str, prompt: str, verbose: bool = False) -> str:
     """Run a document QA agent using the OpenAI Agents SDK.
 
@@ -62,21 +77,28 @@ def query_agent(client: PageIndexClient, doc_id: str, prompt: str, verbose: bool
     @function_tool
     def get_document() -> str:
         """Get document metadata: status, page count, name, and description."""
-        return client.get_document(doc_id)
+        return json.dumps(client.get_document(doc_id))
 
     @function_tool
     def get_document_structure() -> str:
         """Get the document's full tree structure (without text) to find relevant sections."""
-        return client.get_document_structure(doc_id)
+        tree = client.get_tree(doc_id, node_summary=True)["result"]
+        return json.dumps(utils.remove_fields(tree, fields=["text"]), ensure_ascii=False)
 
     @function_tool
     def get_page_content(pages: str) -> str:
         """
-        Get the text content of specific pages or line numbers.
+        Get the text content of specific pages.
         Use tight ranges: e.g. '5-7' for pages 5 to 7, '3,8' for pages 3 and 8, '12' for page 12.
-        For Markdown documents, use line numbers from the structure's line_num field.
         """
-        return client.get_page_content(doc_id, pages)
+        try:
+            wanted = set(_parse_pages(pages))
+        except ValueError:
+            return json.dumps({"error": f"Invalid pages format: {pages!r}. Use '5-7', '3,8', or '12'."})
+        all_pages = client.get_ocr(doc_id, format="page")["result"]
+        return json.dumps(
+            [p for p in all_pages if p["page_index"] in wanted], ensure_ascii=False
+        )
 
     agent = Agent(
         name="PageIndex",
@@ -152,24 +174,25 @@ async def _run():
                         f.write(chunk)
         print("Download complete.\n")
 
-    # Setup
-    client = PageIndexClient(workspace=WORKSPACE)
+    # Setup: local mode — no PageIndex API key needed, your LLM key does the work
+    client = PageIndexClient(storage_path=str(STORAGE_PATH))
 
     # Step 1: Index PDF and view tree structure
     print("=" * 60)
     print("Step 1: Index PDF and view tree structure")
     print("=" * 60)
     doc_id = next(
-        (did for did, doc in client.documents.items() if doc.get('doc_name') == PDF_PATH.name),
+        (doc["id"] for doc in client.list_documents(limit=100)["documents"]
+         if doc["name"] == PDF_PATH.name),
         None,
     )
     if doc_id:
         print(f"\nLoaded cached doc_id: {doc_id}")
     else:
-        doc_id = client.index(PDF_PATH)
+        doc_id = client.submit_document(str(PDF_PATH))["doc_id"]
         print(f"\nIndexed. doc_id: {doc_id}")
     print("\nTree Structure (top-level sections):")
-    structure = json.loads(client.get_document_structure(doc_id))
+    structure = client.get_tree(doc_id, node_summary=True)["result"]
     utils.print_tree(structure)
 
     # Step 2: View document metadata