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

.github/workflows/publish.yml

@@ -0,0 +1,85 @@
+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
+    permissions:
+      contents: read
+    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.
+          export VERSION
+          python -c "import os; from packaging.version import Version; Version(os.environ['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 }}
+          prerelease: ${{ contains(github.ref_name, 'rc') || contains(github.ref_name, 'dev') || contains(github.ref_name, 'alpha') || contains(github.ref_name, 'beta') }}
+          generate_release_notes: true
+          files: dist/*

.github/workflows/tests.yml

@@ -20,22 +20,16 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.10", "3.13"]
-        # "without" proves the package works with no agent framework
-        # installed; "with" covers the framework integration paths.
         agent-frameworks: [without, with]
     name: py${{ matrix.python-version }} (${{ matrix.agent-frameworks }} frameworks)
     timeout-minutes: 15
     steps:
-      - uses: actions/checkout@v4
-      - uses: actions/setup-python@v5
+      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0  # v7.0.0
+      - uses: actions/setup-python@ece7cb06caefa5fff74198d8649806c4678c61a1  # v6.3.0
         with:
           python-version: ${{ matrix.python-version }}
           cache: pip
-      # requirements.txt works on every branch; the packaging metadata
-      # (pyproject) does not exist on all of them.
       - run: pip install -r requirements.txt pytest
       - if: matrix.agent-frameworks == 'with'
         run: pip install openai-agents claude-agent-sdk
-      # python -m pytest puts the repo root on sys.path, so the in-repo
-      # `pageindex` package is imported without an install step.
       - run: python -m pytest -q

.gitignore

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

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
@@ -39,12 +39,12 @@
 
 _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.
@@ -62,27 +62,26 @@ 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)
+        return json.dumps(client.get_document_structure(doc_id), 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)
+        return json.dumps(client.get_page_content(doc_id, pages), ensure_ascii=False)
 
     agent = Agent(
         name="PageIndex",
         instructions=AGENT_SYSTEM_PROMPT,
         tools=[get_document, get_document_structure, get_page_content],
-        model=client.retrieve_model,
+        model=getattr(client, "retrieve_model", None),
         # model_settings=ModelSettings(reasoning={"effort": "low", "summary": "auto"}),  # Uncomment to enable reasoning
     )
 
@@ -152,24 +151,25 @@ 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