pageserve 0.1.0__tar.gz

pageserve-0.1.0/.gitignore

@@ -0,0 +1,221 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#   Usually these files are written by a python script from a template
+#   before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+*.lcov
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+docs_internal
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+# Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+# uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+# poetry.lock
+# poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+# pdm.lock
+# pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+# pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi/*
+!.pixi/config.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule*
+celerybeat.pid
+
+# Redis
+*.rdb
+*.aof
+*.pid
+
+# RabbitMQ
+mnesia/
+rabbitmq/
+rabbitmq-data/
+
+# ActiveMQ
+activemq-data/
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#   JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#   be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#   and can be added to the global gitignore or merged into this file.  For a more nuclear
+#   option (not recommended) you can uncomment the following to ignore the entire idea folder.
+# .idea/
+
+# Abstra
+#   Abstra is an AI-powered process automation framework.
+#   Ignore directories containing user credentials, local state, and settings.
+#   Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#   Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#   that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#   and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#   you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+# Temporary file for partial code execution
+tempCodeRunnerFile.py
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+# Streamlit
+.streamlit/secrets.toml

pageserve-0.1.0/PKG-INFO

@@ -0,0 +1,208 @@
+Metadata-Version: 2.4
+Name: pageserve
+Version: 0.1.0
+Summary: Python SDK and MCP server for self-hosted PageIndex RAG service
+Project-URL: Homepage, https://github.com/pageserve/pageserve
+Project-URL: Repository, https://github.com/pageserve/pageserve
+Project-URL: Issues, https://github.com/pageserve/pageserve/issues
+Project-URL: Documentation, https://github.com/pageserve/pageserve#readme
+Author-email: pageserve <pageserve03@gmail.com>
+License: Apache-2.0
+Keywords: document-ai,llm,mcp,pageindex,rag,self-host,vector-free
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: >=3.10
+Requires-Dist: httpx>=0.27.0
+Requires-Dist: pydantic>=2.0
+Provides-Extra: all
+Requires-Dist: click>=8.0; extra == 'all'
+Requires-Dist: mcp>=1.9.4; extra == 'all'
+Provides-Extra: cli
+Requires-Dist: click>=8.0; extra == 'cli'
+Provides-Extra: dev
+Requires-Dist: hatch; extra == 'dev'
+Requires-Dist: mypy; extra == 'dev'
+Requires-Dist: pytest-asyncio>=0.23; extra == 'dev'
+Requires-Dist: pytest-cov; extra == 'dev'
+Requires-Dist: pytest>=8.0; extra == 'dev'
+Requires-Dist: respx>=0.21; extra == 'dev'
+Requires-Dist: ruff; extra == 'dev'
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.9.4; extra == 'mcp'
+Description-Content-Type: text/markdown
+
+# pageserve
+
+Python SDK and MCP server for [PageIndex](https://github.com/VectifyAI/PageIndex) self-hosted RAG service.
+
+PageIndex is a reasoning-based RAG engine that navigates document structure rather than doing vector similarity search — it reads the table of contents, picks the right sections, and synthesizes answers with page-level citations.
+
+## Installation
+
+```bash
+pip install pageserve              # SDK only (sync + async)
+pip install "pageserve[mcp]"       # + MCP server for agent frameworks
+pip install "pageserve[cli]"       # + CLI commands
+pip install "pageserve[all]"       # everything
+```
+
+## Quick start
+
+```python
+from pageserve import PageServeClient
+
+client = PageServeClient(
+    base_url   = "https://pageindex.company.com",
+    public_key = "<your-public-key>",
+    secret_key = "<your-secret-key>",
+)
+
+# List indexed documents
+docs = client.list_documents()
+
+# Ask a question
+result = client.query(docs[0].doc_id, "What are the probation terms?")
+print(result.answer)
+print(result.citation)   # "Employment Contract p.5, 6"
+print(result.page_refs)  # [5, 6]
+
+# Upload and wait for indexing to complete
+upload = client.upload("./contract.pdf", wait=True)
+
+# Read specific pages (no LLM, instant)
+pages = client.get_pages(docs[0].doc_id, "22-24")
+```
+
+## Async usage
+
+```python
+import asyncio
+from pageserve import AsyncPageServeClient
+
+async def main():
+    async with AsyncPageServeClient(
+        base_url   = "https://pageindex.company.com",
+        public_key = "<your-public-key>",
+        secret_key = "<your-secret-key>",
+    ) as client:
+        docs = await client.list_documents()
+
+        # Query multiple documents concurrently
+        results = await client.query_many([
+            (docs[0].doc_id, "What are the probation terms?"),
+            (docs[1].doc_id, "What does the law say about probation?"),
+        ])
+        for r in results:
+            print(r.answer)
+
+asyncio.run(main())
+```
+
+## Streaming
+
+```python
+for event in client.query_stream(doc_id, "What are the key clauses?"):
+    if event.type == "token":
+        print(event.content, end="", flush=True)
+    elif event.type == "sources":
+        for src in event.sources:
+            print(f"\nSource: {src.citation}")
+    elif event.type == "done":
+        break
+```
+
+## MCP server (Claude Desktop / Cursor)
+
+Run the MCP server so Claude or any MCP-compatible agent can query your documents:
+
+```json
+{
+  "mcpServers": {
+    "pageindex": {
+      "command": "pageserve",
+      "args": ["mcp"],
+      "env": {
+        "PAGESERVE_URL":        "https://pageindex.company.com",
+        "PAGESERVE_PUBLIC_KEY": "<your-public-key>",
+        "PAGESERVE_SECRET_KEY": "<your-secret-key>"
+      }
+    }
+  }
+}
+```
+
+The MCP server exposes five tools:
+- `list_documents` — see what documents are available
+- `query_document` — ask a question against one document
+- `query_multiple_documents` — cross-reference multiple documents
+- `get_page_content` — read raw page text (no LLM, instant)
+- `get_document_structure` — browse the table of contents
+
+Keys live in env vars and never appear in tool arguments or the model's context window.
+
+## CLI
+
+```bash
+export PAGESERVE_URL=https://pageindex.company.com
+export PAGESERVE_PUBLIC_KEY=<your-public-key>
+export PAGESERVE_SECRET_KEY=<your-secret-key>
+
+pageserve list                                      # list documents
+pageserve query <doc_id> "question"                 # ask a question
+pageserve query <doc_id> "question" --stream        # streaming output
+pageserve upload ./report.pdf --watch               # upload + progress bar
+pageserve health                                    # service status
+pageserve keys list                                 # list API keys
+pageserve keys create "My App"                      # create a key
+pageserve mcp                                       # run MCP server (stdio)
+pageserve mcp --transport sse --port 3000           # MCP over SSE
+```
+
+## Error handling
+
+```python
+from pageserve import (
+    AuthError,
+    NotFoundError,
+    DocumentNotReadyError,
+    FileTooLargeError,
+    RateLimitError,
+    ServiceUnavailableError,
+    ServiceError,
+)
+
+try:
+    result = client.query(doc_id, "question")
+except AuthError:
+    print("Invalid or expired API key")
+except NotFoundError:
+    print("Document not found")
+except RateLimitError as e:
+    import time; time.sleep(e.retry_after)
+except ServiceError as e:
+    print(f"Server error [{e.status_code}]")
+```
+
+## Documentation
+
+- [Getting Started](docs/getting-started.md)
+- [Authentication](docs/authentication.md)
+- [Sync Client Reference](docs/sync-client.md)
+- [Async Client Reference](docs/async-client.md)
+- [Streaming (SSE)](docs/streaming.md)
+- [MCP Server](docs/mcp-server.md)
+- [CLI Reference](docs/cli.md)
+- [Data Models](docs/models.md)
+- [Error Handling](docs/error-handling.md)
+
+## Related
+
+- [PageIndex OSS](https://github.com/VectifyAI/PageIndex) — the self-hosted service this SDK wraps
+- [PageIndex Cloud](https://pageindex.ai) — hosted version

pageserve-0.1.0/README.md

@@ -0,0 +1,168 @@
+# pageserve
+
+Python SDK and MCP server for [PageIndex](https://github.com/VectifyAI/PageIndex) self-hosted RAG service.
+
+PageIndex is a reasoning-based RAG engine that navigates document structure rather than doing vector similarity search — it reads the table of contents, picks the right sections, and synthesizes answers with page-level citations.
+
+## Installation
+
+```bash
+pip install pageserve              # SDK only (sync + async)
+pip install "pageserve[mcp]"       # + MCP server for agent frameworks
+pip install "pageserve[cli]"       # + CLI commands
+pip install "pageserve[all]"       # everything
+```
+
+## Quick start
+
+```python
+from pageserve import PageServeClient
+
+client = PageServeClient(
+    base_url   = "https://pageindex.company.com",
+    public_key = "<your-public-key>",
+    secret_key = "<your-secret-key>",
+)
+
+# List indexed documents
+docs = client.list_documents()
+
+# Ask a question
+result = client.query(docs[0].doc_id, "What are the probation terms?")
+print(result.answer)
+print(result.citation)   # "Employment Contract p.5, 6"
+print(result.page_refs)  # [5, 6]
+
+# Upload and wait for indexing to complete
+upload = client.upload("./contract.pdf", wait=True)
+
+# Read specific pages (no LLM, instant)
+pages = client.get_pages(docs[0].doc_id, "22-24")
+```
+
+## Async usage
+
+```python
+import asyncio
+from pageserve import AsyncPageServeClient
+
+async def main():
+    async with AsyncPageServeClient(
+        base_url   = "https://pageindex.company.com",
+        public_key = "<your-public-key>",
+        secret_key = "<your-secret-key>",
+    ) as client:
+        docs = await client.list_documents()
+
+        # Query multiple documents concurrently
+        results = await client.query_many([
+            (docs[0].doc_id, "What are the probation terms?"),
+            (docs[1].doc_id, "What does the law say about probation?"),
+        ])
+        for r in results:
+            print(r.answer)
+
+asyncio.run(main())
+```
+
+## Streaming
+
+```python
+for event in client.query_stream(doc_id, "What are the key clauses?"):
+    if event.type == "token":
+        print(event.content, end="", flush=True)
+    elif event.type == "sources":
+        for src in event.sources:
+            print(f"\nSource: {src.citation}")
+    elif event.type == "done":
+        break
+```
+
+## MCP server (Claude Desktop / Cursor)
+
+Run the MCP server so Claude or any MCP-compatible agent can query your documents:
+
+```json
+{
+  "mcpServers": {
+    "pageindex": {
+      "command": "pageserve",
+      "args": ["mcp"],
+      "env": {
+        "PAGESERVE_URL":        "https://pageindex.company.com",
+        "PAGESERVE_PUBLIC_KEY": "<your-public-key>",
+        "PAGESERVE_SECRET_KEY": "<your-secret-key>"
+      }
+    }
+  }
+}
+```
+
+The MCP server exposes five tools:
+- `list_documents` — see what documents are available
+- `query_document` — ask a question against one document
+- `query_multiple_documents` — cross-reference multiple documents
+- `get_page_content` — read raw page text (no LLM, instant)
+- `get_document_structure` — browse the table of contents
+
+Keys live in env vars and never appear in tool arguments or the model's context window.
+
+## CLI
+
+```bash
+export PAGESERVE_URL=https://pageindex.company.com
+export PAGESERVE_PUBLIC_KEY=<your-public-key>
+export PAGESERVE_SECRET_KEY=<your-secret-key>
+
+pageserve list                                      # list documents
+pageserve query <doc_id> "question"                 # ask a question
+pageserve query <doc_id> "question" --stream        # streaming output
+pageserve upload ./report.pdf --watch               # upload + progress bar
+pageserve health                                    # service status
+pageserve keys list                                 # list API keys
+pageserve keys create "My App"                      # create a key
+pageserve mcp                                       # run MCP server (stdio)
+pageserve mcp --transport sse --port 3000           # MCP over SSE
+```
+
+## Error handling
+
+```python
+from pageserve import (
+    AuthError,
+    NotFoundError,
+    DocumentNotReadyError,
+    FileTooLargeError,
+    RateLimitError,
+    ServiceUnavailableError,
+    ServiceError,
+)
+
+try:
+    result = client.query(doc_id, "question")
+except AuthError:
+    print("Invalid or expired API key")
+except NotFoundError:
+    print("Document not found")
+except RateLimitError as e:
+    import time; time.sleep(e.retry_after)
+except ServiceError as e:
+    print(f"Server error [{e.status_code}]")
+```
+
+## Documentation
+
+- [Getting Started](docs/getting-started.md)
+- [Authentication](docs/authentication.md)
+- [Sync Client Reference](docs/sync-client.md)
+- [Async Client Reference](docs/async-client.md)
+- [Streaming (SSE)](docs/streaming.md)
+- [MCP Server](docs/mcp-server.md)
+- [CLI Reference](docs/cli.md)
+- [Data Models](docs/models.md)
+- [Error Handling](docs/error-handling.md)
+
+## Related
+
+- [PageIndex OSS](https://github.com/VectifyAI/PageIndex) — the self-hosted service this SDK wraps
+- [PageIndex Cloud](https://pageindex.ai) — hosted version

pageserve-0.1.0/pageserve/__init__.py

@@ -0,0 +1,68 @@
+from pageserve._async_client import AsyncPageServeClient
+from pageserve._client import PageServeClient
+from pageserve._exceptions import (
+    AuthError,
+    DocumentNotReadyError,
+    FileTooLargeError,
+    InsufficientStorageError,
+    NotFoundError,
+    PageServeError,
+    RateLimitError,
+    ServiceError,
+    ServiceUnavailableError,
+    TimeoutError,
+)
+from pageserve._models import (
+    ApiKey,
+    CreatedApiKey,
+    Document,
+    DocumentList,
+    HealthResult,
+    IndexProgress,
+    Page,
+    QueryResult,
+    QuerySource,
+    SSEEvent,
+    Stats,
+    StructureNode,
+    UploadResult,
+    Webhook,
+    WebhookTestResult,
+)
+
+__version__ = "0.1.0"
+__author__ = "pageserve"
+__license__ = "Apache-2.0"
+
+__all__ = [
+    # Clients
+    "PageServeClient",
+    "AsyncPageServeClient",
+    # Models
+    "Document",
+    "DocumentList",
+    "UploadResult",
+    "StructureNode",
+    "Page",
+    "QueryResult",
+    "QuerySource",
+    "SSEEvent",
+    "IndexProgress",
+    "ApiKey",
+    "CreatedApiKey",
+    "Stats",
+    "Webhook",
+    "WebhookTestResult",
+    "HealthResult",
+    # Exceptions
+    "PageServeError",
+    "AuthError",
+    "NotFoundError",
+    "DocumentNotReadyError",
+    "FileTooLargeError",
+    "ServiceUnavailableError",
+    "InsufficientStorageError",
+    "RateLimitError",
+    "ServiceError",
+    "TimeoutError",
+]