Feat/fastapi server

Dockerfile

@@ -0,0 +1,15 @@
+FROM python:3.11-slim
+
+WORKDIR /app
+
+COPY requirements.txt requirements-server.txt ./
+RUN pip install --no-cache-dir -r requirements.txt -r requirements-server.txt
+
+COPY . .
+
+ENV WORKSPACE_DIR=/data/workspace
+RUN mkdir -p /data/workspace
+
+EXPOSE 8000
+
+CMD ["uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8000"]

docker-compose.yml

@@ -0,0 +1,16 @@
+services:
+  pageindex:
+    build: .
+    restart: unless-stopped
+    ports:
+      - "8000:8000"
+    environment:
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
+      - WORKSPACE_DIR=/data/workspace
+      - ALLOWED_ORIGINS=${ALLOWED_ORIGINS:-*}
+      - API_SECRET=${API_SECRET:-}
+    volumes:
+      - pageindex_data:/data/workspace
+
+volumes:
+  pageindex_data:

requirements-server.txt

@@ -0,0 +1,4 @@
+fastapi==0.115.0
+uvicorn[standard]==0.30.6
+python-multipart==0.0.9
+anthropic>=0.40.0

requirements.txt

@@ -2,5 +2,6 @@ litellm==1.83.7
 # openai-agents  # optional: required for examples/agentic_vectorless_rag_demo.py
 pymupdf==1.26.4
 PyPDF2==3.0.1
-python-dotenv==1.2.2
+python-dotenv==1.0.1
 pyyaml==6.0.2
+

server.py

@@ -0,0 +1,128 @@
+import os
+import tempfile
+import anthropic
+from fastapi import FastAPI, File, HTTPException, Header, UploadFile
+from fastapi.middleware.cors import CORSMiddleware
+from pydantic import BaseModel
+
+from pageindex.client import PageIndexClient
+
+app = FastAPI(title="PageIndex API")
+
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=os.environ.get("ALLOWED_ORIGINS", "*").split(","),
+    allow_methods=["POST", "GET"],
+    allow_headers=["*"],
+)
+
+WORKSPACE_DIR = os.environ.get("WORKSPACE_DIR", "./workspace")
+API_SECRET = os.environ.get("API_SECRET", "")
+os.makedirs(WORKSPACE_DIR, exist_ok=True)
+
+pi_client = PageIndexClient(
+    model=os.environ.get("PAGEINDEX_MODEL", "claude-sonnet-4-6"),
+    workspace=WORKSPACE_DIR,
+)
+
+anthropic_client = anthropic.Anthropic()
+
+
+def verify_secret(x_api_secret: str = Header(default="")):
+    if API_SECRET and x_api_secret != API_SECRET:
+        raise HTTPException(status_code=401, detail="Invalid API secret.")
+
+
+@app.get("/health")
+def health():
+    return {"status": "ok"}
+
+
+@app.post("/index")
+async def index_document(
+    file: UploadFile = File(...),
+    x_api_secret: str = Header(default=""),
+):
+    verify_secret(x_api_secret)
+    if not file.filename.lower().endswith(".pdf"):
+        raise HTTPException(status_code=400, detail="Only PDF files are supported")
+
+    with tempfile.NamedTemporaryFile(suffix=".pdf", delete=False) as tmp:
+        tmp.write(await file.read())
+        tmp_path = tmp.name
+
+    try:
+        doc_id = pi_client.index(tmp_path)
+        return {"doc_id": doc_id, "filename": file.filename}
+    finally:
+        os.unlink(tmp_path)
+
+
+class QueryRequest(BaseModel):
+    doc_id: str
+    question: str
+
+
+@app.post("/query")
+def query_document(
+    req: QueryRequest,
+    x_api_secret: str = Header(default=""),
+):
+    verify_secret(x_api_secret)
+    structure = pi_client.get_document_structure(req.doc_id)
+
+    tools = [
+        {
+            "name": "get_page_content",
+            "description": "Retrieve the text of specific pages from the document.",
+            "input_schema": {
+                "type": "object",
+                "properties": {
+                    "pages": {
+                        "type": "string",
+                        "description": "Pages to fetch. Examples: '5-7', '3,8', '12'.",
+                    }
+                },
+                "required": ["pages"],
+            },
+        }
+    ]
+
+    messages = [
+        {
+            "role": "user",
+            "content": f"Document structure:\n{structure}\n\nQuestion: {req.question}",
+        }
+    ]
+
+    for _ in range(10):
+        response = anthropic_client.messages.create(
+            model="claude-sonnet-4-6",
+            max_tokens=2048,
+            system=(
+                "You are a document analysis assistant. "
+                "Use the document structure to navigate the document and answer the question. "
+                "Always cite the page numbers where you found the information."
+            ),
+            tools=tools,
+            messages=messages,
+        )
+
+        if response.stop_reason == "end_turn":
+            answer = next(
+                (b.text for b in response.content if hasattr(b, "text")), ""
+            )
+            return {"answer": answer}
+
+        if response.stop_reason == "tool_use":
+            tool_results = []
+            for block in response.content:
+                if block.type == "tool_use" and block.name == "get_page_content":
+                    content = pi_client.get_page_content(req.doc_id, block.input["pages"])
+                    tool_results.append(
+                        {"type": "tool_result", "tool_use_id": block.id, "content": content}
+                    )
+            messages.append({"role": "assistant", "content": response.content})
+            messages.append({"role": "user", "content": tool_results})
+
+    raise HTTPException(status_code=500, detail="Could not answer the question.")

setup.sh

@@ -0,0 +1,37 @@
+#!/bin/bash
+# PageIndex Azure VM setup script
+# Run as root on a fresh Ubuntu 22.04 VM
+set -e
+
+echo "=== Installing Docker ==="
+apt-get update -qq
+apt-get install -y docker.io docker-compose-plugin git curl
+
+systemctl enable docker
+systemctl start docker
+
+echo "=== Cloning PageIndex ==="
+git clone https://github.com/clapointe-carbonleo/PageIndex.git /opt/pageindex
+cd /opt/pageindex
+git checkout feat/fastapi-server
+
+echo "=== Creating .env file ==="
+cat > /opt/pageindex/.env << 'ENVEOF'
+# Required — Anthropic API key for Claude
+ANTHROPIC_API_KEY=sk-ant-REPLACE_ME
+
+# Allowed origins (comma-separated) — set to your mike-legal Vercel URL
+ALLOWED_ORIGINS=https://mike-legal-three.vercel.app
+
+# Optional — secret token to protect the API (add to PAGEINDEX_SECRET in Vercel)
+API_SECRET=REPLACE_WITH_RANDOM_SECRET
+ENVEOF
+
+echo "=== Building and starting service ==="
+cd /opt/pageindex
+docker compose up -d --build
+
+echo ""
+echo "=== Done! ==="
+echo "PageIndex service is running on port 8000."
+echo "Edit /opt/pageindex/.env to set your real API keys, then run: docker compose restart"