Phase 3: AI integration with Ollama via Python sidecar

- sidecar: FastAPI app with /embed, /generate, /rerank hitting Ollama
- sidecar: Dockerfile, env var config (EMBED_MODEL, GEN_MODEL, RERANK_MODEL)
- aibridge: reqwest HTTP client with typed request/response structs
- aibridge: Axum proxy endpoints (POST /ai/embed, /ai/generate, /ai/rerank)
- gateway: wires AiClient with SIDECAR_URL env var
- e2e verified: nomic-embed-text returns 768d vectors, qwen2.5 generates text

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

sidecar/sidecar/embed.py

@@ -0,0 +1,44 @@
+import os
+
+from fastapi import APIRouter, HTTPException
+from pydantic import BaseModel
+
+from .ollama import client
+
+router = APIRouter()
+
+EMBED_MODEL = os.environ.get("EMBED_MODEL", "nomic-embed-text")
+
+
+class EmbedRequest(BaseModel):
+    texts: list[str]
+    model: str | None = None
+
+
+class EmbedResponse(BaseModel):
+    embeddings: list[list[float]]
+    model: str
+    dimensions: int
+
+
+@router.post("", response_model=EmbedResponse)
+async def embed(req: EmbedRequest):
+    model = req.model or EMBED_MODEL
+    embeddings = []
+
+    async with client() as c:
+        for text in req.texts:
+            resp = await c.post("/api/embed", json={"model": model, "input": text})
+            if resp.status_code != 200:
+                raise HTTPException(502, f"Ollama error: {resp.text}")
+            data = resp.json()
+            embeddings.extend(data.get("embeddings", []))
+
+    if not embeddings:
+        raise HTTPException(502, "No embeddings returned")
+
+    return EmbedResponse(
+        embeddings=embeddings,
+        model=model,
+        dimensions=len(embeddings[0]),
+    )