Initial commit

llamaCpp.Wrapper.app/llamacpp_client.py

@@ -0,0 +1,52 @@
+import logging
+from typing import AsyncIterator, Dict, Optional
+
+import httpx
+
+
+log = logging.getLogger("llamacpp_client")
+
+
+def _filter_headers(headers: Dict[str, str]) -> Dict[str, str]:
+    drop = {"host", "content-length"}
+    return {k: v for k, v in headers.items() if k.lower() not in drop}
+
+
+async def proxy_json(
+    base_url: str,
+    path: str,
+    method: str,
+    headers: Dict[str, str],
+    payload: Optional[dict],
+    timeout_s: float,
+) -> httpx.Response:
+    async with httpx.AsyncClient(base_url=base_url, timeout=timeout_s) as client:
+        return await client.request(method, path, headers=_filter_headers(headers), json=payload)
+
+
+async def proxy_raw(
+    base_url: str,
+    path: str,
+    method: str,
+    headers: Dict[str, str],
+    body: Optional[bytes],
+    timeout_s: float,
+) -> httpx.Response:
+    async with httpx.AsyncClient(base_url=base_url, timeout=timeout_s) as client:
+        return await client.request(method, path, headers=_filter_headers(headers), content=body)
+
+
+async def proxy_stream(
+    base_url: str,
+    path: str,
+    method: str,
+    headers: Dict[str, str],
+    payload: Optional[dict],
+    timeout_s: float,
+) -> AsyncIterator[bytes]:
+    async with httpx.AsyncClient(base_url=base_url, timeout=timeout_s) as client:
+        async with client.stream(method, path, headers=_filter_headers(headers), json=payload) as resp:
+            resp.raise_for_status()
+            async for chunk in resp.aiter_bytes():
+                if chunk:
+                    yield chunk