Initial commit

llamaCpp.Wrapper.app/stream_transform.py

@@ -0,0 +1,102 @@
+import json
+import time
+import uuid
+from typing import Any, AsyncIterator, Dict
+
+import httpx
+
+
+def _sse_event(event: str, data: Dict[str, Any]) -> bytes:
+    payload = json.dumps(data, separators=(",", ":"))
+    return f"event: {event}\ndata: {payload}\n\n".encode("utf-8")
+
+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 stream_chat_to_responses(
+    base_url: str,
+    headers: Dict[str, str],
+    payload: Dict[str, Any],
+    timeout_s: float,
+) -> AsyncIterator[bytes]:
+    response_id = f"resp_{uuid.uuid4().hex}"
+    created = int(time.time())
+    model = payload.get("model") or "unknown"
+    msg_id = f"msg_{uuid.uuid4().hex}"
+    output_text = ""
+
+    response_stub = {
+        "id": response_id,
+        "object": "response",
+        "created": created,
+        "model": model,
+        "output": [
+            {
+                "id": msg_id,
+                "type": "message",
+                "role": "assistant",
+                "content": [
+                    {"type": "output_text", "text": ""}
+                ],
+            }
+        ],
+    }
+
+    yield _sse_event("response.created", {"type": "response.created", "response": response_stub})
+
+    async with httpx.AsyncClient(base_url=base_url, timeout=timeout_s) as client:
+        async with client.stream(
+            "POST",
+            "/v1/chat/completions",
+            headers=_filter_headers(headers),
+            json=payload,
+        ) as resp:
+            resp.raise_for_status()
+            buffer = ""
+            async for chunk in resp.aiter_text():
+                buffer += chunk
+                while "\n\n" in buffer:
+                    block, buffer = buffer.split("\n\n", 1)
+                    lines = [line for line in block.splitlines() if line.startswith("data:")]
+                    if not lines:
+                        continue
+                    data_str = "\n".join(line[len("data:"):].strip() for line in lines)
+                    if data_str == "[DONE]":
+                        continue
+                    try:
+                        data = json.loads(data_str)
+                    except json.JSONDecodeError:
+                        continue
+                    choices = data.get("choices") or []
+                    if not choices:
+                        continue
+                    delta = choices[0].get("delta") or {}
+                    text_delta = delta.get("content")
+                    if text_delta:
+                        output_text += text_delta
+                        yield _sse_event(
+                            "response.output_text.delta",
+                            {
+                                "type": "response.output_text.delta",
+                                "delta": text_delta,
+                                "item_id": msg_id,
+                                "output_index": 0,
+                                "content_index": 0,
+                            },
+                        )
+
+    yield _sse_event(
+        "response.output_text.done",
+        {
+            "type": "response.output_text.done",
+            "text": output_text,
+            "item_id": msg_id,
+            "output_index": 0,
+            "content_index": 0,
+        },
+    )
+
+    response_stub["output"][0]["content"][0]["text"] = output_text
+    yield _sse_event("response.completed", {"type": "response.completed", "response": response_stub})