feat: RAG pipeline + OpenAI SSE streaming, llama-server cluster integration

app.py

@@ -57,7 +57,7 @@ log.addHandler(syslog_handler)
 
 # --- Configuration ---
 VERSION = "1.7.6"
-OLLAMA_BASE = "http://localhost:11434"
+OLLAMA_BASE = os.environ.get("OLLAMA_BASE", "http://localhost:11434")
 SEARXNG_BASE = "http://localhost:8888"
 BASE_DIR = Path(__file__).parent
 DB_PATH = BASE_DIR / "jarvischat.db"
@@ -1480,14 +1480,24 @@ async def index(request: Request):
     return templates.TemplateResponse(request, "index.html", {"version": VERSION})
 
 
+#@app.get("/api/models")
+#async def list_models():
+#    async with httpx.AsyncClient() as client:
+#        try:
+#            resp = await client.get(f"{OLLAMA_BASE}/api/tags", timeout=10)
+#            return resp.json()
+#        except httpx.ConnectError:
+#            raise HTTPException(status_code=502, detail="Cannot connect to Ollama.")
 @app.get("/api/models")
 async def list_models():
     async with httpx.AsyncClient() as client:
         try:
-            resp = await client.get(f"{OLLAMA_BASE}/api/tags", timeout=10)
+            resp = await client.get(f"{OLLAMA_BASE}/v1/models", timeout=10)
-            return resp.json()
+            data = resp.json()
+            models = [{"name": m["id"], "model": m["id"]} for m in data.get("data", [])]
+            return {"models": models}
         except httpx.ConnectError:
-            raise HTTPException(status_code=502, detail="Cannot connect to Ollama.")
+            raise HTTPException(status_code=502, detail="Cannot connect to llama-server.")
 
 
 @app.get("/api/ps")
@@ -1962,16 +1972,12 @@ async def explicit_search(request: Request):
                 ) as resp:
                     async for line in resp.aiter_lines():
                         if line.strip():
-                            try:
+                            token, done, _ = parse_llama_stream_chunk(line)
-                                chunk = json.loads(line)
+                            if token:
-                                if "message" in chunk and "content" in chunk["message"]:
+                                full_response.append(token)
-                                    token = chunk["message"]["content"]
+                                yield f"data: {json.dumps({'token': token, 'conversation_id': conv_id})}\n\n"
-                                    full_response.append(token)
+                            if done:
-                                    yield f"data: {json.dumps({'token': token, 'conversation_id': conv_id})}\n\n"
+                                break
-                                if chunk.get("done"):
-                                    break
-                            except json.JSONDecodeError:
-                                pass
             except Exception as e:
                 incident_key = log_incident(
                     "search_summarization_stream",
@@ -2010,7 +2016,32 @@ async def explicit_search(request: Request):
 # =============================================================================
 
 
-def build_system_prompt(db, extra_prompt="", user_message=""):
+
+async def query_rag(query: str, limit: int = 3) -> list[dict]:
+    """Query Qdrant for semantically relevant chunks."""
+    try:
+        async with httpx.AsyncClient() as client:
+            embed_resp = await client.post(
+                "http://192.168.50.108:11434/api/embeddings",
+                json={"model": "mxbai-embed-large", "prompt": query},
+                timeout=10.0,
+            )
+            if embed_resp.status_code != 200:
+                return []
+            vector = embed_resp.json()["embedding"]
+            search_resp = await client.post(
+                "http://192.168.50.108:6333/collections/jarvis_rag/points/search",
+                json={"vector": vector, "limit": limit, "with_payload": True},
+                timeout=10.0,
+            )
+            if search_resp.status_code != 200:
+                return []
+            return search_resp.json().get("result", [])
+    except Exception as e:
+        log.warning(f"RAG query error: {e}")
+        return []
+
+async def build_system_prompt(db, extra_prompt="", user_message=""):
     """Build the full system prompt: profile + memories + preset."""
     parts = []
     settings = {
@@ -2030,6 +2061,17 @@ def build_system_prompt(db, extra_prompt="", user_message=""):
             parts.append("## Relevant Context from Memory\n" + "\n".join(memory_lines))
             log.debug(f"Injected {len(memories)} memories into context")
 
+    if user_message:
+        try:
+            rag_results = await query_rag(user_message)
+            if rag_results:
+                rag_lines = [r["payload"]["text"] for r in rag_results if r["score"] > 0.25]
+                if rag_lines:
+                    parts.append("## Retrieved Context\n" + "\n\n---\n\n".join(rag_lines))
+                    log.warning(f"RAG injected {len(rag_lines)} chunks into context")
+        except Exception as e:
+            log.warning(f"RAG injection error: {e}")
+
     if settings.get("skills_enabled", "true") == "true":
         active_skills = [s for s in list_skills_with_state(db) if s["enabled"]]
         if active_skills:
@@ -2041,6 +2083,42 @@ def build_system_prompt(db, extra_prompt="", user_message=""):
     return "\n\n---\n\n".join(parts) if parts else ""
 
 
+def parse_llama_stream_chunk(line: str) -> tuple[str | None, bool, dict]:
+    """Parse OpenAI-compatible SSE chunk. Returns (token, is_done, stats)."""
+    if line.startswith("data: "):
+        line = line[6:]
+    if line.strip() == "[DONE]":
+        return None, True, {}
+    try:
+        chunk = json.loads(line)
+        # OpenAI format
+        choices = chunk.get("choices", [])
+        if choices:
+            delta = choices[0].get("delta", {})
+            token = delta.get("content")
+            finish = choices[0].get("finish_reason")
+            stats = {}
+            if finish == "stop":
+                usage = chunk.get("usage", {})
+                stats["tokens_per_sec"] = usage.get("tokens_per_second", 0.0)
+            return token, finish == "stop", stats
+        # Ollama format fallback
+        if "message" in chunk and "content" in chunk["message"]:
+            token = chunk["message"]["content"]
+            done = chunk.get("done", False)
+            stats = {}
+            if done:
+                eval_count = chunk.get("eval_count", 0)
+                eval_duration = chunk.get("eval_duration", 0)
+                stats["tokens_per_sec"] = (
+                    (eval_count / (eval_duration / 1e9)) if eval_duration > 0 else 0
+                )
+            return token, done, stats
+    except json.JSONDecodeError:
+        pass
+    return None, False, {}
+
+
 @app.post("/api/chat")
 async def chat(request: Request):
     body = await read_json_body(request, BODY_LIMIT_CHAT_BYTES)
@@ -2086,7 +2164,7 @@ async def chat(request: Request):
         "SELECT role, content FROM messages WHERE conversation_id = ? ORDER BY id ASC",
         (conv_id,),
     ).fetchall()
-    system_prompt = build_system_prompt(db, preset_prompt, user_message)
+    system_prompt = await build_system_prompt(db, preset_prompt, user_message)
     db.close()
 
     messages = []
@@ -2099,7 +2177,6 @@ async def chat(request: Request):
         "model": model,
         "messages": messages,
         "stream": True,
-        "logprobs": True,
     }
 
     async def stream_response():
@@ -2120,25 +2197,12 @@ async def chat(request: Request):
                 ) as resp:
                     async for line in resp.aiter_lines():
                         if line.strip():
-                            try:
+                            token, done, stats = parse_llama_stream_chunk(line)
-                                chunk = json.loads(line)
+                            if token:
-                                if "message" in chunk and "content" in chunk["message"]:
+                                full_response.append(token)
-                                    token = chunk["message"]["content"]
+                                yield f"data: {json.dumps({'token': token, 'conversation_id': conv_id})}\n\n"
-                                    full_response.append(token)
+                            if done:
-                                    yield f"data: {json.dumps({'token': token, 'conversation_id': conv_id})}\n\n"
+                                tokens_per_sec = stats.get("tokens_per_sec", 0.0)
-                                if "logprobs" in chunk and chunk["logprobs"]:
-                                    all_logprobs.extend(chunk["logprobs"])
-                                if chunk.get("done"):
-                                    eval_count = chunk.get("eval_count", 0)
-                                    eval_duration = chunk.get("eval_duration", 0)
-                                    tokens_per_sec = (
-                                        (eval_count / (eval_duration / 1e9))
-                                        if eval_duration > 0
-                                        else 0
-                                    )
-                                    break
-                            except json.JSONDecodeError:
-                                pass
 
                 assistant_msg = "".join(full_response)
                 perplexity = calculate_perplexity(all_logprobs) if all_logprobs else 0.0
@@ -2186,19 +2250,11 @@ async def chat(request: Request):
                         ) as resp2:
                             async for line in resp2.aiter_lines():
                                 if line.strip():
-                                    try:
+                                    token2, done2, _ = parse_llama_stream_chunk(line)
-                                        chunk = json.loads(line)
+                                    if token2:
-                                        if (
+                                        augmented_response.append(token2)
-                                            "message" in chunk
+                                    if done2:
-                                            and "content" in chunk["message"]
+                                        break
-                                        ):
-                                            augmented_response.append(
-                                                chunk["message"]["content"]
-                                            )
-                                        if chunk.get("done"):
-                                            break
-                                    except json.JSONDecodeError:
-                                        pass
 
                         raw_response = "".join(augmented_response) or assistant_msg
                         cleaned_response = clean_hedging(raw_response)
@@ -2251,6 +2307,8 @@ async def chat(request: Request):
 
                 yield f"data: {json.dumps({'done': True, 'conversation_id': conv_id, 'perplexity': round(perplexity, 2), 'tokens_per_sec': round(tokens_per_sec, 1)})}\n\n"
 
+            except httpx.RemoteProtocolError:
+                pass  # llama-server closes connection after [DONE] — normal
             except httpx.ConnectError:
                 yield f"data: {json.dumps({'error': 'Cannot connect to Ollama. Is it running?'})}\n\n"
             except Exception as e: