diff --git a/Dockerfile.llamaswap-rocm b/Dockerfile.llamaswap-rocm index 72bd488..fff3911 100644 --- a/Dockerfile.llamaswap-rocm +++ b/Dockerfile.llamaswap-rocm @@ -1,31 +1,7 @@ # Multi-stage build for llama-swap with ROCm support -# Stage 1: Build llama.cpp with ROCm (requires ROCm 6.1+) -FROM rocm/dev-ubuntu-22.04:6.2.4 AS llama-builder +# Now using official llama.cpp ROCm image (PR #18439 merged Dec 29, 2025) -WORKDIR /build - -# Install build dependencies including ROCm/HIP development libraries -RUN apt-get update && apt-get install -y \ - git \ - build-essential \ - cmake \ - wget \ - libcurl4-openssl-dev \ - hip-dev \ - hipblas-dev \ - rocblas-dev \ - && rm -rf /var/lib/apt/lists/* - -# Clone and build llama.cpp with HIP/ROCm support (gfx1030 = RX 6800) -RUN git clone https://github.com/ggml-org/llama.cpp.git && \ - cd llama.cpp && \ - HIPCXX="$(hipconfig -l)/clang" HIP_PATH="$(hipconfig -R)" \ - cmake -S . -B build -DGGML_HIP=ON -DGPU_TARGETS=gfx1030 -DCMAKE_BUILD_TYPE=Release && \ - cmake --build build --config Release -- -j$(nproc) && \ - cp build/bin/llama-server /build/llama-server && \ - find build -name "*.so*" -exec cp {} /build/ \; - -# Stage 2: Build llama-swap UI and binary +# Stage 1: Build llama-swap UI FROM node:22-alpine AS ui-builder WORKDIR /build @@ -36,11 +12,11 @@ RUN apk add --no-cache git # Clone llama-swap RUN git clone https://github.com/mostlygeek/llama-swap.git -# Build UI -WORKDIR /build/llama-swap/ui +# Build UI (now in ui-svelte directory) +WORKDIR /build/llama-swap/ui-svelte RUN npm install && npm run build -# Stage 3: Build llama-swap binary +# Stage 2: Build llama-swap binary FROM golang:1.23-alpine AS swap-builder WORKDIR /build @@ -55,27 +31,19 @@ COPY --from=ui-builder /build/llama-swap /build/llama-swap WORKDIR /build/llama-swap RUN GOTOOLCHAIN=auto go build -o /build/llama-swap-binary . -# Stage 4: Final runtime image -FROM rocm/dev-ubuntu-22.04:6.2.4 +# Stage 3: Final runtime image using official llama.cpp ROCm image +FROM ghcr.io/ggml-org/llama.cpp:server-rocm WORKDIR /app -# Install runtime dependencies including additional ROCm libraries -RUN apt-get update && apt-get install -y \ - curl \ - ca-certificates \ - rocm-libs \ - && rm -rf /var/lib/apt/lists/* - -# Copy built binaries and shared libraries from previous stages -COPY --from=llama-builder /build/llama-server /app/llama-server -COPY --from=llama-builder /build/*.so* /app/ +# Copy llama-swap binary from builder COPY --from=swap-builder /build/llama-swap-binary /app/llama-swap -# Make binaries executable -RUN chmod +x /app/llama-server /app/llama-swap +# Make binary executable +RUN chmod +x /app/llama-swap -# Create user and add to GPU access groups (using host GIDs) +# Create non-root user and add to GPU access groups +# The official llama.cpp image already has llama-server installed # GID 187 = render group on host, GID 989 = video/kfd group on host RUN groupadd -g 187 hostrender && \ groupadd -g 989 hostvideo && \ @@ -86,7 +54,6 @@ RUN groupadd -g 187 hostrender && \ ENV HSA_OVERRIDE_GFX_VERSION=10.3.0 ENV ROCM_PATH=/opt/rocm ENV HIP_VISIBLE_DEVICES=0 -ENV LD_LIBRARY_PATH=/opt/rocm/lib:/app:$LD_LIBRARY_PATH USER llamaswap diff --git a/bot/static/index.html b/bot/static/index.html index aace144..19294a0 100644 --- a/bot/static/index.html +++ b/bot/static/index.html @@ -1548,9 +1548,6 @@ - - -
@@ -1687,6 +1684,9 @@
+ + +

Logs

diff --git a/bot/utils/cat_client.py b/bot/utils/cat_client.py index 2c05433..3a75e0f 100644 --- a/bot/utils/cat_client.py +++ b/bot/utils/cat_client.py @@ -21,7 +21,7 @@ from typing import Optional, Dict, Any, List import globals from utils.logger import get_logger -logger = get_logger('cat_client') +logger = get_logger('llm') # Use existing 'llm' logger component class CatAdapter: @@ -254,24 +254,36 @@ class CatAdapter: async def get_memory_stats(self) -> Optional[Dict[str, Any]]: """ - Get memory collection statistics from Cat. + Get memory collection statistics with actual counts from Qdrant. Returns dict with collection names and point counts. """ try: - async with aiohttp.ClientSession() as session: - async with session.get( - f"{self._base_url}/memory/collections", - headers=self._get_headers(), - timeout=aiohttp.ClientTimeout(total=15) - ) as response: - if response.status == 200: - data = await response.json() - return data - else: - logger.error(f"Failed to get memory stats: {response.status}") - return None + # Query Qdrant directly for accurate counts + qdrant_host = self._base_url.replace("http://cheshire-cat:80", "http://cheshire-cat-vector-memory:6333") + + collections_data = [] + for collection_name in ["episodic", "declarative", "procedural"]: + async with aiohttp.ClientSession() as session: + async with session.get( + f"{qdrant_host}/collections/{collection_name}", + timeout=aiohttp.ClientTimeout(total=10) + ) as response: + if response.status == 200: + data = await response.json() + count = data.get("result", {}).get("points_count", 0) + collections_data.append({ + "name": collection_name, + "vectors_count": count + }) + else: + collections_data.append({ + "name": collection_name, + "vectors_count": 0 + }) + + return {"collections": collections_data} except Exception as e: - logger.error(f"Error getting memory stats: {e}") + logger.error(f"Error getting memory stats from Qdrant: {e}") return None async def get_memory_points( @@ -281,28 +293,33 @@ class CatAdapter: offset: Optional[str] = None ) -> Optional[Dict[str, Any]]: """ - Get all points from a memory collection. + Get all points from a memory collection via Qdrant. + Cat doesn't expose /memory/collections/{id}/points, so we query Qdrant directly. Returns paginated list of memory points. """ try: - params = {"limit": limit} + # Use Qdrant directly (Cat's vector memory backend) + # Qdrant is accessible at the same host, port 6333 internally + qdrant_host = self._base_url.replace("http://cheshire-cat:80", "http://cheshire-cat-vector-memory:6333") + + payload = {"limit": limit, "with_payload": True, "with_vector": False} if offset: - params["offset"] = offset + payload["offset"] = offset async with aiohttp.ClientSession() as session: - async with session.get( - f"{self._base_url}/memory/collections/{collection}/points", - headers=self._get_headers(), - params=params, + async with session.post( + f"{qdrant_host}/collections/{collection}/points/scroll", + json=payload, timeout=aiohttp.ClientTimeout(total=30) ) as response: if response.status == 200: - return await response.json() + data = await response.json() + return data.get("result", {}) else: - logger.error(f"Failed to get {collection} points: {response.status}") + logger.error(f"Failed to get {collection} points from Qdrant: {response.status}") return None except Exception as e: - logger.error(f"Error getting memory points: {e}") + logger.error(f"Error getting memory points from Qdrant: {e}") return None async def get_all_facts(self) -> List[Dict[str, Any]]: @@ -344,22 +361,24 @@ class CatAdapter: return all_facts async def delete_memory_point(self, collection: str, point_id: str) -> bool: - """Delete a single memory point by ID.""" + """Delete a single memory point by ID via Qdrant.""" try: + qdrant_host = self._base_url.replace("http://cheshire-cat:80", "http://cheshire-cat-vector-memory:6333") + async with aiohttp.ClientSession() as session: - async with session.delete( - f"{self._base_url}/memory/collections/{collection}/points/{point_id}", - headers=self._get_headers(), + async with session.post( + f"{qdrant_host}/collections/{collection}/points/delete", + json={"points": [point_id]}, timeout=aiohttp.ClientTimeout(total=15) ) as response: if response.status == 200: - logger.info(f"Deleted point {point_id} from {collection}") + logger.info(f"Deleted memory point {point_id} from {collection}") return True else: logger.error(f"Failed to delete point: {response.status}") return False except Exception as e: - logger.error(f"Error deleting point: {e}") + logger.error(f"Error deleting memory point: {e}") return False async def wipe_all_memories(self) -> bool: diff --git a/cat-plugins/discord_bridge/discord_bridge.py b/cat-plugins/discord_bridge/discord_bridge.py index f6b665b..ccd3e5e 100644 --- a/cat-plugins/discord_bridge/discord_bridge.py +++ b/cat-plugins/discord_bridge/discord_bridge.py @@ -52,6 +52,14 @@ def before_cat_reads_message(user_message_json: dict, cat) -> dict: cat.working_memory['mood'] = mood cat.working_memory['response_type'] = response_type + # If we have an author name, prepend it to the message text so the LLM can see it + # This ensures Miku knows who is talking to her + if author_name and 'text' in user_message_json: + original_text = user_message_json['text'] + # Don't add name if it's already in the message + if not original_text.lower().startswith(author_name.lower()): + user_message_json['text'] = f"[{author_name} says:] {original_text}" + return user_message_json