{
"event": "PreToolUse",
"tool_name": "Grep",
"tool_input": {
"pattern": "def.*chat|search_similar|get_embedding",
"path": "\/var\/www\/scripts\/pipeline",
"output_mode": "content"
}
}
{
"tool_response": {
"mode": "content",
"numFiles": 0,
"filenames": [],
"content": "venv\/lib\/python3.13\/site-packages\/qdrant_client-1.16.2.dist-info\/METADATA:178: size=client.get_embedding_size(model_name), distance=models.Distance.COSINE)\nvenv\/lib\/python3.13\/site-packages\/ollama-0.6.1.dist-info\/METADATA:95:async def chat():\nvenv\/lib\/python3.13\/site-packages\/ollama-0.6.1.dist-info\/METADATA:108:async def chat():\nvenv\/lib\/python3.13\/site-packages\/ollama\/_client.py:287: def chat(\nvenv\/lib\/python3.13\/site-packages\/ollama\/_client.py:303: def chat(\nvenv\/lib\/python3.13\/site-packages\/ollama\/_client.py:318: def chat(\nvenv\/lib\/python3.13\/site-packages\/ollama\/_client.py:904: async def chat(\nvenv\/lib\/python3.13\/site-packages\/ollama\/_client.py:920: async def chat(\nvenv\/lib\/python3.13\/site-packages\/ollama\/_client.py:935: async def chat(\nvenv\/lib\/python3.13\/site-packages\/qdrant_client\/async_qdrant_fastembed.py:425: def get_embedding_size(self, model_name: str | None = None) -> int:\nvenv\/lib\/python3.13\/site-packages\/qdrant_client\/qdrant_fastembed.py:443: def get_embedding_size(\ngenerate.py:14:from embed import search_similar # noqa: E402\ngenerate.py:83: results = search_similar(briefing, collection=collection, limit=limit)\nmodel_registry.py:46: def get_chat_models(self) -> dict:\nmodel_registry.py:62: def get_embedding_models(self) -> dict:\nmodel_registry.py:121: def get_default_chat_model(self) -> str:\nmodel_registry.py:122: \"\"\"Get default chat model (first available by priority).\"\"\"\nmodel_registry.py:130: embed_models = self.get_embedding_models()\nmodel_registry.py:169:def get_chat_model() -> str:\nmodel_registry.py:170: \"\"\"Get the default chat model from registry.\"\"\"\nmodel_registry.py:176: return registry.get_default_chat_model()\nmodel_registry.py:179:def get_embedding_model() -> str:\nchat.py:18:def get_embedding(text):\nchat.py:121:def chat(question, use_claude=True, top_k=5):\nchat.py:134: query_embedding = get_embedding(question)\nconfig.py:117:def get_chat_model_from_registry():\nconfig.py:118: \"\"\"Get default chat model from central registry (ki_dev.ai_models).\"\"\"\nembed.py:20:def get_embedding(text):\nembed.py:77: embedding = get_embedding(chunk[\"content\"])\nembed.py:132: embedding = get_embedding(chunk[\"content\"])\nembed.py:166:def search_similar(query, collection=\"documents\", limit=5):\nembed.py:169: embedding = get_embedding(query)\nembed.py:196: results = search_similar(query)",
"numLines": 33
}
}