phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-07 02:58:21 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

update rag examples to use fresh faiss index every time

Browse source
This commit is contained in:
Hardik Shah 2025-02-06 16:07:38 -08:00
parent c79cc92b37
commit 3e7f682906
3 changed files with 9 additions and 7 deletions
Download patch file Download diff file Expand all files Collapse all files

9
docs/getting_started.ipynb
View file

@ -89,7 +89,7 @@
"# install a branch of llama stack\n", "# install a branch of llama stack\n",
"import os\n", "import os\n",
"os.environ[\"UV_SYSTEM_PYTHON\"] = \"1\"\n", "os.environ[\"UV_SYSTEM_PYTHON\"] = \"1\"\n",
"!pip install uv \n", "!pip install uv\n",
"!uv pip install llama-stack" "!uv pip install llama-stack"
] ]
}, },
@ -691,7 +691,7 @@
" from google.colab import userdata\n", " from google.colab import userdata\n",
" os.environ['TOGETHER_API_KEY'] = userdata.get('TOGETHER_API_KEY')\n", " os.environ['TOGETHER_API_KEY'] = userdata.get('TOGETHER_API_KEY')\n",
" os.environ['TAVILY_SEARCH_API_KEY'] = userdata.get('TAVILY_SEARCH_API_KEY')\n", " os.environ['TAVILY_SEARCH_API_KEY'] = userdata.get('TAVILY_SEARCH_API_KEY')\n",
"except ImportError: \n", "except ImportError:\n",
" print(\"Not in Google Colab environment\")\n", " print(\"Not in Google Colab environment\")\n",
"\n", "\n",
"for key in ['TOGETHER_API_KEY', 'TAVILY_SEARCH_API_KEY']:\n", "for key in ['TOGETHER_API_KEY', 'TAVILY_SEARCH_API_KEY']:\n",
@ -1656,6 +1656,7 @@
} }
], ],
"source": [ "source": [
"import uuid\n",
"from llama_stack_client.lib.agents.agent import Agent\n", "from llama_stack_client.lib.agents.agent import Agent\n",
"from llama_stack_client.lib.agents.event_logger import EventLogger\n", "from llama_stack_client.lib.agents.event_logger import EventLogger\n",
"from llama_stack_client.types.agent_create_params import AgentConfig\n", "from llama_stack_client.types.agent_create_params import AgentConfig\n",
@ -1673,7 +1674,7 @@
" for i, url in enumerate(urls)\n", " for i, url in enumerate(urls)\n",
"]\n", "]\n",
"\n", "\n",
"vector_db_id = \"test-vector-db\"\n", "vector_db_id = f\"test-vector-db-{uuid.uuid4().hex}\"\n",
"client.vector_dbs.register(\n", "client.vector_dbs.register(\n",
" vector_db_id=vector_db_id,\n", " vector_db_id=vector_db_id,\n",
" embedding_model=\"all-MiniLM-L6-v2\",\n", " embedding_model=\"all-MiniLM-L6-v2\",\n",
@ -3098,7 +3099,7 @@
} }
], ],
"source": [ "source": [
"# NBVAL_SKIP \n", "# NBVAL_SKIP\n",
"print(f\"Getting traces for session_id={session_id}\")\n", "print(f\"Getting traces for session_id={session_id}\")\n",
"import json\n", "import json\n",
"\n", "\n",

3
docs/source/getting_started/index.md
View file

@ -173,6 +173,7 @@ Here is an example of a simple RAG (Retrieval Augmented Generation) chatbot agen
```python ```python
import os import os
import uuid
from termcolor import cprint from termcolor import cprint
from llama_stack_client.lib.agents.agent import Agent from llama_stack_client.lib.agents.agent import Agent
@ -214,7 +215,7 @@ documents = [
] ]
# Register a vector database # Register a vector database
vector_db_id = "test-vector-db" vector_db_id = f"test-vector-db-{uuid.uuid4().hex}"
client.vector_dbs.register( client.vector_dbs.register(
vector_db_id=vector_db_id, vector_db_id=vector_db_id,
embedding_model="all-MiniLM-L6-v2", embedding_model="all-MiniLM-L6-v2",

4
tests/client-sdk/agents/test_agents.py
View file

@ -297,7 +297,7 @@ def test_override_system_message_behavior(llama_stack_client, agent_config):
You are an expert in composing functions. You are given a question and a set of possible functions. You are an expert in composing functions. You are given a question and a set of possible functions.
Based on the question, you may or may not need to make one or more function/tool calls to achieve the purpose. Based on the question, you may or may not need to make one or more function/tool calls to achieve the purpose.
If none of the function can be used, don't return [], instead answer the question directly without using functions. If the given question lacks the parameters required by the function, If none of the function can be used, don't return [], instead answer the question directly without using functions. If the given question lacks the parameters required by the function,
also point it out. also point it out.
{{ function_description }} {{ function_description }}
""" """
@ -414,7 +414,7 @@ def test_rag_and_code_agent(llama_stack_client, agent_config):
) )
for i, url in enumerate(urls) for i, url in enumerate(urls)
] ]
vector_db_id = "test-vector-db" vector_db_id = f"test-vector-db-{uuid4()}"
llama_stack_client.vector_dbs.register( llama_stack_client.vector_dbs.register(
vector_db_id=vector_db_id, vector_db_id=vector_db_id,
embedding_model="all-MiniLM-L6-v2", embedding_model="all-MiniLM-L6-v2",