phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-12 04:50:39 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

header size

Browse source
This commit is contained in:
Xi Yan 2025-03-03 16:08:58 -08:00
parent db4e5708a3
commit 9ff6ceef45
1 changed files with 11 additions and 11 deletions
Download patch file Download diff file Expand all files Collapse all files

22
docs/notebooks/Llama_Stack_Agent_Workflows.ipynb
View file

@ -1798,6 +1798,15 @@
" print(\"\\n\")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 1.3.1 Monitor Parallelization Internals\n",
"\n",
"Now, let's see how the worker agents processed the tasks. "
]
},
{
"cell_type": "code",
"execution_count": 126,
@ -2223,16 +2232,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"### 1.3.1 Monitor Parallelization Internals\n",
"\n",
"Now, let's see how the worker agents processed the tasks. "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 2. Evaluator-Optimizer Workflow\n",
"## 2. Evaluator-Optimizer Workflow\n",
"\n",
"In the evaluator-optimizer workflow, one LLM call generates a response while another provider evaluation and feedback in a loop. \n",
"\n",
@ -2399,7 +2399,7 @@
"cell_type": "markdown",
"metadata": {},
"source": [
"#### 2.1. Monitor Generator-Evaluator Internals\n",
"### 2.1. Monitor Generator-Evaluator Internals\n",
"\n",
"In addition to final output from workflow, we can also look at how the generator and evaluator agents processed the user's request. Note that the `evaluator_agent` PASSED after 1 iteration. "
]