Skip to content

A programming framework for agentic AI

version update post release v1.2.2 (#1005)

Chi Wangf097c20f860c
diff --git a/notebook/autogen_chatgpt.ipynb b/notebook/autogen_chatgpt.ipynb
index e0016922d..672038b9c 100644
--- a/notebook/autogen_chatgpt.ipynb
+++ b/notebook/autogen_chatgpt.ipynb
@@ -23,7 +23,7 @@
"\n",
"FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the [openai,blendsearch] option:\n",
"```bash\n",
- "pip install flaml[openai,blendsearch]==1.2.1\n",
+ "pip install flaml[openai,blendsearch]==1.2.2\n",
"```"
]
},
@@ -40,7 +40,7 @@
},
"outputs": [],
"source": [
- "# %pip install flaml[openai,blendsearch]==1.2.1 datasets"
+ "# %pip install flaml[openai,blendsearch]==1.2.2 datasets"
]
},
{
diff --git a/notebook/autogen_openai.ipynb b/notebook/autogen_openai.ipynb
index 58e87f470..68d77935c 100644
--- a/notebook/autogen_openai.ipynb
+++ b/notebook/autogen_openai.ipynb
@@ -23,7 +23,7 @@
"\n",
"FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the [autogen,blendsearch] option:\n",
"```bash\n",
- "pip install flaml[autogen,blendsearch]==1.2.1\n",
+ "pip install flaml[autogen,blendsearch]==1.2.2\n",
"```"
]
},
@@ -40,7 +40,7 @@
},
"outputs": [],
"source": [
- "# %pip install flaml[autogen,blendsearch]==1.2.1 datasets"
+ "# %pip install flaml[autogen,blendsearch]==1.2.2 datasets"
]
},
{
diff --git a/notebook/research/autogen_code.ipynb b/notebook/research/autogen_code.ipynb
index 29b3f3ae4..25f288ef5 100644
--- a/notebook/research/autogen_code.ipynb
+++ b/notebook/research/autogen_code.ipynb
@@ -21,7 +21,7 @@
"\n",
"FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the [autogen] option:\n",
"```bash\n",
- "pip install flaml[autogen]==1.2.1\n",
+ "pip install flaml[autogen]==1.2.2\n",
"```"
]
},
@@ -38,7 +38,7 @@
},
"outputs": [],
"source": [
- "# %pip install flaml[autogen]==1.2.1 datasets"
+ "# %pip install flaml[autogen]==1.2.2 datasets"
]
},
{
diff --git a/notebook/research/math_level5counting.ipynb b/notebook/research/math_level5counting.ipynb
index e7e7e0433..aa712cf41 100644
--- a/notebook/research/math_level5counting.ipynb
+++ b/notebook/research/math_level5counting.ipynb
@@ -21,7 +21,7 @@
"\n",
"FLAML requires `Python>=3.7`. To run this notebook example, please install flaml with the [openai] option:\n",
"```bash\n",
- "pip install flaml[openai]==1.2.1\n",
+ "pip install flaml[openai]==1.2.2\n",
"```"
]
},
@@ -38,7 +38,7 @@
},
"outputs": [],
"source": [
- "# %pip install flaml[openai]==1.2.1 datasets"
+ "# %pip install flaml[openai]==1.2.2 datasets"
]
},
{
diff --git a/website/docs/Examples/AutoGen-OpenAI.md b/website/docs/Examples/AutoGen-OpenAI.md
index 4f83cd99f..18759306b 100644
--- a/website/docs/Examples/AutoGen-OpenAI.md
+++ b/website/docs/Examples/AutoGen-OpenAI.md
@@ -5,9 +5,9 @@ In this example, we will tune several hyperparameters for the OpenAI's completio
### Prerequisites
-Install the [autogen,blendsearch] option. The OpenAI integration is in preview.
+Install the [autogen,blendsearch] option.
```bash
-pip install "flaml[autogen,blendsearch]==1.2.1 datasets"
+pip install "flaml[autogen,blendsearch]==1.2.2 datasets"
```
Setup your OpenAI key:
@@ -64,7 +64,9 @@ Before starting tuning, you need to define the metric for the optimization. For
from functools import partial
from flaml.autogen.code_utils import eval_function_completions, generate_assertions
-eval_with_generated_assertions = partial(eval_function_completions, assertions=generate_assertions)
+eval_with_generated_assertions = partial(
+ eval_function_completions, assertions=generate_assertions,
+)
```
This function will first generate assertion statements for each problem. Then, it uses the assertions to select the generated responses.
diff --git a/website/docs/Use-Cases/Auto-Generation.md b/website/docs/Use-Cases/Auto-Generation.md
index 8f51a1fa3..541141044 100644
--- a/website/docs/Use-Cases/Auto-Generation.md
+++ b/website/docs/Use-Cases/Auto-Generation.md
@@ -1,6 +1,6 @@
# Auto Generation
-`flaml.autogen` is a subpackage for automating generation tasks. It uses [`flaml.tune`](../reference/tune/tune) to find good hyperparameter configurations under budget constraints.
+`flaml.autogen` is a package for automating generation tasks (in preview). It uses [`flaml.tune`](../reference/tune/tune) to find good hyperparameter configurations under budget constraints.
Such optimization has several benefits:
* Maximize the utility out of using expensive foundation models.
* Reduce the inference cost by using cheaper models or configurations which achieve equal or better performance.