wangtao
/
autogen
mirror of https://github.com/microsoft/autogen.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Bugfix: PGVector/RAG - Calculate the Vector Size based on Model Dimensions (#2865) 

* Calculate the dimension size based off model chosen.

* Added example docstring.

* Validated working notebook with sentence models of different dimensions.

* Validated removal of model_name working.

* Second example uses conn object.

* embedding_function no longer directly references .encode

* Fixed pre-commit issue.

* Use try/except to raise error when shape is not found in embedding function.

* Re-ran notebook.

* Update autogen/agentchat/contrib/vectordb/pgvectordb.py

Co-authored-by: Li Jiang <bnujli@gmail.com>

* Update autogen/agentchat/contrib/vectordb/pgvectordb.py

Co-authored-by: Li Jiang <bnujli@gmail.com>

* Added .encode

* Removed example comment.

* Fix overwrite doesn't work with existing collection when custom embedding function has different dimension from default one

---------

Co-authored-by: Li Jiang <bnujli@gmail.com>
This commit is contained in:
Audel Rouhi 2024-06-11 07:16:56 -05:00 committed by GitHub
parent 2d6c8c012b
commit bf7e4d619c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 451 additions and 94 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

84
autogen/agentchat/contrib/vectordb/pgvectordb.py
View File

@ -32,10 +32,11 @@ class Collection:
client: The PGVector client.
collection_name (str): The name of the collection. Default is "documents".
embedding_function (Callable): The embedding function used to generate the vector representation.
Default is None. SentenceTransformer("all-MiniLM-L6-v2").encode will be used when None.
Models can be chosen from:
https://huggingface.co/models?library=sentence-transformers
metadata (Optional[dict]): The metadata of the collection.
get_or_create (Optional): The flag indicating whether to get or create the collection.
model_name: (Optional str) | Sentence embedding model to use. Models can be chosen from:
https://huggingface.co/models?library=sentence-transformers
"""
def __init__(
@ -45,7 +46,6 @@ class Collection:
embedding_function: Callable = None,
metadata=None,
get_or_create=None,
model_name="all-MiniLM-L6-v2",
):
"""
Initialize the Collection object.
@ -56,30 +56,26 @@ class Collection:
embedding_function: The embedding function used to generate the vector representation.
metadata: The metadata of the collection.
get_or_create: The flag indicating whether to get or create the collection.
model_name: | Sentence embedding model to use. Models can be chosen from:
https://huggingface.co/models?library=sentence-transformers
Returns:
None
"""
self.client = client
self.embedding_function = embedding_function
self.model_name = model_name
self.name = self.set_collection_name(collection_name)
self.require_embeddings_or_documents = False
self.ids = []
try:
self.embedding_function = (
SentenceTransformer(self.model_name) if embedding_function is None else embedding_function
)
except Exception as e:
logger.error(
f"Validate the model name entered: {self.model_name} "
f"from https://huggingface.co/models?library=sentence-transformers\nError: {e}"
)
raise e
if embedding_function:
self.embedding_function = embedding_function
else:
self.embedding_function = SentenceTransformer("all-MiniLM-L6-v2").encode
self.metadata = metadata if metadata else {"hnsw:space": "ip", "hnsw:construction_ef": 32, "hnsw:M": 16}
self.documents = ""
self.get_or_create = get_or_create
# This will get the model dimension size by computing the embeddings dimensions
sentences = [
"The weather is lovely today in paradise.",
]
embeddings = self.embedding_function(sentences)
self.dimension = len(embeddings[0])
def set_collection_name(self, collection_name) -> str:
name = re.sub("-", "_", collection_name)
@ -115,14 +111,14 @@ class Collection:
elif metadatas is not None:
for doc_id, metadata, document in zip(ids, metadatas, documents):
metadata = re.sub("'", '"', str(metadata))
embedding = self.embedding_function.encode(document)
embedding = self.embedding_function(document)
sql_values.append((doc_id, metadata, embedding, document))
sql_string = (
f"INSERT INTO {self.name} (id, metadatas, embedding, documents)\n" f"VALUES (%s, %s, %s, %s);\n"
)
else:
for doc_id, document in zip(ids, documents):
embedding = self.embedding_function.encode(document)
embedding = self.embedding_function(document)
sql_values.append((doc_id, document, embedding))
sql_string = f"INSERT INTO {self.name} (id, documents, embedding)\n" f"VALUES (%s, %s, %s);\n"
logger.debug(f"Add SQL String:\n{sql_string}\n{sql_values}")
@ -166,7 +162,7 @@ class Collection:
elif metadatas is not None:
for doc_id, metadata, document in zip(ids, metadatas, documents):
metadata = re.sub("'", '"', str(metadata))
embedding = self.embedding_function.encode(document)
embedding = self.embedding_function(document)
sql_values.append((doc_id, metadata, embedding, document, metadata, document, embedding))
sql_string = (
f"INSERT INTO {self.name} (id, metadatas, embedding, documents)\n"
@ -176,7 +172,7 @@ class Collection:
)
else:
for doc_id, document in zip(ids, documents):
embedding = self.embedding_function.encode(document)
embedding = self.embedding_function(document)
sql_values.append((doc_id, document, embedding, document))
sql_string = (
f"INSERT INTO {self.name} (id, documents, embedding)\n"
@ -304,7 +300,7 @@ class Collection:
)
except (psycopg.errors.UndefinedTable, psycopg.errors.UndefinedColumn) as e:
logger.info(f"Error executing select on non-existent table: {self.name}. Creating it instead. Error: {e}")
self.create_collection(collection_name=self.name)
self.create_collection(collection_name=self.name, dimension=self.dimension)
logger.info(f"Created table {self.name}")
cursor.close()
@ -419,7 +415,7 @@ class Collection:
cursor = self.client.cursor()
results = []
for query_text in query_texts:
vector = self.embedding_function.encode(query_text, convert_to_tensor=False).tolist()
vector = self.embedding_function(query_text, convert_to_tensor=False).tolist()
if distance_type.lower() == "cosine":
index_function = "<=>"
elif distance_type.lower() == "euclidean":
@ -526,22 +522,31 @@ class Collection:
cursor.execute(f"DROP TABLE IF EXISTS {self.name}")
cursor.close()
def create_collection(self, collection_name: Optional[str] = None) -> None:
def create_collection(
self, collection_name: Optional[str] = None, dimension: Optional[Union[str, int]] = None
) -> None:
"""
Create a new collection.
Args:
collection_name (Optional[str]): The name of the new collection.
dimension (Optional[Union[str, int]]): The dimension size of the sentence embedding model
Returns:
None
"""
if collection_name:
self.name = collection_name
if dimension:
self.dimension = dimension
elif self.dimension is None:
self.dimension = 384
cursor = self.client.cursor()
cursor.execute(
f"CREATE TABLE {self.name} ("
f"documents text, id CHAR(8) PRIMARY KEY, metadatas JSONB, embedding vector(384));"
f"documents text, id CHAR(8) PRIMARY KEY, metadatas JSONB, embedding vector({self.dimension}));"
f"CREATE INDEX "
f'ON {self.name} USING hnsw (embedding vector_l2_ops) WITH (m = {self.metadata["hnsw:M"]}, '
f'ef_construction = {self.metadata["hnsw:construction_ef"]});'
@ -573,7 +578,6 @@ class PGVectorDB(VectorDB):
connect_timeout: Optional[int] = 10,
embedding_function: Callable = None,
metadata: Optional[dict] = None,
model_name: Optional[str] = "all-MiniLM-L6-v2",
) -> None:
"""
Initialize the vector database.
@ -591,15 +595,14 @@ class PGVectorDB(VectorDB):
username: str | The database username to use. Default is None.
password: str | The database user password to use. Default is None.
connect_timeout: int | The timeout to set for the connection. Default is 10.
embedding_function: Callable | The embedding function used to generate the vector representation
of the documents. Default is None.
embedding_function: Callable | The embedding function used to generate the vector representation.
Default is None. SentenceTransformer("all-MiniLM-L6-v2").encode will be used when None.
Models can be chosen from:
https://huggingface.co/models?library=sentence-transformers
metadata: dict | The metadata of the vector database. Default is None. If None, it will use this
setting: {"hnsw:space": "ip", "hnsw:construction_ef": 30, "hnsw:M": 16}. Creates Index on table
using hnsw (embedding vector_l2_ops) WITH (m = hnsw:M) ef_construction = "hnsw:construction_ef".
For more info: https://github.com/pgvector/pgvector?tab=readme-ov-file#hnsw
model_name: str | Sentence embedding model to use. Models can be chosen from:
https://huggingface.co/models?library=sentence-transformers
Returns:
None
"""
@ -613,17 +616,10 @@ class PGVectorDB(VectorDB):
password=password,
connect_timeout=connect_timeout,
)
self.model_name = model_name
try:
self.embedding_function = (
SentenceTransformer(self.model_name) if embedding_function is None else embedding_function
)
except Exception as e:
logger.error(
f"Validate the model name entered: {self.model_name} "
f"from https://huggingface.co/models?library=sentence-transformers\nError: {e}"
)
raise e
if embedding_function:
self.embedding_function = embedding_function
else:
self.embedding_function = SentenceTransformer("all-MiniLM-L6-v2").encode
self.metadata = metadata
register_vector(self.client)
self.active_collection = None
@ -738,7 +734,6 @@ class PGVectorDB(VectorDB):
embedding_function=self.embedding_function,
get_or_create=get_or_create,
metadata=self.metadata,
model_name=self.model_name,
)
collection.set_collection_name(collection_name=collection_name)
collection.create_collection(collection_name=collection_name)
@ -751,7 +746,6 @@ class PGVectorDB(VectorDB):
embedding_function=self.embedding_function,
get_or_create=get_or_create,
metadata=self.metadata,
model_name=self.model_name,
)
collection.set_collection_name(collection_name=collection_name)
collection.create_collection(collection_name=collection_name)
@ -765,7 +759,6 @@ class PGVectorDB(VectorDB):
embedding_function=self.embedding_function,
get_or_create=get_or_create,
metadata=self.metadata,
model_name=self.model_name,
)
collection.set_collection_name(collection_name=collection_name)
collection.create_collection(collection_name=collection_name)
@ -797,7 +790,6 @@ class PGVectorDB(VectorDB):
client=self.client,
collection_name=collection_name,
embedding_function=self.embedding_function,
model_name=self.model_name,
)
return self.active_collection

459
notebook/agentchat_pgvector_RetrieveChat.ipynb
View File

@ -72,14 +72,14 @@
},
{
"cell_type": "code",
"execution_count": 2,
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"models to use: ['gpt-35-turbo', 'gpt4-1106-preview', 'gpt-35-turbo-0613']\n"
"models to use: ['gpt4-1106-preview', 'gpt-4o', 'gpt-35-turbo', 'gpt-35-turbo-0613']\n"
]
}
],
@ -89,6 +89,7 @@
"\n",
"import chromadb\n",
"import psycopg\n",
"from sentence_transformers import SentenceTransformer\n",
"\n",
"import autogen\n",
"from autogen.agentchat.contrib.retrieve_assistant_agent import RetrieveAssistantAgent\n",
@ -114,7 +115,10 @@
" \"api_key\": \"...\",\n",
" },\n",
"]\n",
"\n",
"config_list = autogen.config_list_from_json(\n",
" \"OAI_CONFIG_LIST\",\n",
" file_location=\".\",\n",
")\n",
"assert len(config_list) > 0\n",
"print(\"models to use: \", [config_list[i][\"model\"] for i in range(len(config_list))])"
]
@ -137,7 +141,7 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": 2,
"metadata": {},
"outputs": [
{
@ -145,7 +149,7 @@
"output_type": "stream",
"text": [
"Accepted file formats for `docs_path`:\n",
"['txt', 'json', 'csv', 'tsv', 'md', 'html', 'htm', 'rtf', 'rst', 'jsonl', 'log', 'xml', 'yaml', 'yml', 'pdf']\n"
"['yaml', 'ppt', 'rst', 'jsonl', 'xml', 'txt', 'yml', 'log', 'rtf', 'msg', 'xlsx', 'htm', 'pdf', 'org', 'pptx', 'md', 'docx', 'epub', 'tsv', 'csv', 'html', 'doc', 'odt', 'json']\n"
]
}
],
@ -156,17 +160,15 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 3,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/workspace/anaconda3/envs/autogen/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
" from .autonotebook import tqdm as notebook_tqdm\n",
"/workspace/anaconda3/envs/autogen/lib/python3.11/site-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
" warnings.warn(\n"
"/home/lijiang1/anaconda3/envs/autogen/lib/python3.10/site-packages/transformers/utils/generic.py:311: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n",
" torch.utils._pytree._register_pytree_node(\n"
]
}
],
@ -185,6 +187,9 @@
"# Optionally create psycopg conn object\n",
"# conn = psycopg.connect(conninfo=\"postgresql://postgres:postgres@localhost:5432/postgres\", autocommit=True)\n",
"\n",
"# Optionally create embedding function object\n",
"sentence_transformer_ef = SentenceTransformer(\"all-distilroberta-v1\").encode\n",
"\n",
"# 2. create the RetrieveUserProxyAgent instance named \"ragproxyagent\"\n",
"# By default, the human_input_mode is \"ALWAYS\", which means the agent will ask for human input at every step. We set it to \"NEVER\" here.\n",
"# `docs_path` is the path to the docs directory. It can also be the path to a single file, or the url to a single file. By default,\n",
@ -218,11 +223,11 @@
" # \"dbname\": \"postgres\", # Optional vector database name\n",
" # \"username\": \"postgres\", # Optional vector database username\n",
" # \"password\": \"postgres\", # Optional vector database password\n",
" \"model_name\": \"all-MiniLM-L6-v2\", # Sentence embedding model from https://huggingface.co/models?library=sentence-transformers or https://www.sbert.net/docs/pretrained_models.html\n",
" # \"conn\": conn, # Optional - conn object to connect to database\n",
" },\n",
" \"get_or_create\": True, # set to False if you don't want to reuse an existing collection\n",
" \"overwrite\": False, # set to True if you want to overwrite an existing collection\n",
" \"overwrite\": True, # set to True if you want to overwrite an existing collection\n",
" \"embedding_function\": sentence_transformer_ef, # If left out SentenceTransformer(\"all-MiniLM-L6-v2\").encode will be used\n",
" },\n",
" code_execution_config=False, # set to False if you don't want to execute the code\n",
")"
@ -244,16 +249,9 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-05-23 08:48:18,875 - autogen.agentchat.contrib.retrieve_user_proxy_agent - INFO - \u001b[32mUse the existing collection `flaml_collection`.\u001b[0m\n"
]
},
{
"name": "stdout",
"output_type": "stream",
@ -265,11 +263,8 @@
"name": "stderr",
"output_type": "stream",
"text": [
"2024-05-23 08:48:19,975 - autogen.agentchat.contrib.retrieve_user_proxy_agent - INFO - Found 2 chunks.\u001b[0m\n",
"2024-05-23 08:48:19,977 - autogen.agentchat.contrib.vectordb.pgvectordb - INFO - Error executing select on non-existent table: flaml_collection. Creating it instead. Error: relation \"flaml_collection\" does not exist\n",
"LINE 1: SELECT id, metadatas, documents, embedding FROM flaml_collec...\n",
" ^\u001b[0m\n",
"2024-05-23 08:48:19,996 - autogen.agentchat.contrib.vectordb.pgvectordb - INFO - Created table flaml_collection\u001b[0m\n"
"2024-06-11 19:57:44,122 - autogen.agentchat.contrib.retrieve_user_proxy_agent - INFO - Found 2 chunks.\u001b[0m\n",
"Model gpt4-1106-preview not found. Using cl100k_base encoding.\n"
]
},
{
@ -277,7 +272,20 @@
"output_type": "stream",
"text": [
"VectorDB returns doc_ids: [['bdfbc921', '7968cf3c']]\n",
"\u001b[32mAdding content of doc bdfbc921 to context.\u001b[0m\n",
"\u001b[32mAdding content of doc bdfbc921 to context.\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Model gpt4-1106-preview not found. Using cl100k_base encoding.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32mAdding content of doc 7968cf3c to context.\u001b[0m\n",
"\u001b[33mragproxyagent\u001b[0m (to assistant):\n",
"\n",
@ -540,7 +548,6 @@
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"\u001b[32mAdding content of doc 7968cf3c to context.\u001b[0m\n",
"\u001b[33mragproxyagent\u001b[0m (to assistant):\n",
"\n",
"You're a retrieve augmented coding assistant. You answer user's questions based on your own knowledge and the\n",
@ -804,7 +811,50 @@
"--------------------------------------------------------------------------------\n",
"\u001b[33massistant\u001b[0m (to ragproxyagent):\n",
"\n",
"To use FLAML to perform a classification task and use Spark to do parallel training, you need to use the Spark ML estimators for AutoML. First, you need to prepare your data in the required format as described in the previous section. FLAML provides a convenient function \"to_pandas_on_spark\" to convert your data into a pandas-on-spark dataframe/series, which Spark estimators require. After that, use the pandas-on-spark data like non-spark data and pass them using X_train, y_train or dataframe, label. Finally, configure FLAML to use Spark as the parallel backend during parallel tuning by setting the use_spark to true. An example code snippet is provided in the context above.\n",
"Based on the provided context which details the integration of Spark with FLAML for distributed training, and the requirement to perform a classification task with parallel training in Spark, here's a code snippet that configures FLAML to train a classification model for 30 seconds and cancels the jobs if the time limit is reached.\n",
"\n",
"```python\n",
"from flaml import AutoML\n",
"from flaml.automl.spark.utils import to_pandas_on_spark\n",
"import pandas as pd\n",
"\n",
"# Your pandas DataFrame 'data' goes here\n",
"# Assuming 'data' is already a pandas DataFrame with appropriate data for classification\n",
"# and 'label_column' is the name of the column that we want to predict.\n",
"\n",
"# First, convert your pandas DataFrame to a pandas-on-spark DataFrame\n",
"psdf = to_pandas_on_spark(data)\n",
"\n",
"# Now, we prepare the settings for the AutoML training with Spark\n",
"automl_settings = {\n",
" \"time_budget\": 30, # Train for 30 seconds\n",
" \"metric\": \"accuracy\", # Assuming you want to use accuracy as the metric\n",
" \"task\": \"classification\",\n",
" \"n_concurrent_trials\": 2, # Adjust the number of concurrent trials depending on your cluster setup\n",
" \"use_spark\": True,\n",
" \"force_cancel\": True, # Force cancel jobs if time limit is reached\n",
"}\n",
"\n",
"# Create an AutoML instance\n",
"automl = AutoML()\n",
"\n",
"# Run the AutoML search\n",
"# You need to replace 'psdf' with your actual pandas-on-spark DataFrame variable\n",
"# and 'label_column' with the name of your label column\n",
"automl.fit(dataframe=psdf, label=label_column, **automl_settings)\n",
"```\n",
"\n",
"This code snippet assumes that the `data` variable contains the pandas DataFrame you want to classify and that `label_column` is the name of the target variable for the classification task. Make sure to replace 'data' and 'label_column' with your actual data and label column name before running this code.\n",
"\n",
"--------------------------------------------------------------------------------\n",
"\u001b[33mragproxyagent\u001b[0m (to assistant):\n",
"\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n",
"\u001b[33massistant\u001b[0m (to ragproxyagent):\n",
"\n",
"UPDATE CONTEXT\n",
"\n",
"--------------------------------------------------------------------------------\n"
]
@ -840,15 +890,51 @@
},
{
"cell_type": "code",
"execution_count": 6,
"execution_count": 5,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/lijiang1/anaconda3/envs/autogen/lib/python3.10/site-packages/transformers/utils/generic.py:311: UserWarning: torch.utils._pytree._register_pytree_node is deprecated. Please use torch.utils._pytree.register_pytree_node instead.\n",
" torch.utils._pytree._register_pytree_node(\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Trying to create collection.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"2024-06-11 19:58:21,076 - autogen.agentchat.contrib.retrieve_user_proxy_agent - INFO - Found 2 chunks.\u001b[0m\n",
"Model gpt4-1106-preview not found. Using cl100k_base encoding.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"VectorDB returns doc_ids: [['7968cf3c', 'bdfbc921']]\n",
"\u001b[32mAdding content of doc 7968cf3c to context.\u001b[0m\n",
"\u001b[32mAdding content of doc 7968cf3c to context.\u001b[0m\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Model gpt4-1106-preview not found. Using cl100k_base encoding.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[32mAdding content of doc bdfbc921 to context.\u001b[0m\n",
"\u001b[33mragproxyagent\u001b[0m (to assistant):\n",
"\n",
@ -1110,18 +1196,270 @@
"\n",
"\n",
"\n",
"--------------------------------------------------------------------------------\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[33massistant\u001b[0m (to ragproxyagent):\n",
"--------------------------------------------------------------------------------\n",
"\u001b[33mragproxyagent\u001b[0m (to assistant):\n",
"\n",
"You're a retrieve augmented coding assistant. You answer user's questions based on your own knowledge and the\n",
"context provided by the user.\n",
"If you can't answer the question with or without the current context, you should reply exactly `UPDATE CONTEXT`.\n",
"For code generation, you must obey the following rules:\n",
"Rule 1. You MUST NOT install any packages because all the packages needed are already installed.\n",
"Rule 2. You must follow the formats below to write your code:\n",
"```language\n",
"# your code\n",
"```\n",
"\n",
"User's question is: Who is the author of FLAML?\n",
"\n",
"Context is: # Research\n",
"\n",
"For technical details, please check our research publications.\n",
"\n",
"- [FLAML: A Fast and Lightweight AutoML Library](https://www.microsoft.com/en-us/research/publication/flaml-a-fast-and-lightweight-automl-library/). Chi Wang, Qingyun Wu, Markus Weimer, Erkang Zhu. MLSys 2021.\n",
"\n",
"```bibtex\n",
"@inproceedings{wang2021flaml,\n",
" title={FLAML: A Fast and Lightweight AutoML Library},\n",
" author={Chi Wang and Qingyun Wu and Markus Weimer and Erkang Zhu},\n",
" year={2021},\n",
" booktitle={MLSys},\n",
"}\n",
"```\n",
"\n",
"- [Frugal Optimization for Cost-related Hyperparameters](https://arxiv.org/abs/2005.01571). Qingyun Wu, Chi Wang, Silu Huang. AAAI 2021.\n",
"\n",
"```bibtex\n",
"@inproceedings{wu2021cfo,\n",
" title={Frugal Optimization for Cost-related Hyperparameters},\n",
" author={Qingyun Wu and Chi Wang and Silu Huang},\n",
" year={2021},\n",
" booktitle={AAAI},\n",
"}\n",
"```\n",
"\n",
"- [Economical Hyperparameter Optimization With Blended Search Strategy](https://www.microsoft.com/en-us/research/publication/economical-hyperparameter-optimization-with-blended-search-strategy/). Chi Wang, Qingyun Wu, Silu Huang, Amin Saied. ICLR 2021.\n",
"\n",
"```bibtex\n",
"@inproceedings{wang2021blendsearch,\n",
" title={Economical Hyperparameter Optimization With Blended Search Strategy},\n",
" author={Chi Wang and Qingyun Wu and Silu Huang and Amin Saied},\n",
" year={2021},\n",
" booktitle={ICLR},\n",
"}\n",
"```\n",
"\n",
"- [An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models](https://aclanthology.org/2021.acl-long.178.pdf). Susan Xueqing Liu, Chi Wang. ACL 2021.\n",
"\n",
"```bibtex\n",
"@inproceedings{liuwang2021hpolm,\n",
" title={An Empirical Study on Hyperparameter Optimization for Fine-Tuning Pre-trained Language Models},\n",
" author={Susan Xueqing Liu and Chi Wang},\n",
" year={2021},\n",
" booktitle={ACL},\n",
"}\n",
"```\n",
"\n",
"- [ChaCha for Online AutoML](https://www.microsoft.com/en-us/research/publication/chacha-for-online-automl/). Qingyun Wu, Chi Wang, John Langford, Paul Mineiro and Marco Rossi. ICML 2021.\n",
"\n",
"```bibtex\n",
"@inproceedings{wu2021chacha,\n",
" title={ChaCha for Online AutoML},\n",
" author={Qingyun Wu and Chi Wang and John Langford and Paul Mineiro and Marco Rossi},\n",
" year={2021},\n",
" booktitle={ICML},\n",
"}\n",
"```\n",
"\n",
"- [Fair AutoML](https://arxiv.org/abs/2111.06495). Qingyun Wu, Chi Wang. ArXiv preprint arXiv:2111.06495 (2021).\n",
"\n",
"```bibtex\n",
"@inproceedings{wuwang2021fairautoml,\n",
" title={Fair AutoML},\n",
" author={Qingyun Wu and Chi Wang},\n",
" year={2021},\n",
" booktitle={ArXiv preprint arXiv:2111.06495},\n",
"}\n",
"```\n",
"\n",
"- [Mining Robust Default Configurations for Resource-constrained AutoML](https://arxiv.org/abs/2202.09927). Moe Kayali, Chi Wang. ArXiv preprint arXiv:2202.09927 (2022).\n",
"\n",
"```bibtex\n",
"@inproceedings{kayaliwang2022default,\n",
" title={Mining Robust Default Configurations for Resource-constrained AutoML},\n",
" author={Moe Kayali and Chi Wang},\n",
" year={2022},\n",
" booktitle={ArXiv preprint arXiv:2202.09927},\n",
"}\n",
"```\n",
"\n",
"- [Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives](https://openreview.net/forum?id=0Ij9_q567Ma). Shaokun Zhang, Feiran Jia, Chi Wang, Qingyun Wu. ICLR 2023 (notable-top-5%).\n",
"\n",
"```bibtex\n",
"@inproceedings{zhang2023targeted,\n",
" title={Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives},\n",
" author={Shaokun Zhang and Feiran Jia and Chi Wang and Qingyun Wu},\n",
" booktitle={International Conference on Learning Representations},\n",
" year={2023},\n",
" url={https://openreview.net/forum?id=0Ij9_q567Ma},\n",
"}\n",
"```\n",
"\n",
"- [Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference](https://arxiv.org/abs/2303.04673). Chi Wang, Susan Xueqing Liu, Ahmed H. Awadallah. ArXiv preprint arXiv:2303.04673 (2023).\n",
"\n",
"```bibtex\n",
"@inproceedings{wang2023EcoOptiGen,\n",
" title={Cost-Effective Hyperparameter Optimization for Large Language Model Generation Inference},\n",
" author={Chi Wang and Susan Xueqing Liu and Ahmed H. Awadallah},\n",
" year={2023},\n",
" booktitle={ArXiv preprint arXiv:2303.04673},\n",
"}\n",
"```\n",
"\n",
"- [An Empirical Study on Challenging Math Problem Solving with GPT-4](https://arxiv.org/abs/2306.01337). Yiran Wu, Feiran Jia, Shaokun Zhang, Hangyu Li, Erkang Zhu, Yue Wang, Yin Tat Lee, Richard Peng, Qingyun Wu, Chi Wang. ArXiv preprint arXiv:2306.01337 (2023).\n",
"\n",
"```bibtex\n",
"@inproceedings{wu2023empirical,\n",
" title={An Empirical Study on Challenging Math Problem Solving with GPT-4},\n",
" author={Yiran Wu and Feiran Jia and Shaokun Zhang and Hangyu Li and Erkang Zhu and Yue Wang and Yin Tat Lee and Richard Peng and Qingyun Wu and Chi Wang},\n",
" year={2023},\n",
" booktitle={ArXiv preprint arXiv:2306.01337},\n",
"}\n",
"```\n",
"# Integrate - Spark\n",
"\n",
"FLAML has integrated Spark for distributed training. There are two main aspects of integration with Spark:\n",
"\n",
"- Use Spark ML estimators for AutoML.\n",
"- Use Spark to run training in parallel spark jobs.\n",
"\n",
"## Spark ML Estimators\n",
"\n",
"FLAML integrates estimators based on Spark ML models. These models are trained in parallel using Spark, so we called them Spark estimators. To use these models, you first need to organize your data in the required format.\n",
"\n",
"### Data\n",
"\n",
"For Spark estimators, AutoML only consumes Spark data. FLAML provides a convenient function `to_pandas_on_spark` in the `flaml.automl.spark.utils` module to convert your data into a pandas-on-spark (`pyspark.pandas`) dataframe/series, which Spark estimators require.\n",
"\n",
"This utility function takes data in the form of a `pandas.Dataframe` or `pyspark.sql.Dataframe` and converts it into a pandas-on-spark dataframe. It also takes `pandas.Series` or `pyspark.sql.Dataframe` and converts it into a [pandas-on-spark](https://spark.apache.org/docs/latest/api/python/user_guide/pandas_on_spark/index.html) series. If you pass in a `pyspark.pandas.Dataframe`, it will not make any changes.\n",
"\n",
"This function also accepts optional arguments `index_col` and `default_index_type`.\n",
"\n",
"- `index_col` is the column name to use as the index, default is None.\n",
"- `default_index_type` is the default index type, default is \"distributed-sequence\". More info about default index type could be found on Spark official [documentation](https://spark.apache.org/docs/latest/api/python/user_guide/pandas_on_spark/options.html#default-index-type)\n",
"\n",
"Here is an example code snippet for Spark Data:\n",
"\n",
"```python\n",
"import pandas as pd\n",
"from flaml.automl.spark.utils import to_pandas_on_spark\n",
"\n",
"# Creating a dictionary\n",
"data = {\n",
" \"Square_Feet\": [800, 1200, 1800, 1500, 850],\n",
" \"Age_Years\": [20, 15, 10, 7, 25],\n",
" \"Price\": [100000, 200000, 300000, 240000, 120000],\n",
"}\n",
"\n",
"# Creating a pandas DataFrame\n",
"dataframe = pd.DataFrame(data)\n",
"label = \"Price\"\n",
"\n",
"# Convert to pandas-on-spark dataframe\n",
"psdf = to_pandas_on_spark(dataframe)\n",
"```\n",
"\n",
"To use Spark ML models you need to format your data appropriately. Specifically, use [`VectorAssembler`](https://spark.apache.org/docs/latest/api/python/reference/api/pyspark.ml.feature.VectorAssembler.html) to merge all feature columns into a single vector column.\n",
"\n",
"Here is an example of how to use it:\n",
"\n",
"```python\n",
"from pyspark.ml.feature import VectorAssembler\n",
"\n",
"columns = psdf.columns\n",
"feature_cols = [col for col in columns if col != label]\n",
"featurizer = VectorAssembler(inputCols=feature_cols, outputCol=\"features\")\n",
"psdf = featurizer.transform(psdf.to_spark(index_col=\"index\"))[\"index\", \"features\"]\n",
"```\n",
"\n",
"Later in conducting the experiment, use your pandas-on-spark data like non-spark data and pass them using `X_train, y_train` or `dataframe, label`.\n",
"\n",
"### Estimators\n",
"\n",
"#### Model List\n",
"\n",
"- `lgbm_spark`: The class for fine-tuning Spark version LightGBM models, using [SynapseML](https://microsoft.github.io/SynapseML/docs/features/lightgbm/about/) API.\n",
"\n",
"#### Usage\n",
"\n",
"First, prepare your data in the required format as described in the previous section.\n",
"\n",
"By including the models you intend to try in the `estimators_list` argument to `flaml.automl`, FLAML will start trying configurations for these models. If your input is Spark data, FLAML will also use estimators with the `_spark` postfix by default, even if you haven't specified them.\n",
"\n",
"Here is an example code snippet using SparkML models in AutoML:\n",
"\n",
"```python\n",
"import flaml\n",
"\n",
"# prepare your data in pandas-on-spark format as we previously mentioned\n",
"\n",
"automl = flaml.AutoML()\n",
"settings = {\n",
" \"time_budget\": 30,\n",
" \"metric\": \"r2\",\n",
" \"estimator_list\": [\"lgbm_spark\"], # this setting is optional\n",
" \"task\": \"regression\",\n",
"}\n",
"\n",
"automl.fit(\n",
" dataframe=psdf,\n",
" label=label,\n",
" **settings,\n",
")\n",
"```\n",
"\n",
"[Link to notebook](https://github.com/microsoft/FLAML/blob/main/notebook/automl_bankrupt_synapseml.ipynb) | [Open in colab](https://colab.research.google.com/github/microsoft/FLAML/blob/main/notebook/automl_bankrupt_synapseml.ipynb)\n",
"\n",
"## Parallel Spark Jobs\n",
"\n",
"You can activate Spark as the parallel backend during parallel tuning in both [AutoML](/docs/Use-Cases/Task-Oriented-AutoML#parallel-tuning) and [Hyperparameter Tuning](/docs/Use-Cases/Tune-User-Defined-Function#parallel-tuning), by setting the `use_spark` to `true`. FLAML will dispatch your job to the distributed Spark backend using [`joblib-spark`](https://github.com/joblib/joblib-spark).\n",
"\n",
"Please note that you should not set `use_spark` to `true` when applying AutoML and Tuning for Spark Data. This is because only SparkML models will be used for Spark Data in AutoML and Tuning. As SparkML models run in parallel, there is no need to distribute them with `use_spark` again.\n",
"\n",
"All the Spark-related arguments are stated below. These arguments are available in both Hyperparameter Tuning and AutoML:\n",
"\n",
"- `use_spark`: boolean, default=False | Whether to use spark to run the training in parallel spark jobs. This can be used to accelerate training on large models and large datasets, but will incur more overhead in time and thus slow down training in some cases. GPU training is not supported yet when use_spark is True. For Spark clusters, by default, we will launch one trial per executor. However, sometimes we want to launch more trials than the number of executors (e.g., local mode). In this case, we can set the environment variable `FLAML_MAX_CONCURRENT` to override the detected `num_executors`. The final number of concurrent trials will be the minimum of `n_concurrent_trials` and `num_executors`.\n",
"- `n_concurrent_trials`: int, default=1 | The number of concurrent trials. When n_concurrent_trials > 1, FLAML performes parallel tuning.\n",
"- `force_cancel`: boolean, default=False | Whether to forcely cancel Spark jobs if the search time exceeded the time budget. Spark jobs include parallel tuning jobs and Spark-based model training jobs.\n",
"\n",
"An example code snippet for using parallel Spark jobs:\n",
"\n",
"```python\n",
"import flaml\n",
"\n",
"automl_experiment = flaml.AutoML()\n",
"automl_settings = {\n",
" \"time_budget\": 30,\n",
" \"metric\": \"r2\",\n",
" \"task\": \"regression\",\n",
" \"n_concurrent_trials\": 2,\n",
" \"use_spark\": True,\n",
" \"force_cancel\": True, # Activating the force_cancel option can immediately halt Spark jobs once they exceed the allocated time_budget.\n",
"}\n",
"\n",
"automl.fit(\n",
" dataframe=dataframe,\n",
" label=label,\n",
" **automl_settings,\n",
")\n",
"```\n",
"\n",
"[Link to notebook](https://github.com/microsoft/FLAML/blob/main/notebook/integrate_spark.ipynb) | [Open in colab](https://colab.research.google.com/github/microsoft/FLAML/blob/main/notebook/integrate_spark.ipynb)\n",
"\n",
"\n",
"The authors of FLAML are Chi Wang, Qingyun Wu, Markus Weimer, and Erkang Zhu.\n",
"\n",
"--------------------------------------------------------------------------------\n",
"\u001b[33massistant\u001b[0m (to ragproxyagent):\n",
"\n",
"The authors of FLAML are Chi Wang, Qingyun Wu, Markus Weimer, and Erkang Zhu.\n",
"\n",
"--------------------------------------------------------------------------------\n"
@ -1132,16 +1470,43 @@
"# reset the assistant. Always reset the assistant before starting a new conversation.\n",
"assistant.reset()\n",
"\n",
"# Optionally create psycopg conn object\n",
"conn = psycopg.connect(conninfo=\"postgresql://postgres:postgres@localhost:5432/postgres\", autocommit=True)\n",
"\n",
"ragproxyagent = RetrieveUserProxyAgent(\n",
" name=\"ragproxyagent\",\n",
" human_input_mode=\"NEVER\",\n",
" max_consecutive_auto_reply=1,\n",
" retrieve_config={\n",
" \"task\": \"code\",\n",
" \"docs_path\": [\n",
" \"https://raw.githubusercontent.com/microsoft/FLAML/main/website/docs/Examples/Integrate%20-%20Spark.md\",\n",
" \"https://raw.githubusercontent.com/microsoft/FLAML/main/website/docs/Research.md\",\n",
" os.path.join(os.path.abspath(\"\"), \"..\", \"website\", \"docs\"),\n",
" ],\n",
" \"custom_text_types\": [\"non-existent-type\"],\n",
" \"chunk_token_size\": 2000,\n",
" \"model\": config_list[0][\"model\"],\n",
" \"vector_db\": \"pgvector\", # PGVector database\n",
" \"collection_name\": \"flaml_collection\",\n",
" \"db_config\": {\n",
" # \"connection_string\": \"postgresql://postgres:postgres@localhost:5432/postgres\", # Optional - connect to an external vector database\n",
" # \"host\": \"postgres\", # Optional vector database host\n",
" # \"port\": 5432, # Optional vector database port\n",
" # \"dbname\": \"postgres\", # Optional vector database name\n",
" # \"username\": \"postgres\", # Optional vector database username\n",
" # \"password\": \"postgres\", # Optional vector database password\n",
" \"conn\": conn, # Optional - conn object to connect to database\n",
" },\n",
" \"get_or_create\": True, # set to False if you don't want to reuse an existing collection\n",
" \"overwrite\": True, # set to True if you want to overwrite an existing collection\n",
" },\n",
" code_execution_config=False, # set to False if you don't want to execute the code\n",
")\n",
"\n",
"qa_problem = \"Who is the author of FLAML?\"\n",
"chat_result = ragproxyagent.initiate_chat(assistant, message=ragproxyagent.message_generator, problem=qa_problem)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@ -1166,7 +1531,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.11.9"
"version": "3.10.13"
},
"skip_test": "Requires interactive usage"
},

2
test/agentchat/contrib/retrievechat/test_pgvector_retrievechat.py
View File

@ -56,7 +56,7 @@ def test_retrievechat():
},
)
sentence_transformer_ef = SentenceTransformer("all-MiniLM-L6-v2")
sentence_transformer_ef = SentenceTransformer("all-MiniLM-L6-v2").encode
ragproxyagent = RetrieveUserProxyAgent(
name="ragproxyagent",
human_input_mode="NEVER",