autogen/test/agentchat/contrib/retrievechat/test_retrievechat.py
Audel Rouhi 1b8d65df0a
2447 fix pgvector tests and notebook (#2455)
* Re-added missing notebook

* Test installing postgres

* Error handle the connection.

* Fixed import.

* Fixed import.

* Fixed creation of collection without client.

* PGVector portion working. OpenAI untested.

* Fixed prints.

* Added output.

* Fixed pre-commits.

* Run pgvector notebook

* Improve efficiency of get_collection

* Fix delete_collection

* Fixed issues with pytests and validated functions.

* Validated pytests.

* Fixed pre-commits

* Separated extra_requires to allow more logic. Retrieve_chat base dependencies included on pgvector and qdrant.

* Fixed extra newline.

* Added username and password fields.

* URL Encode the connection string parameters to support symbols like %

* Fixed pre-commits.

* Added pgvector service

* pgvector doesn't have health intervals.

* Switched to colon based key values.

* Run on Ubuntu only. Linux is only option with container service support.

* Using default credentials instead.

* Fix postgres setup

* Fix postgres setup

* Don't skip tests on win and mac

* Fix command error

* Try apt install postgresql

* Assert table does not exist when deleted.

* Raise value error on a empty list or None value provided for IDs

* pre-commit

* Add install pgvector

* Add install pgvector

* Reorg test files, create a separate job for test pgvector

* Fix format

* Fix env format

* Simplify job name, enable test_retrieve_config

* Fix test_retrieve_config

* Corrected behavior for get_docs_by_ids with no ids returning all docs.

* Corrected behavior for get_docs_by_ids with no ids returning all docs.

* Fixed pre-commits.

* Added return values for all functions.

* Validated distance search is implemented correctly.

* Validated all pytests

* Removed print.

* Added default clause.

* Make ids optional

* Fix test, make it more robust

* Bump version of openai for the vector_store support

* Added support for choosing the sentence transformer model.

* Added error handling for model name entered.

* Updated model info.

* Added model_name db_config param.

* pre-commit fixes and last link fix.

* Use secrets password.

* fix: link fixed

* updated tests

* Updated config_list.

* pre-commit fix.

* Added chat_result to all output.
Unable to re-run notebooks.

* Pre-commit fix detected this requirement.

* Fix python 3.8 and 3.9 not supported for macos

* Fix python 3.8 and 3.9 not supported for macos

* Fix format

* Reran notebook with MetaLlama3Instruct7BQ4_k_M

* added gpt model.

* Reran notebook

---------

Co-authored-by: Li Jiang <bnujli@gmail.com>
Co-authored-by: Hk669 <hrushi669@gmail.com>
2024-04-28 13:43:02 +00:00

104 lines
2.8 KiB
Python
Executable File

#!/usr/bin/env python3 -m pytest
import os
import sys
import pytest
import autogen
sys.path.append(os.path.join(os.path.dirname(__file__), "../../.."))
from conftest import reason, skip_openai # noqa: E402
sys.path.append(os.path.join(os.path.dirname(__file__), "../.."))
from test_assistant_agent import KEY_LOC, OAI_CONFIG_LIST # noqa: E402
try:
import chromadb
import openai
from chromadb.utils import embedding_functions as ef
from autogen.agentchat.contrib.retrieve_assistant_agent import (
RetrieveAssistantAgent,
)
from autogen.agentchat.contrib.retrieve_user_proxy_agent import (
RetrieveUserProxyAgent,
)
except ImportError:
skip = True
else:
skip = False
reason = "do not run on MacOS or windows OR dependency is not installed OR " + reason
@pytest.mark.skipif(
sys.platform in ["darwin", "win32"] or skip or skip_openai,
reason=reason,
)
def test_retrievechat():
conversations = {}
# autogen.ChatCompletion.start_logging(conversations) # deprecated in v0.2
config_list = autogen.config_list_from_json(
OAI_CONFIG_LIST,
file_location=KEY_LOC,
)
assistant = RetrieveAssistantAgent(
name="assistant",
system_message="You are a helpful assistant.",
llm_config={
"timeout": 600,
"seed": 42,
"config_list": config_list,
},
)
sentence_transformer_ef = ef.SentenceTransformerEmbeddingFunction()
ragproxyagent = RetrieveUserProxyAgent(
name="ragproxyagent",
human_input_mode="NEVER",
max_consecutive_auto_reply=2,
retrieve_config={
"docs_path": "./website/docs",
"chunk_token_size": 2000,
"model": config_list[0]["model"],
"client": chromadb.PersistentClient(path="/tmp/chromadb"),
"embedding_function": sentence_transformer_ef,
"get_or_create": True,
},
)
assistant.reset()
code_problem = "How can I use FLAML to perform a classification task, set use_spark=True, train 30 seconds and force cancel jobs if time limit is reached."
ragproxyagent.initiate_chat(
assistant, message=ragproxyagent.message_generator, problem=code_problem, search_string="spark", silent=True
)
print(conversations)
@pytest.mark.skipif(
sys.platform in ["darwin", "win32"] or skip,
reason=reason,
)
def test_retrieve_config():
# test warning message when no docs_path is provided
ragproxyagent = RetrieveUserProxyAgent(
name="ragproxyagent",
human_input_mode="NEVER",
max_consecutive_auto_reply=2,
retrieve_config={
"chunk_token_size": 2000,
"get_or_create": True,
},
)
assert ragproxyagent._docs_path is None
if __name__ == "__main__":
# test_retrievechat()
test_retrieve_config()