autogen/test/agentchat/contrib/vectordb/test_pgvectordb.py

135 lines
5.1 KiB
Python
Raw Normal View History

import os
import sys
import urllib.parse
import pytest
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 06:43:02 -07:00
from conftest import reason
sys.path.append(os.path.join(os.path.dirname(__file__), ".."))
try:
import pgvector
import psycopg
import sentence_transformers
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 06:43:02 -07:00
from autogen.agentchat.contrib.vectordb.pgvectordb import PGVectorDB
except ImportError:
skip = True
else:
skip = False
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 06:43:02 -07:00
reason = "do not run on MacOS or windows OR dependency is not installed OR " + reason
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 06:43:02 -07:00
@pytest.mark.skipif(
sys.platform in ["darwin", "win32"] or skip,
reason=reason,
)
def test_pgvector():
# test db config
db_config = {
"connection_string": "postgresql://postgres:postgres@localhost:5432/postgres",
}
# test create collection with connection_string authentication
db = PGVectorDB(
connection_string=db_config["connection_string"],
)
collection_name = "test_collection"
collection = db.create_collection(collection_name=collection_name, overwrite=True, get_or_create=True)
assert collection.name == collection_name
# test create collection with conn object authentication
parsed_connection = urllib.parse.urlparse(db_config["connection_string"])
encoded_username = urllib.parse.quote(parsed_connection.username, safe="")
encoded_password = urllib.parse.quote(parsed_connection.password, safe="")
encoded_host = urllib.parse.quote(parsed_connection.hostname, safe="")
encoded_database = urllib.parse.quote(parsed_connection.path[1:], safe="")
connection_string_encoded = (
f"{parsed_connection.scheme}://{encoded_username}:{encoded_password}"
f"@{encoded_host}:{parsed_connection.port}/{encoded_database}"
)
conn = psycopg.connect(conninfo=connection_string_encoded, autocommit=True)
db = PGVectorDB(conn=conn)
collection_name = "test_collection"
collection = db.create_collection(collection_name=collection_name, overwrite=True, get_or_create=True)
assert collection.name == collection_name
# test create collection with basic authentication
db_config = {
"username": "postgres",
"password": os.environ.get("POSTGRES_PASSWORD", default="postgres"),
"host": "localhost",
"port": 5432,
"dbname": "postgres",
}
db = PGVectorDB(
username=db_config["username"],
password=db_config["password"],
port=db_config["port"],
host=db_config["host"],
dbname=db_config["dbname"],
)
collection_name = "test_collection"
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 06:43:02 -07:00
collection = db.create_collection(collection_name=collection_name, overwrite=True, get_or_create=True)
assert collection.name == collection_name
# test_delete_collection
db.delete_collection(collection_name)
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 06:43:02 -07:00
assert collection.table_exists(table_name=collection_name) is False
# test more create collection
collection = db.create_collection(collection_name, overwrite=False, get_or_create=False)
assert collection.name == collection_name
pytest.raises(ValueError, db.create_collection, collection_name, overwrite=False, get_or_create=False)
collection = db.create_collection(collection_name, overwrite=True, get_or_create=False)
assert collection.name == collection_name
collection = db.create_collection(collection_name, overwrite=False, get_or_create=True)
assert collection.name == collection_name
# test_get_collection
collection = db.get_collection(collection_name)
assert collection.name == collection_name
# test_insert_docs
docs = [{"content": "doc1", "id": "1"}, {"content": "doc2", "id": "2"}, {"content": "doc3", "id": "3"}]
db.insert_docs(docs, collection_name, upsert=False)
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 06:43:02 -07:00
res = db.get_collection(collection_name).get(ids=["1", "2"])
final_results = [result.get("content") for result in res]
assert final_results == ["doc1", "doc2"]
# test_update_docs
docs = [{"content": "doc11", "id": "1"}, {"content": "doc2", "id": "2"}, {"content": "doc3", "id": "3"}]
db.update_docs(docs, collection_name)
res = db.get_collection(collection_name).get(["1", "2"])
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 06:43:02 -07:00
final_results = [result.get("content") for result in res]
assert final_results == ["doc11", "doc2"]
# test_delete_docs
ids = ["1"]
collection_name = "test_collection"
db.delete_docs(ids, collection_name)
res = db.get_collection(collection_name).get(ids)
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 06:43:02 -07:00
final_results = [result.get("content") for result in res]
assert final_results == []
# test_retrieve_docs
queries = ["doc2", "doc3"]
collection_name = "test_collection"
res = db.retrieve_docs(queries, collection_name)
assert [[r[0]["id"] for r in rr] for rr in res] == [["2", "3"], ["3", "2"]]
res = db.retrieve_docs(queries, collection_name, distance_threshold=0.1)
assert [[r[0]["id"] for r in rr] for rr in res] == [["2"], ["3"]]
# test_get_docs_by_ids
res = db.get_docs_by_ids(["1", "2"], collection_name)
assert [r["id"] for r in res] == ["2"] # "1" has been deleted
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 06:43:02 -07:00
res = db.get_docs_by_ids(collection_name=collection_name)
assert set([r["id"] for r in res]) == set(["2", "3"]) # All Docs returned
if __name__ == "__main__":
test_pgvector()