Vector memory revamp (part 1: refactoring) (#4208)

Additional changes:

* Improve typing

* Modularize message history memory & fix/refactor lots of things

* Fix summarization

* Move memory relevance calculation to MemoryItem & improve test

* Fix import warnings in web_selenium.py

* Remove `memory_add` ghost command

* Implement overlap in `split_text`

* Move memory tests into subdirectory

* Remove deprecated `get_ada_embedding()` and helpers

* Fix used token calculation in `chat_with_ai`

* Replace Message TypedDict by dataclass

* Fix AgentManager singleton issues in tests

---------

Co-authored-by: Auto-GPT-Bot <github-bot@agpt.co>

tests/integration/memory/utils.py

@@ -0,0 +1,44 @@
+import numpy
+import pytest
+from pytest_mock import MockerFixture
+
+import autogpt.memory.vector.memory_item as vector_memory_item
+import autogpt.memory.vector.providers.base as memory_provider_base
+from autogpt.config.config import Config
+from autogpt.llm.providers.openai import OPEN_AI_EMBEDDING_MODELS
+from autogpt.memory.vector import get_memory
+from autogpt.memory.vector.utils import Embedding
+
+
+@pytest.fixture
+def embedding_dimension(config: Config):
+    return OPEN_AI_EMBEDDING_MODELS[config.embedding_model].embedding_dimensions
+
+
+@pytest.fixture
+def mock_embedding(embedding_dimension: int) -> Embedding:
+    return numpy.full((1, embedding_dimension), 0.0255, numpy.float32)[0]
+
+
+@pytest.fixture
+def mock_get_embedding(mocker: MockerFixture, embedding_dimension: int):
+    mocker.patch.object(
+        vector_memory_item,
+        "get_embedding",
+        return_value=[0.0255] * embedding_dimension,
+    )
+    mocker.patch.object(
+        memory_provider_base,
+        "get_embedding",
+        return_value=[0.0255] * embedding_dimension,
+    )
+
+
+@pytest.fixture
+def memory_none(agent_test_config: Config, mock_get_embedding):
+    was_memory_backend = agent_test_config.memory_backend
+
+    agent_test_config.set_memory_backend("no_memory")
+    yield get_memory(agent_test_config)
+
+    agent_test_config.set_memory_backend(was_memory_backend)