The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Refactoring vectordb naming convention in embedchain.config (#1469)
Vatsal Rathod83e8c9729552
diff --git a/embedchain/config/__init__.py b/embedchain/config/__init__.pyindex d0bf2a0a4..f497b2e66 100644--- a/embedchain/config/__init__.py+++ b/embedchain/config/__init__.py@@ -8,8 +8,8 @@ from .embedder.base import BaseEmbedderConfigfrom .embedder.base import BaseEmbedderConfig as EmbedderConfigfrom .embedder.ollama import OllamaEmbedderConfigfrom .llm.base import BaseLlmConfig-from .vectordb.chroma import ChromaDbConfig-from .vectordb.elasticsearch import ElasticsearchDBConfig-from .vectordb.opensearch import OpenSearchDBConfig-from .vectordb.zilliz import ZillizDBConfig+from .vector_db.chroma import ChromaDbConfig+from .vector_db.elasticsearch import ElasticsearchDBConfig+from .vector_db.opensearch import OpenSearchDBConfig+from .vector_db.zilliz import ZillizDBConfigfrom .mem0_config import Mem0Configdiff --git a/embedchain/config/vectordb/base.py b/embedchain/config/vector_db/base.pysimilarity index 100%rename from embedchain/config/vectordb/base.pyrename to embedchain/config/vector_db/base.pydiff --git a/embedchain/config/vectordb/chroma.py b/embedchain/config/vector_db/chroma.pysimilarity index 96%rename from embedchain/config/vectordb/chroma.pyrename to embedchain/config/vector_db/chroma.pyindex b99f1d942..64220165c 100644--- a/embedchain/config/vectordb/chroma.py+++ b/embedchain/config/vector_db/chroma.py@@ -1,6 +1,6 @@from typing import Optional-from embedchain.config.vectordb.base import BaseVectorDbConfig+from embedchain.config.vector_db.base import BaseVectorDbConfigfrom embedchain.helpers.json_serializable import register_deserializablediff --git a/embedchain/config/vectordb/elasticsearch.py b/embedchain/config/vector_db/elasticsearch.pysimilarity index 95%rename from embedchain/config/vectordb/elasticsearch.pyrename to embedchain/config/vector_db/elasticsearch.pyindex 1679700af..5e8ef6b61 100644--- a/embedchain/config/vectordb/elasticsearch.py+++ b/embedchain/config/vector_db/elasticsearch.py@@ -1,56 +1,56 @@-import os-from typing import Optional, Union--from embedchain.config.vectordb.base import BaseVectorDbConfig-from embedchain.helpers.json_serializable import register_deserializable---@register_deserializable-class ElasticsearchDBConfig(BaseVectorDbConfig):- def __init__(- self,- collection_name: Optional[str] = None,- dir: Optional[str] = None,- es_url: Union[str, list[str]] = None,- cloud_id: Optional[str] = None,- batch_size: Optional[int] = 100,- **ES_EXTRA_PARAMS: dict[str, any],- ):- """- Initializes a configuration class instance for an Elasticsearch client.-- :param collection_name: Default name for the collection, defaults to None- :type collection_name: Optional[str], optional- :param dir: Path to the database directory, where the database is stored, defaults to None- :type dir: Optional[str], optional- :param es_url: elasticsearch url or list of nodes url to be used for connection, defaults to None- :type es_url: Union[str, list[str]], optional- :param cloud_id: cloud id of the elasticsearch cluster, defaults to None- :type cloud_id: Optional[str], optional- :param batch_size: Number of items to insert in one batch, defaults to 100- :type batch_size: Optional[int], optional- :param ES_EXTRA_PARAMS: extra params dict that can be passed to elasticsearch.- :type ES_EXTRA_PARAMS: dict[str, Any], optional- """- if es_url and cloud_id:- raise ValueError("Only one of `es_url` and `cloud_id` can be set.")- # self, es_url: Union[str, list[str]] = None, **ES_EXTRA_PARAMS: dict[str, any]):- self.ES_URL = es_url or os.environ.get("ELASTICSEARCH_URL")- self.CLOUD_ID = cloud_id or os.environ.get("ELASTICSEARCH_CLOUD_ID")- if not self.ES_URL and not self.CLOUD_ID:- raise AttributeError(- "Elasticsearch needs a URL or CLOUD_ID attribute, "- "this can either be passed to `ElasticsearchDBConfig` or as `ELASTICSEARCH_URL` or `ELASTICSEARCH_CLOUD_ID` in `.env`" # noqa: E501- )- self.ES_EXTRA_PARAMS = ES_EXTRA_PARAMS- # Load API key from .env if it's not explicitly passed.- # Can only set one of 'api_key', 'basic_auth', and 'bearer_auth'- if (- not self.ES_EXTRA_PARAMS.get("api_key")- and not self.ES_EXTRA_PARAMS.get("basic_auth")- and not self.ES_EXTRA_PARAMS.get("bearer_auth")- ):- self.ES_EXTRA_PARAMS["api_key"] = os.environ.get("ELASTICSEARCH_API_KEY")-- self.batch_size = batch_size- super().__init__(collection_name=collection_name, dir=dir)+import os+from typing import Optional, Union++from embedchain.config.vector_db.base import BaseVectorDbConfig+from embedchain.helpers.json_serializable import register_deserializable+++@register_deserializable+class ElasticsearchDBConfig(BaseVectorDbConfig):+ def __init__(+ self,+ collection_name: Optional[str] = None,+ dir: Optional[str] = None,+ es_url: Union[str, list[str]] = None,+ cloud_id: Optional[str] = None,+ batch_size: Optional[int] = 100,+ **ES_EXTRA_PARAMS: dict[str, any],+ ):+ """+ Initializes a configuration class instance for an Elasticsearch client.++ :param collection_name: Default name for the collection, defaults to None+ :type collection_name: Optional[str], optional+ :param dir: Path to the database directory, where the database is stored, defaults to None+ :type dir: Optional[str], optional+ :param es_url: elasticsearch url or list of nodes url to be used for connection, defaults to None+ :type es_url: Union[str, list[str]], optional+ :param cloud_id: cloud id of the elasticsearch cluster, defaults to None+ :type cloud_id: Optional[str], optional+ :param batch_size: Number of items to insert in one batch, defaults to 100+ :type batch_size: Optional[int], optional+ :param ES_EXTRA_PARAMS: extra params dict that can be passed to elasticsearch.+ :type ES_EXTRA_PARAMS: dict[str, Any], optional+ """+ if es_url and cloud_id:+ raise ValueError("Only one of `es_url` and `cloud_id` can be set.")+ # self, es_url: Union[str, list[str]] = None, **ES_EXTRA_PARAMS: dict[str, any]):+ self.ES_URL = es_url or os.environ.get("ELASTICSEARCH_URL")+ self.CLOUD_ID = cloud_id or os.environ.get("ELASTICSEARCH_CLOUD_ID")+ if not self.ES_URL and not self.CLOUD_ID:+ raise AttributeError(+ "Elasticsearch needs a URL or CLOUD_ID attribute, "+ "this can either be passed to `ElasticsearchDBConfig` or as `ELASTICSEARCH_URL` or `ELASTICSEARCH_CLOUD_ID` in `.env`" # noqa: E501+ )+ self.ES_EXTRA_PARAMS = ES_EXTRA_PARAMS+ # Load API key from .env if it's not explicitly passed.+ # Can only set one of 'api_key', 'basic_auth', and 'bearer_auth'+ if (+ not self.ES_EXTRA_PARAMS.get("api_key")+ and not self.ES_EXTRA_PARAMS.get("basic_auth")+ and not self.ES_EXTRA_PARAMS.get("bearer_auth")+ ):+ self.ES_EXTRA_PARAMS["api_key"] = os.environ.get("ELASTICSEARCH_API_KEY")++ self.batch_size = batch_size+ super().__init__(collection_name=collection_name, dir=dir)diff --git a/embedchain/config/vectordb/lancedb.py b/embedchain/config/vector_db/lancedb.pysimilarity index 95%rename from embedchain/config/vectordb/lancedb.pyrename to embedchain/config/vector_db/lancedb.pyindex 2e53ccdab..08b7d0ac7 100644--- a/embedchain/config/vectordb/lancedb.py+++ b/embedchain/config/vector_db/lancedb.py@@ -1,6 +1,6 @@from typing import Optional-from embedchain.config.vectordb.base import BaseVectorDbConfig+from embedchain.config.vector_db.base import BaseVectorDbConfigfrom embedchain.helpers.json_serializable import register_deserializablediff --git a/embedchain/config/vectordb/opensearch.py b/embedchain/config/vector_db/opensearch.pysimilarity index 94%rename from embedchain/config/vectordb/opensearch.pyrename to embedchain/config/vector_db/opensearch.pyindex 3d0b60995..5beeb8cee 100644--- a/embedchain/config/vectordb/opensearch.py+++ b/embedchain/config/vector_db/opensearch.py@@ -1,41 +1,41 @@-from typing import Optional--from embedchain.config.vectordb.base import BaseVectorDbConfig-from embedchain.helpers.json_serializable import register_deserializable---@register_deserializable-class OpenSearchDBConfig(BaseVectorDbConfig):- def __init__(- self,- opensearch_url: str,- http_auth: tuple[str, str],- vector_dimension: int = 1536,- collection_name: Optional[str] = None,- dir: Optional[str] = None,- batch_size: Optional[int] = 100,- **extra_params: dict[str, any],- ):- """- Initializes a configuration class instance for an OpenSearch client.-- :param collection_name: Default name for the collection, defaults to None- :type collection_name: Optional[str], optional- :param opensearch_url: URL of the OpenSearch domain- :type opensearch_url: str, Eg, "http://localhost:9200"- :param http_auth: Tuple of username and password- :type http_auth: tuple[str, str], Eg, ("username", "password")- :param vector_dimension: Dimension of the vector, defaults to 1536 (openai embedding model)- :type vector_dimension: int, optional- :param dir: Path to the database directory, where the database is stored, defaults to None- :type dir: Optional[str], optional- :param batch_size: Number of items to insert in one batch, defaults to 100- :type batch_size: Optional[int], optional- """- self.opensearch_url = opensearch_url- self.http_auth = http_auth- self.vector_dimension = vector_dimension- self.extra_params = extra_params- self.batch_size = batch_size-- super().__init__(collection_name=collection_name, dir=dir)+from typing import Optional++from embedchain.config.vector_db.base import BaseVectorDbConfig+from embedchain.helpers.json_serializable import register_deserializable+++@register_deserializable+class OpenSearchDBConfig(BaseVectorDbConfig):+ def __init__(+ self,+ opensearch_url: str,+ http_auth: tuple[str, str],+ vector_dimension: int = 1536,+ collection_name: Optional[str] = None,+ dir: Optional[str] = None,+ batch_size: Optional[int] = 100,+ **extra_params: dict[str, any],+ ):+ """+ Initializes a configuration class instance for an OpenSearch client.++ :param collection_name: Default name for the collection, defaults to None+ :type collection_name: Optional[str], optional+ :param opensearch_url: URL of the OpenSearch domain+ :type opensearch_url: str, Eg, "http://localhost:9200"+ :param http_auth: Tuple of username and password+ :type http_auth: tuple[str, str], Eg, ("username", "password")+ :param vector_dimension: Dimension of the vector, defaults to 1536 (openai embedding model)+ :type vector_dimension: int, optional+ :param dir: Path to the database directory, where the database is stored, defaults to None+ :type dir: Optional[str], optional+ :param batch_size: Number of items to insert in one batch, defaults to 100+ :type batch_size: Optional[int], optional+ """+ self.opensearch_url = opensearch_url+ self.http_auth = http_auth+ self.vector_dimension = vector_dimension+ self.extra_params = extra_params+ self.batch_size = batch_size++ super().__init__(collection_name=collection_name, dir=dir)diff --git a/embedchain/config/vectordb/pinecone.py b/embedchain/config/vector_db/pinecone.pysimilarity index 96%rename from embedchain/config/vectordb/pinecone.pyrename to embedchain/config/vector_db/pinecone.pyindex 4eb66f214..83248579f 100644--- a/embedchain/config/vectordb/pinecone.py+++ b/embedchain/config/vector_db/pinecone.py@@ -1,7 +1,7 @@import osfrom typing import Optional-from embedchain.config.vectordb.base import BaseVectorDbConfig+from embedchain.config.vector_db.base import BaseVectorDbConfigfrom embedchain.helpers.json_serializable import register_deserializablediff --git a/embedchain/config/vectordb/qdrant.py b/embedchain/config/vector_db/qdrant.pysimilarity index 97%rename from embedchain/config/vectordb/qdrant.pyrename to embedchain/config/vector_db/qdrant.pyindex 2520226a4..acdeacfff 100644--- a/embedchain/config/vectordb/qdrant.py+++ b/embedchain/config/vector_db/qdrant.py@@ -1,6 +1,6 @@from typing import Optional-from embedchain.config.vectordb.base import BaseVectorDbConfig+from embedchain.config.vector_db.base import BaseVectorDbConfigfrom embedchain.helpers.json_serializable import register_deserializablediff --git a/embedchain/config/vectordb/weaviate.py b/embedchain/config/vector_db/weaviate.pysimilarity index 89%rename from embedchain/config/vectordb/weaviate.pyrename to embedchain/config/vector_db/weaviate.pyindex 8277e88fc..f40c472e7 100644--- a/embedchain/config/vectordb/weaviate.py+++ b/embedchain/config/vector_db/weaviate.py@@ -1,6 +1,6 @@from typing import Optional-from embedchain.config.vectordb.base import BaseVectorDbConfig+from embedchain.config.vector_db.base import BaseVectorDbConfigfrom embedchain.helpers.json_serializable import register_deserializablediff --git a/embedchain/config/vectordb/zilliz.py b/embedchain/config/vector_db/zilliz.pysimilarity index 96%rename from embedchain/config/vectordb/zilliz.pyrename to embedchain/config/vector_db/zilliz.pyindex 25c3c957a..268941157 100644--- a/embedchain/config/vectordb/zilliz.py+++ b/embedchain/config/vector_db/zilliz.py@@ -1,7 +1,7 @@import osfrom typing import Optional-from embedchain.config.vectordb.base import BaseVectorDbConfig+from embedchain.config.vector_db.base import BaseVectorDbConfigfrom embedchain.helpers.json_serializable import register_deserializablediff --git a/embedchain/factory.py b/embedchain/factory.pyindex db07e3777..dd402f631 100644--- a/embedchain/factory.py+++ b/embedchain/factory.py@@ -98,14 +98,14 @@ class VectorDBFactory:"zilliz": "embedchain.vectordb.zilliz.ZillizVectorDB",}provider_to_config_class = {- "chroma": "embedchain.config.vectordb.chroma.ChromaDbConfig",- "elasticsearch": "embedchain.config.vectordb.elasticsearch.ElasticsearchDBConfig",- "opensearch": "embedchain.config.vectordb.opensearch.OpenSearchDBConfig",- "lancedb": "embedchain.config.vectordb.lancedb.LanceDBConfig",- "pinecone": "embedchain.config.vectordb.pinecone.PineconeDBConfig",- "qdrant": "embedchain.config.vectordb.qdrant.QdrantDBConfig",- "weaviate": "embedchain.config.vectordb.weaviate.WeaviateDBConfig",- "zilliz": "embedchain.config.vectordb.zilliz.ZillizDBConfig",+ "chroma": "embedchain.config.vector_db.chroma.ChromaDbConfig",+ "elasticsearch": "embedchain.config.vector_db.elasticsearch.ElasticsearchDBConfig",+ "opensearch": "embedchain.config.vector_db.opensearch.OpenSearchDBConfig",+ "lancedb": "embedchain.config.vector_db.lancedb.LanceDBConfig",+ "pinecone": "embedchain.config.vector_db.pinecone.PineconeDBConfig",+ "qdrant": "embedchain.config.vector_db.qdrant.QdrantDBConfig",+ "weaviate": "embedchain.config.vector_db.weaviate.WeaviateDBConfig",+ "zilliz": "embedchain.config.vector_db.zilliz.ZillizDBConfig",}@classmethoddiff --git a/embedchain/vectordb/base.py b/embedchain/vectordb/base.pyindex a31cf1002..e65cde01a 100644--- a/embedchain/vectordb/base.py+++ b/embedchain/vectordb/base.py@@ -1,4 +1,4 @@-from embedchain.config.vectordb.base import BaseVectorDbConfig+from embedchain.config.vector_db.base import BaseVectorDbConfigfrom embedchain.embedder.base import BaseEmbedderfrom embedchain.helpers.json_serializable import JSONSerializablediff --git a/embedchain/vectordb/lancedb.py b/embedchain/vectordb/lancedb.pyindex 3179eb5c3..d3d4b6898 100644--- a/embedchain/vectordb/lancedb.py+++ b/embedchain/vectordb/lancedb.py@@ -7,7 +7,7 @@ try:except ImportError:raise ImportError('LanceDB is required. Install with pip install "embedchain[lancedb]"') from None-from embedchain.config.vectordb.lancedb import LanceDBConfig+from embedchain.config.vector_db.lancedb import LanceDBConfigfrom embedchain.helpers.json_serializable import register_deserializablefrom embedchain.vectordb.base import BaseVectorDBdiff --git a/embedchain/vectordb/pinecone.py b/embedchain/vectordb/pinecone.pyindex c89dbcdab..3c0520ce3 100644--- a/embedchain/vectordb/pinecone.py+++ b/embedchain/vectordb/pinecone.py@@ -11,7 +11,7 @@ except ImportError:from pinecone_text.sparse import BM25Encoder-from embedchain.config.vectordb.pinecone import PineconeDBConfig+from embedchain.config.vector_db.pinecone import PineconeDBConfigfrom embedchain.helpers.json_serializable import register_deserializablefrom embedchain.utils.misc import chunksfrom embedchain.vectordb.base import BaseVectorDBdiff --git a/embedchain/vectordb/qdrant.py b/embedchain/vectordb/qdrant.pyindex d9b050206..cdac19cfa 100644--- a/embedchain/vectordb/qdrant.py+++ b/embedchain/vectordb/qdrant.py@@ -12,7 +12,7 @@ except ImportError:from tqdm import tqdm-from embedchain.config.vectordb.qdrant import QdrantDBConfig+from embedchain.config.vector_db.qdrant import QdrantDBConfigfrom embedchain.vectordb.base import BaseVectorDBdiff --git a/embedchain/vectordb/weaviate.py b/embedchain/vectordb/weaviate.pyindex f46324364..897412a64 100644--- a/embedchain/vectordb/weaviate.py+++ b/embedchain/vectordb/weaviate.py@@ -9,7 +9,7 @@ except ImportError:"Weaviate requires extra dependencies. Install with `pip install --upgrade 'embedchain[weaviate]'`") from None-from embedchain.config.vectordb.weaviate import WeaviateDBConfig+from embedchain.config.vector_db.weaviate import WeaviateDBConfigfrom embedchain.helpers.json_serializable import register_deserializablefrom embedchain.vectordb.base import BaseVectorDBdiff --git a/tests/vectordb/test_lancedb.py b/tests/vectordb/test_lancedb.pyindex f50660bb9..91885bdd5 100644--- a/tests/vectordb/test_lancedb.py+++ b/tests/vectordb/test_lancedb.py@@ -5,7 +5,7 @@ import pytestfrom embedchain import Appfrom embedchain.config import AppConfig-from embedchain.config.vectordb.lancedb import LanceDBConfig+from embedchain.config.vector_db.lancedb import LanceDBConfigfrom embedchain.vectordb.lancedb import LanceDBos.environ["OPENAI_API_KEY"] = "test-api-key"diff --git a/tests/vectordb/test_pinecone.py b/tests/vectordb/test_pinecone.pyindex 472b05930..00051ed94 100644--- a/tests/vectordb/test_pinecone.py+++ b/tests/vectordb/test_pinecone.py@@ -1,6 +1,6 @@import pytest-from embedchain.config.vectordb.pinecone import PineconeDBConfig+from embedchain.config.vector_db.pinecone import PineconeDBConfigfrom embedchain.vectordb.pinecone import PineconeDBdiff --git a/tests/vectordb/test_qdrant.py b/tests/vectordb/test_qdrant.pyindex 473269521..b2b3dfa07 100644--- a/tests/vectordb/test_qdrant.py+++ b/tests/vectordb/test_qdrant.py@@ -7,7 +7,7 @@ from qdrant_client.http.models import Batchfrom embedchain import Appfrom embedchain.config import AppConfig-from embedchain.config.vectordb.pinecone import PineconeDBConfig+from embedchain.config.vector_db.pinecone import PineconeDBConfigfrom embedchain.embedder.base import BaseEmbedderfrom embedchain.vectordb.qdrant import QdrantDBdiff --git a/tests/vectordb/test_weaviate.py b/tests/vectordb/test_weaviate.pyindex b263579fd..a51870d44 100644--- a/tests/vectordb/test_weaviate.py+++ b/tests/vectordb/test_weaviate.py@@ -3,7 +3,7 @@ from unittest.mock import patchfrom embedchain import Appfrom embedchain.config import AppConfig-from embedchain.config.vectordb.pinecone import PineconeDBConfig+from embedchain.config.vector_db.pinecone import PineconeDBConfigfrom embedchain.embedder.base import BaseEmbedderfrom embedchain.vectordb.weaviate import WeaviateDB