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
[Feature/Improvements] Delete data sources from metadata db when using `app.delete()` (#1286)
Deshraj Yadav752f638cfcc8
diff --git a/embedchain/config/vectordb/pinecone.py b/embedchain/config/vectordb/pinecone.pyindex f82da24d6..f021639d5 100644--- a/embedchain/config/vectordb/pinecone.py+++ b/embedchain/config/vectordb/pinecone.py@@ -16,6 +16,7 @@ class PineconeDBConfig(BaseVectorDbConfig):pod_config: Optional[dict[str, any]] = None,serverless_config: Optional[dict[str, any]] = None,hybrid_search: bool = False,+ bm25_encoder: any = None,**extra_params: dict[str, any],):self.metric = metric@@ -24,6 +25,7 @@ class PineconeDBConfig(BaseVectorDbConfig):self.vector_dimension = vector_dimensionself.extra_params = extra_paramsself.hybrid_search = hybrid_search+ self.bm25_encoder = bm25_encoderif pod_config is None and serverless_config is None:# If no config is provided, use the default pod spec configpod_environment = os.environ.get("PINECONE_ENV", "gcp-starter")diff --git a/embedchain/embedchain.py b/embedchain/embedchain.pyindex c8e27f39a..639c3ad67 100644--- a/embedchain/embedchain.py+++ b/embedchain/embedchain.py@@ -6,17 +6,20 @@ from typing import Any, Optional, Unionfrom dotenv import load_dotenvfrom langchain.docstore.document import Document-from embedchain.cache import adapt, get_gptcache_session, gptcache_data_convert, gptcache_update_cache_callback+from embedchain.cache import (adapt, get_gptcache_session,+ gptcache_data_convert,+ gptcache_update_cache_callback)from embedchain.chunkers.base_chunker import BaseChunkerfrom embedchain.config import AddConfig, BaseLlmConfig, ChunkerConfigfrom embedchain.config.base_app_config import BaseAppConfig-from embedchain.core.db.models import DataSource+from embedchain.core.db.models import ChatHistory, DataSourcefrom embedchain.data_formatter import DataFormatterfrom embedchain.embedder.base import BaseEmbedderfrom embedchain.helpers.json_serializable import JSONSerializablefrom embedchain.llm.base import BaseLlmfrom embedchain.loaders.base_loader import BaseLoader-from embedchain.models.data_type import DataType, DirectDataType, IndirectDataType, SpecialDataType+from embedchain.models.data_type import (DataType, DirectDataType,+ IndirectDataType, SpecialDataType)from embedchain.utils.misc import detect_datatype, is_valid_json_stringfrom embedchain.vectordb.base import BaseVectorDB@@ -642,9 +645,10 @@ class EmbedChain(JSONSerializable):"""try:self.db_session.query(DataSource).filter_by(app_id=self.config.id).delete()+ self.db_session.query(ChatHistory).filter_by(app_id=self.config.id).delete()self.db_session.commit()except Exception as e:- logging.error(f"Error deleting chat history: {e}")+ logging.error(f"Error deleting data sources: {e}")self.db_session.rollback()return Noneself.db.reset()@@ -682,6 +686,13 @@ class EmbedChain(JSONSerializable)::param source_hash: The hash of the source.:type source_hash: str"""+ try:+ self.db_session.query(DataSource).filter_by(hash=source_id, app_id=self.config.id).delete()+ self.db_session.commit()+ except Exception as e:+ logging.error(f"Error deleting data sources: {e}")+ self.db_session.rollback()+ return Noneself.db.delete(where={"hash": source_id})logging.info(f"Successfully deleted {source_id}")# Send anonymous telemetrydiff --git a/embedchain/vectordb/pinecone.py b/embedchain/vectordb/pinecone.pyindex 24c030eb5..23fd64cea 100644--- a/embedchain/vectordb/pinecone.py+++ b/embedchain/vectordb/pinecone.py@@ -49,9 +49,8 @@ class PineconeDB(BaseVectorDB):# Setup BM25Encoder if sparse vectors are to be usedself.bm25_encoder = Noneif self.config.hybrid_search:- # TODO: Add support for fitting BM25Encoder on any corpuslogging.info("Initializing BM25Encoder for sparse vectors..")- self.bm25_encoder = BM25Encoder.default()+ self.bm25_encoder = self.config.bm25_encoder if self.config.bm25_encoder else BM25Encoder.default()# Call parent init here because embedder is neededsuper().__init__(config=self.config)diff --git a/pyproject.toml b/pyproject.tomlindex 9c9fb7803..f1362687d 100644--- a/pyproject.toml+++ b/pyproject.toml@@ -1,6 +1,6 @@[tool.poetry]name = "embedchain"-version = "0.1.86"+version = "0.1.87"description = "Simplest open source retrieval(RAG) framework"authors = ["Taranjeet Singh <[email protected]>",