[Bug fix] Fix issue of missing user directory (#975)

docs/components/embedding-models.mdx

@@ -55,8 +55,8 @@ import os
 from embedchain import Pipeline as App
 
 os.environ["OPENAI_API_TYPE"] = "azure"
-os.environ["OPENAI_API_BASE"] = "https://xxx.openai.azure.com/"
-os.environ["OPENAI_API_KEY"] = "xxx"
+os.environ["AZURE_OPENAI_ENDPOINT"] = "https://xxx.openai.azure.com/"
+os.environ["AZURE_OPENAI_API_KEY"] = "xxx"
 os.environ["OPENAI_API_VERSION"] = "xxx"
 
 app = App.from_config(yaml_path="config.yaml")

embedchain/__init__.py

@@ -6,3 +6,6 @@ from embedchain.apps.app import App  # noqa: F401
 from embedchain.client import Client  # noqa: F401
 from embedchain.pipeline import Pipeline  # noqa: F401
 from embedchain.vectordb.chroma import ChromaDB  # noqa: F401
+
+# Setup the user directory if doesn't exist already
+Client.setup_dir()

embedchain/apps/app.py

@@ -2,9 +2,7 @@ from typing import Optional
 
 import yaml
 
-from embedchain.client import Client
-from embedchain.config import (AppConfig, BaseEmbedderConfig, BaseLlmConfig,
-                               ChunkerConfig)
+from embedchain.config import AppConfig, BaseEmbedderConfig, BaseLlmConfig, ChunkerConfig
 from embedchain.config.vectordb.base import BaseVectorDbConfig
 from embedchain.embedchain import EmbedChain
 from embedchain.embedder.base import BaseEmbedder
@@ -68,9 +66,6 @@ class App(EmbedChain):
         :type system_prompt: Optional[str], optional
         :raises TypeError: LLM, database or embedder or their config is not a valid class instance.
         """
-        # Setup user directory if it doesn't exist already
-        Client.setup_dir()
-
         # Type check configs
         if config and not isinstance(config, AppConfig):
             raise TypeError(
@@ -134,9 +129,6 @@ class App(EmbedChain):
         :return: An instance of the App class.
         :rtype: App
         """
-        # Setup user directory if it doesn't exist already
-        Client.setup_dir()
-
         with open(yaml_path, "r") as file:
             config_data = yaml.safe_load(file)
 

embedchain/embedchain.py

@@ -16,8 +16,7 @@ from embedchain.embedder.base import BaseEmbedder
 from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.llm.base import BaseLlm
 from 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.telemetry.posthog import AnonymousTelemetry
 from embedchain.utils import detect_datatype, is_valid_json_string
 from embedchain.vectordb.base import BaseVectorDB

embedchain/pipeline.py

@@ -24,6 +24,10 @@ from embedchain.vectordb.base import BaseVectorDB
 from embedchain.vectordb.chroma import ChromaDB
 
 
+# Setup the user directory if doesn't exist already
+Client.setup_dir()
+
+
 @register_deserializable
 class Pipeline(EmbedChain):
     """
@@ -64,9 +68,6 @@ class Pipeline(EmbedChain):
         :type auto_deploy: bool, optional
         :raises Exception: If an error occurs while creating the pipeline
         """
-        # Setup user directory if it doesn't exist already
-        Client.setup_dir()
-
         if id and yaml_path:
             raise Exception("Cannot provide both id and config. Please provide only one of them.")
 
@@ -357,9 +358,6 @@ class Pipeline(EmbedChain):
         :return: An instance of the Pipeline class.
         :rtype: Pipeline
         """
-        # Setup user directory if it doesn't exist already
-        Client.setup_dir()
-
         with open(yaml_path, "r") as file:
             config_data = yaml.safe_load(file)
 

embedchain/store/assistants.py

@@ -10,7 +10,7 @@ from typing import cast
 from openai import OpenAI
 from openai.types.beta.threads import MessageContentText, ThreadMessage
 
-from embedchain import Pipeline
+from embedchain import Client, Pipeline
 from embedchain.config import AddConfig
 from embedchain.data_formatter import DataFormatter
 from embedchain.models.data_type import DataType
@@ -19,6 +19,9 @@ from embedchain.utils import detect_datatype
 
 logging.basicConfig(level=logging.WARN)
 
+# Setup the user directory if doesn't exist already
+Client.setup_dir()
+
 
 class OpenAIAssistant:
     def __init__(

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "embedchain"
-version = "0.1.20"
+version = "0.1.21"
 description = "Data platform for LLMs - Load, index, retrieve and sync any unstructured data"
 authors = [
     "Taranjeet Singh <taranjeet@embedchain.ai>",