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

configs/chroma.yaml

@@ -23,4 +23,3 @@ embedder:
   provider: openai
   config:
     model: 'text-embedding-ada-002'
-    deployment_name: 'test-deployment'

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

@@ -2,15 +2,13 @@ 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
 from embedchain.embedder.openai import OpenAIEmbedder
 from embedchain.factory import EmbedderFactory, LlmFactory, VectorDBFactory
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 from embedchain.llm.openai import OpenAILlm
 from embedchain.utils import validate_yaml_config
@@ -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/bots/base.py

@@ -3,8 +3,8 @@ from typing import Any
 from embedchain import Pipeline as App
 from embedchain.config import AddConfig, BaseLlmConfig, PipelineConfig
 from embedchain.embedder.openai import OpenAIEmbedder
-from embedchain.helper.json_serializable import (JSONSerializable,
-                                                 register_deserializable)
+from embedchain.helpers.json_serializable import (JSONSerializable,
+                                                  register_deserializable)
 from embedchain.llm.openai import OpenAILlm
 from embedchain.vectordb.chroma import ChromaDB
 

embedchain/bots/discord.py

@@ -2,7 +2,7 @@ import argparse
 import logging
 import os
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base import BaseBot
 

embedchain/bots/poe.py

@@ -3,7 +3,7 @@ import logging
 import os
 from typing import List, Optional
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base import BaseBot
 

embedchain/bots/slack.py

@@ -5,7 +5,7 @@ import signal
 import sys
 
 from embedchain import App
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base import BaseBot
 

embedchain/bots/whatsapp.py

@@ -4,7 +4,7 @@ import logging
 import signal
 import sys
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base import BaseBot
 

embedchain/chunkers/base_chunker.py

@@ -1,6 +1,6 @@
 import hashlib
 
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.models.data_type import DataType
 
 

embedchain/chunkers/common_chunker.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/discourse.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/docs_site.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/docx_file.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/gmail.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/json.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/mdx.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/mysql.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/notion.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/pdf_file.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/postgres.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/qna_pair.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/sitemap.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/slack.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/substack.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/text.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/unstructured_file.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/web_page.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/xml.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/chunkers/youtube_video.py

@@ -4,7 +4,7 @@ from langchain.text_splitter import RecursiveCharacterTextSplitter
 
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config.add_config import ChunkerConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/add_config.py

@@ -3,7 +3,7 @@ from importlib import import_module
 from typing import Callable, Optional
 
 from embedchain.config.base_config import BaseConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/apps/app_config.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .base_app_config import BaseAppConfig
 

embedchain/config/apps/base_app_config.py

@@ -2,7 +2,7 @@ import logging
 from typing import Optional
 
 from embedchain.config.base_config import BaseConfig
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.vectordb.base import BaseVectorDB
 
 

embedchain/config/base_config.py

@@ -1,6 +1,6 @@
 from typing import Any, Dict
 
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 
 
 class BaseConfig(JSONSerializable):

embedchain/config/embedder/base.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/llm/base.py

@@ -1,9 +1,9 @@
 import re
 from string import Template
-from typing import Any, Dict, Optional
+from typing import Any, Dict, List, Optional
 
 from embedchain.config.base_config import BaseConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 DEFAULT_PROMPT = """
   Use the following pieces of context to answer the query at the end.
@@ -68,6 +68,7 @@ class BaseLlmConfig(BaseConfig):
         system_prompt: Optional[str] = None,
         where: Dict[str, Any] = None,
         query_type: Optional[str] = None,
+        callbacks: Optional[List] = None,
     ):
         """
         Initializes a configuration class instance for the LLM.
@@ -98,6 +99,8 @@ class BaseLlmConfig(BaseConfig):
         :type system_prompt: Optional[str], optional
         :param where: A dictionary of key-value pairs to filter the database results., defaults to None
         :type where: Dict[str, Any], optional
+        :param callbacks: Langchain callback functions to use, defaults to None
+        :type callbacks: Optional[List], optional
         :raises ValueError: If the template is not valid as template should
         contain $context and $query (and optionally $history)
         :raises ValueError: Stream is not boolean
@@ -113,6 +116,7 @@ class BaseLlmConfig(BaseConfig):
         self.deployment_name = deployment_name
         self.system_prompt = system_prompt
         self.query_type = query_type
+        self.callbacks = callbacks
 
         if type(template) is str:
             template = Template(template)

embedchain/config/pipeline_config.py

@@ -1,6 +1,6 @@
 from typing import Optional
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 from .apps.base_app_config import BaseAppConfig
 

embedchain/config/vectordb/chroma.py

@@ -1,7 +1,7 @@
 from typing import Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/elasticsearch.py

@@ -2,7 +2,7 @@ import os
 from typing import Dict, List, Optional, Union
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/opensearch.py

@@ -1,7 +1,7 @@
 from typing import Dict, Optional, Tuple
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/pinecone.py

@@ -1,7 +1,7 @@
 from typing import Dict, Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/qdrant.py

@@ -1,7 +1,7 @@
 from typing import Dict, Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/weaviate.py

@@ -1,7 +1,7 @@
 from typing import Dict, Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/config/vectordb/zilliz.py

@@ -2,7 +2,7 @@ import os
 from typing import Optional
 
 from embedchain.config.vectordb.base import BaseVectorDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 
 
 @register_deserializable

embedchain/data_formatter/data_formatter.py

@@ -4,7 +4,7 @@ from typing import Any, Dict
 from embedchain.chunkers.base_chunker import BaseChunker
 from embedchain.config import AddConfig
 from embedchain.config.add_config import ChunkerConfig, LoaderConfig
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.models.data_type import DataType
 

embedchain/embedchain.py

@@ -13,11 +13,10 @@ from embedchain.config.apps.base_app_config import BaseAppConfig
 from embedchain.constants import SQLITE_PATH
 from embedchain.data_formatter import DataFormatter
 from embedchain.embedder.base import BaseEmbedder
-from embedchain.helper.json_serializable import JSONSerializable
+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/embedder/base.py

@@ -3,12 +3,20 @@ from typing import Any, Callable, Optional
 from embedchain.config.embedder.base import BaseEmbedderConfig
 
 try:
-    from chromadb.api.types import Documents, Embeddings
+    from chromadb.api.types import Embeddable, EmbeddingFunction, Embeddings
 except RuntimeError:
     from embedchain.utils import use_pysqlite3
 
     use_pysqlite3()
-    from chromadb.api.types import Documents, Embeddings
+    from chromadb.api.types import Embeddable, EmbeddingFunction, Embeddings
+
+
+class EmbeddingFunc(EmbeddingFunction):
+    def __init__(self, embedding_fn: Callable[[list[str]], list[str]]):
+        self.embedding_fn = embedding_fn
+
+    def __call__(self, input: Embeddable) -> Embeddings:
+        return self.embedding_fn(input)
 
 
 class BaseEmbedder:
@@ -66,7 +74,4 @@ class BaseEmbedder:
         :rtype: Callable
         """
 
-        def embed_function(texts: Documents) -> Embeddings:
-            return embeddings.embed_documents(texts)
-
-        return embed_function
+        return EmbeddingFunc(embeddings.embed_documents)

embedchain/embedder/openai.py

@@ -2,7 +2,7 @@ import os
 from typing import Optional
 
 from chromadb.utils.embedding_functions import OpenAIEmbeddingFunction
-from langchain.embeddings import OpenAIEmbeddings
+from langchain.embeddings import AzureOpenAIEmbeddings
 
 from embedchain.config import BaseEmbedderConfig
 from embedchain.embedder.base import BaseEmbedder
@@ -17,7 +17,7 @@ class OpenAIEmbedder(BaseEmbedder):
             self.config.model = "text-embedding-ada-002"
 
         if self.config.deployment_name:
-            embeddings = OpenAIEmbeddings(deployment=self.config.deployment_name)
+            embeddings = AzureOpenAIEmbeddings(deployment=self.config.deployment_name)
             embedding_fn = BaseEmbedder._langchain_default_concept(embeddings)
         else:
             if os.getenv("OPENAI_API_KEY") is None and os.getenv("OPENAI_ORGANIZATION") is None:

embedchain/helpers/callbacks.py

@@ -0,0 +1,73 @@
+import queue
+from typing import Any, Dict, List, Union
+
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+from langchain.schema import LLMResult
+
+STOP_ITEM = "[END]"
+"""
+This is a special item that is used to signal the end of the stream.
+"""
+
+
+class StreamingStdOutCallbackHandlerYield(StreamingStdOutCallbackHandler):
+    """
+    This is a callback handler that yields the tokens as they are generated.
+    For a usage example, see the :func:`generate` function below.
+    """
+
+    q: queue.Queue
+    """
+    The queue to write the tokens to as they are generated.
+    """
+
+    def __init__(self, q: queue.Queue) -> None:
+        """
+        Initialize the callback handler.
+        q: The queue to write the tokens to as they are generated.
+        """
+        super().__init__()
+        self.q = q
+
+    def on_llm_start(self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any) -> None:
+        """Run when LLM starts running."""
+        with self.q.mutex:
+            self.q.queue.clear()
+
+    def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
+        """Run on new LLM token. Only available when streaming is enabled."""
+        self.q.put(token)
+
+    def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
+        """Run when LLM ends running."""
+        self.q.put(STOP_ITEM)
+
+    def on_llm_error(self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any) -> None:
+        """Run when LLM errors."""
+        self.q.put("%s: %s" % (type(error).__name__, str(error)))
+        self.q.put(STOP_ITEM)
+
+
+def generate(rq: queue.Queue):
+    """
+    This is a generator that yields the items in the queue until it reaches the stop item.
+
+    Usage example:
+    ```
+    def askQuestion(callback_fn: StreamingStdOutCallbackHandlerYield):
+        llm = OpenAI(streaming=True, callbacks=[callback_fn])
+        return llm(prompt="Write a poem about a tree.")
+
+    @app.route("/", methods=["GET"])
+    def generate_output():
+        q = Queue()
+        callback_fn = StreamingStdOutCallbackHandlerYield(q)
+        threading.Thread(target=askQuestion, args=(callback_fn,)).start()
+        return Response(generate(q), mimetype="text/event-stream")
+    ```
+    """
+    while True:
+        result: str = rq.get()
+        if result == STOP_ITEM or result is None:
+            break
+        yield result

embedchain/llm/anthropic.py

@@ -3,7 +3,7 @@ import os
 from typing import Optional
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/azure_openai.py

@@ -2,7 +2,7 @@ import logging
 from typing import Optional
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/base.py

@@ -7,7 +7,7 @@ from embedchain.config import BaseLlmConfig
 from embedchain.config.llm.base import (DEFAULT_PROMPT,
                                         DEFAULT_PROMPT_WITH_HISTORY_TEMPLATE,
                                         DOCS_SITE_PROMPT_TEMPLATE)
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 from embedchain.memory.base import ECChatMemory
 from embedchain.memory.message import ChatMessage
 

embedchain/llm/cohere.py

@@ -5,7 +5,7 @@ from typing import Optional
 from langchain.llms import Cohere
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/gpt4all.py

@@ -4,7 +4,7 @@ from langchain.callbacks.stdout import StdOutCallbackHandler
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/huggingface.py

@@ -5,7 +5,7 @@ from typing import Optional
 from langchain.llms import HuggingFaceHub
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/jina.py

@@ -5,7 +5,7 @@ from langchain.chat_models import JinaChat
 from langchain.schema import HumanMessage, SystemMessage
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/llama2.py

@@ -5,7 +5,7 @@ from typing import Optional
 from langchain.llms import Replicate
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/llm/openai.py

@@ -4,7 +4,7 @@ from langchain.chat_models import ChatOpenAI
 from langchain.schema import HumanMessage, SystemMessage
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 
@@ -34,7 +34,8 @@ class OpenAILlm(BaseLlm):
             from langchain.callbacks.streaming_stdout import \
                 StreamingStdOutCallbackHandler
 
-            chat = ChatOpenAI(**kwargs, streaming=config.stream, callbacks=[StreamingStdOutCallbackHandler()])
+            callbacks = config.callbacks if config.callbacks else [StreamingStdOutCallbackHandler()]
+            chat = ChatOpenAI(**kwargs, streaming=config.stream, callbacks=callbacks)
         else:
             chat = ChatOpenAI(**kwargs)
         return chat(messages).content

embedchain/llm/vertex_ai.py

@@ -3,7 +3,7 @@ import logging
 from typing import Optional
 
 from embedchain.config import BaseLlmConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 
 

embedchain/loaders/base_loader.py

@@ -1,4 +1,4 @@
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 
 
 class BaseLoader(JSONSerializable):

embedchain/loaders/docs_site_loader.py

@@ -12,7 +12,7 @@ except ImportError:
     ) from None
 
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/docx_file.py

@@ -6,7 +6,7 @@ except ImportError:
     raise ImportError(
         'Docx file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
     ) from None
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/local_qna_pair.py

@@ -1,6 +1,6 @@
 import hashlib
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/local_text.py

@@ -1,6 +1,6 @@
 import hashlib
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/mdx.py

@@ -1,6 +1,6 @@
 import hashlib
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 
 

embedchain/loaders/notion.py

@@ -10,7 +10,7 @@ except ImportError:
     ) from None
 
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 

embedchain/loaders/pdf_file.py

@@ -6,7 +6,7 @@ except ImportError:
     raise ImportError(
         'PDF File requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
     ) from None
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 

embedchain/loaders/sitemap.py

@@ -13,7 +13,7 @@ except ImportError:
         'Sitemap requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
     ) from None
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.loaders.web_page import WebPageLoader
 from embedchain.utils import is_readable

embedchain/loaders/substack.py

@@ -4,7 +4,7 @@ import time
 
 import requests
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import is_readable
 

embedchain/loaders/unstructured_file.py

@@ -1,6 +1,6 @@
 import hashlib
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 

embedchain/loaders/web_page.py

@@ -10,7 +10,7 @@ except ImportError:
         'Webpage requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
     ) from None
 
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 

embedchain/loaders/xml.py

@@ -6,7 +6,7 @@ except ImportError:
     raise ImportError(
         'XML file requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
     ) from None
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 

embedchain/loaders/youtube_video.py

@@ -6,7 +6,7 @@ except ImportError:
     raise ImportError(
         'YouTube video requires extra dependencies. Install with `pip install --upgrade "embedchain[dataloaders]"`'
     ) from None
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.loaders.base_loader import BaseLoader
 from embedchain.utils import clean_string
 

embedchain/memory/message.py

@@ -1,7 +1,7 @@
 import logging
 from typing import Any, Dict, Optional
 
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 
 
 class BaseMessage(JSONSerializable):

embedchain/pipeline.py

@@ -15,7 +15,7 @@ from embedchain.embedchain import EmbedChain
 from embedchain.embedder.base import BaseEmbedder
 from embedchain.embedder.openai import OpenAIEmbedder
 from embedchain.factory import EmbedderFactory, LlmFactory, VectorDBFactory
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.llm.base import BaseLlm
 from embedchain.llm.openai import OpenAILlm
 from embedchain.telemetry.posthog import AnonymousTelemetry
@@ -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__(

embedchain/vectordb/base.py

@@ -1,6 +1,6 @@
 from embedchain.config.vectordb.base import BaseVectorDbConfig
 from embedchain.embedder.base import BaseEmbedder
-from embedchain.helper.json_serializable import JSONSerializable
+from embedchain.helpers.json_serializable import JSONSerializable
 
 
 class BaseVectorDB(JSONSerializable):

embedchain/vectordb/chroma.py

@@ -6,7 +6,7 @@ from langchain.docstore.document import Document
 from tqdm import tqdm
 
 from embedchain.config import ChromaDbConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 try:

embedchain/vectordb/elasticsearch.py

@@ -10,7 +10,7 @@ except ImportError:
     ) from None
 
 from embedchain.config import ElasticsearchDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 

embedchain/vectordb/opensearch.py

@@ -16,7 +16,7 @@ from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.vectorstores import OpenSearchVectorSearch
 
 from embedchain.config import OpenSearchDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 

embedchain/vectordb/pinecone.py

@@ -9,7 +9,7 @@ except ImportError:
     ) from None
 
 from embedchain.config.vectordb.pinecone import PineconeDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 

embedchain/vectordb/weaviate.py

@@ -10,7 +10,7 @@ except ImportError:
     ) from None
 
 from embedchain.config.vectordb.weaviate import WeaviateDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 

embedchain/vectordb/zilliz.py

@@ -2,7 +2,7 @@ import logging
 from typing import Dict, List, Optional, Tuple, Union
 
 from embedchain.config import ZillizDBConfig
-from embedchain.helper.json_serializable import register_deserializable
+from embedchain.helpers.json_serializable import register_deserializable
 from embedchain.vectordb.base import BaseVectorDB
 
 try:

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "embedchain"
-version = "0.1.17"
+version = "0.1.21"
 description = "Data platform for LLMs - Load, index, retrieve and sync any unstructured data"
 authors = [
     "Taranjeet Singh <taranjeet@embedchain.ai>",

tests/apps/test_apps.py

@@ -119,7 +119,7 @@ class TestAppFromConfig:
         # Validate the Embedder config values
         embedder_config = config_data["embedder"]["config"]
         assert app.embedder.config.model == embedder_config["model"]
-        assert app.embedder.config.deployment_name == embedder_config["deployment_name"]
+        assert app.embedder.config.deployment_name == embedder_config.get("deployment_name")
 
     def test_from_opensource_config(self, mocker):
         mocker.patch("embedchain.vectordb.chroma.chromadb.Client")

tests/helper_classes/test_json_serializable.py

@@ -4,8 +4,8 @@ from string import Template
 
 from embedchain import App
 from embedchain.config import AppConfig, BaseLlmConfig
-from embedchain.helper.json_serializable import (JSONSerializable,
-                                                 register_deserializable)
+from embedchain.helpers.json_serializable import (JSONSerializable,
+                                                  register_deserializable)
 
 
 class TestJsonSerializable(unittest.TestCase):