resolved merge conflict

embedchain/data_format/data_format.py

@@ -3,13 +3,19 @@
 from embedchain.loaders.web_page import WebPageLoader
 from embedchain.loaders.local_qna_pair import LocalQnaPairLoader
 from embedchain.loaders.local_text import LocalTextLoader
+from embedchain.loaders.docx_file import DocxFileLoader
 from embedchain.chunkers.youtube_video import YoutubeVideoChunker
 from embedchain.chunkers.pdf_file import PdfFileChunker
 from embedchain.chunkers.web_page import WebPageChunker
 from embedchain.chunkers.qna_pair import QnaPairChunker
 from embedchain.chunkers.text import TextChunker
+from embedchain.chunkers.docx_file import DocxFileChunker
+
 
 class DataFormat:
+ """
+ DataFormat is an internal utility class which abstracts the mapping for
+ """
  def __init__(self, data_type):
  self.loader = self._get_loader(data_type)
  self.chunker = self._get_chunker(data_type)
@@ -28,6 +34,7 @@ def _get_loader(self, data_type):
  'web_page': WebPageLoader(),
  'qna_pair': LocalQnaPairLoader(),
  'text': LocalTextLoader(),
+ 'docx': DocxFileLoader(),
  }
  if data_type in loaders:
  return loaders[data_type]
@@ -48,8 +55,10 @@ def _get_chunker(self, data_type):
  'web_page': WebPageChunker(),
  'qna_pair': QnaPairChunker(),
  'text': TextChunker(),
+ 'docx': DocxFileChunker(),
  }
  if data_type in chunkers:
  return chunkers[data_type]
  else:
  raise ValueError(f"Unsupported data type: {data_type}")
+

embedchain/embedchain.py

@@ -5,15 +5,11 @@
 from chromadb.utils import embedding_functions
 from dotenv import load_dotenv
 from langchain.docstore.document import Document
-from langchain.embeddings.openai import OpenAIEmbeddings
 from langchain.memory import ConversationBufferMemory
 from embedchain.config import InitConfig, AddConfig, QueryConfig, ChatConfig
 from embedchain.config.QueryConfig import DEFAULT_PROMPT
-
-from embedchain.vectordb.chroma_db import ChromaDB
 from embedchain.data_format import DataFormat
 
-
 gpt4all_model = None
 
 load_dotenv()
@@ -38,7 +34,10 @@ def __init__(self, config: InitConfig):
  self.collection = self.config.db.collection
  self.user_asks = []
 
- def add(self, data_type, url):
+
+
+
+ def add(self, data_type, url, config: AddConfig = None):
  """
  Adds the data from the given URL to the vector db.
  Loads the data, chunks it, create embedding for each chunk
@@ -48,6 +47,9 @@ def add(self, data_type, url):
  :param url: The URL where the data is located.
  :param config: Optional. The `AddConfig` instance to use as configuration options.
  """
+ if config is None:
+ config = AddConfig()
+
  data_format = DataFormat(data_type)
  self.user_asks.append([data_type, url])
  self.load_and_embed(data_format.loader, data_format.chunker, url)
@@ -62,6 +64,9 @@ def add_local(self, data_type, content, config: AddConfig = None):
  :param content: The local data. Refer to the `README` for formatting.
  :param config: Optional. The `AddConfig` instance to use as configuration options.
  """
+ if config is None:
+ config = AddConfig()
+
  data_format = DataFormat(data_type)
  self.user_asks.append([data_type, content])
  self.load_and_embed(data_format.loader, data_format.chunker, content)
@@ -354,7 +359,7 @@ def __init__(self, person, config: InitConfig = None):
 class PersonApp(EmbedChainPersonApp, App):
  """
  The Person app.
- Extends functionality from EmbedChainPersonApp and App
+ Extends functionality fr om EmbedChainPersonApp and App
  """
  def query(self, input_query, config: QueryConfig = None):
  query_config = QueryConfig(