embedding email object

src/knowledge/core_object/__init__.py

@@ -1,4 +1,5 @@
 from .document_object import DocumentObject, DocumentObjectBuilder
 from .image_object import ImageObject, ImageObjectBuilder
 from .video_object import VideoObject, VideoObjectBuilder
+from .rich_text_object import RichTextObject, RichTextObjectBuilder
 from .email_object import EmailObject, EmailObjectBuilder

src/knowledge/core_object/image_object.py

@@ -18,7 +18,7 @@ class ImageObject(KnowledgeObject):
         body = dict()
         desc["meta"] = meta
         desc["exif"] = exif
-        desc
+        desc["tags"] = tags
         desc["hash"] = chunk_list.hash.to_base58()
         body["chunk_list"] = chunk_list.chunk_list
 

src/knowledge/object/object_id.py

@@ -8,7 +8,6 @@ import base36
 
 class ObjectType(Enum):
     Chunk = 7
-    TextChunk = 100
     Image = 101
     Video = 102
     Document = 103

src/knowledge/store.py

@@ -1,6 +1,7 @@
 import os
 from .object import ObjectStore
 from .data import ChunkStore, ChunkTracker, ChunkListWriter, ChunkReader
+from .vector import ChromaVectorStore, VectorBase
 import logging
 
 
@@ -37,6 +38,7 @@ class KnowledgeStore:
         self.chunk_tracker = ChunkTracker(chunk_store_dir)
         self.chunk_list_writer = ChunkListWriter(self.chunk_store, self.chunk_tracker)
         self.chunk_reader = ChunkReader(self.chunk_store, self.chunk_tracker)
+        self.vector_store = {}
         
 
     def get_object_store(self) -> ObjectStore:
@@ -53,3 +55,8 @@ class KnowledgeStore:
     
     def get_chunk_reader(self) -> ChunkReader:
         return self.chunk_reader
+    
+    def get_vector_store(self, model_name: str) -> VectorBase:
+        if model_name not in self.vector_store:
+            self.vector_store[model_name] = ChromaVectorStore(model_name)
+        return self.vector_store[model_name]

src/knowledge/vector/chroma_store.py

@@ -6,11 +6,11 @@ import os
 
 
 class ChromaVectorStore(VectorBase):
-    def __init__(self, db_url, model_name: str) -> None:
-        super().__init__(db_url, model_name)
+    def __init__(self, model_name: str) -> None:
+        super().__init__(model_name)
 
         logging.info(
-            "will init chroma vector store, db={}, model={}".format(db_url, model_name)
+            "will init chroma vector store, model={}".format(model_name)
         )
 
         directory = os.path.join(

src/knowledge/vector/vector_base.py

@@ -3,8 +3,7 @@ from ..object import ObjectID
 
 # define a vector base class
 class VectorBase:
-    def __init__(self, db_url, model_name) -> None:
-        self.db_url = db_url
+    def __init__(self, model_name) -> None:
         self.model_name = model_name
 
     async def insert(self, vector: [float], id: ObjectID):