improve pass metadata

app.py

@@ -112,10 +112,13 @@ class MyEmbeddingFunction(EmbeddingFunction):
     def __init__(self, embedding_generator: EmbeddingGenerator):  
         self.embedding_generator = embedding_generator  
   
-    def __call__(self, input: Documents) -> Embeddings:  
-        embeddings = [self.embedding_generator.compute_embeddings(doc) for doc in input]  
-        embeddings = [item for sublist in embeddings for item in sublist]  
-        return embeddings  
+    def __call__(self, input: Documents) -> (Embeddings, list):  
+        embeddings_with_metadata = [self.embedding_generator.compute_embeddings(doc) for doc in input]  
+        embeddings = [item[0] for item in embeddings_with_metadata]  
+        metadata = [item[1] for item in embeddings_with_metadata]  
+        embeddings_flattened = [emb for sublist in embeddings for emb in sublist]  
+        metadata_flattened = [meta for sublist in metadata for meta in sublist]  
+        return embeddings_flattened, metadata_flattened  
   
 def load_documents(file_path: str, mode: str = "elements"):  
     loader = UnstructuredFileLoader(file_path, mode=mode)  
@@ -130,8 +133,15 @@ def initialize_chroma(collection_name: str, embedding_function: MyEmbeddingFunct
   
 def add_documents_to_chroma(client, collection, documents: list, embedding_function: MyEmbeddingFunction):  
     for doc in documents:  
-        collection.add(ids=[str(uuid.uuid1())], documents=[doc], embeddings=embedding_function([doc]))  
-  
+        embeddings, metadata = embedding_function.embedding_generator.compute_embeddings(doc)  
+        for embedding, meta in zip(embeddings, metadata):  
+            collection.add(  
+                ids=[str(uuid.uuid1())],  
+                documents=[doc],  
+                embeddings=[embedding],  
+                metadatas=[meta]  
+            )  
+
 def query_chroma(client, collection_name: str, query_text: str, embedding_function: MyEmbeddingFunction):  
     db = Chroma(client=client, collection_name=collection_name, embedding_function=embedding_function)  
     result_docs = db.similarity_search(query_text)  
@@ -177,8 +187,8 @@ def upload_documents(files):
     for file in files:  
         loader = UnstructuredFileLoader(file.name)  
         documents = loader.load_documents()  
-        add_documents_to_chroma(documents)  
-    return "Documents uploaded and processed successfully!"  
+        add_documents_to_chroma(chroma_client, chroma_collection, documents, embedding_function)  
+    return "Documents uploaded and processed successfully!" 
   
 def query_documents(query):  
     results = query_chroma(query)