i am using google gen ai as it is free(suggest any better for free) and using google gen ai embedding well
i am trying to get the file splitted into chunks and then embedded it using googlegenaiembedding and then put it to the chroma vector db in my local machine but as i try with smaller data it works well but when i try adding a bigger set of files it stops and gives me an error for

ValueError: Batch size 279 exceeds maximum batch size 166
help me out with it hers the code

model = ChatGoogleGenerativeAI(
    model="gemini-pro",
    google_api_key="my prefectly working api key",
    temperature=0.5,
    convert_system_messages=True,
)


embeddings=GoogleGenerativeAIEmbeddings(
    model="models/embedding-001",
    google_api_key="prefectly working api key"
)
if not os.path.exists(books_dir):
    raise RuntimeError(f"Error loading {books_dir}: File does not exist.")
print(file_contents)
doc_true=r"C:UsersjatinOneDriveshitDesktopbooksjaitn.txt"
def create_vector_store(docs,store_name):
    emb_dir= os.path.join(db_dir, store_name)
    if not os.path.exists(emb_dir):
        print(f"n--- Creating vector store {store_name} ---")
        db = Chroma.from_documents(
            docs, embeddings, persist_directory=emb_dir
        )

        print(f"--- Finished creating vector store {store_name} ---")
        return db
    else:
        print(
            f"Vector store {store_name} already exists. No need to initialize.")
print("n--- Using Character-based Splitting ---")
text_splitter=CharacterTextSplitter(chunk_size=1000,chunk_overlap=100,)
texts=text_splitter.split_documents(file_contents)
create_vector_store(texts, "chroma_db_char")
print(type(texts))
def query_vector_store(store_name, query):
    emb_dir = os.path.join(db_dir, store_name)
    if os.path.exists(emb_dir):
        print(f"n storgae pe ja rahe  {store_name} ")


        db = Chroma(
            persist_directory=emb_dir, embedding_function=embeddings
        )

        retriever = db.as_retriever(
            search_type="similarity_score_threshold",
            search_kwargs={"k": 1, "score_threshold": 0.01},
        )
        print("this is query",query)
        print(retriever)
        relevant_docs = retriever.invoke(query)
        print(relevant_docs)

        print(f"n text--> {store_name} ")
        for i, doc in enumerate(relevant_docs, 1):
            print(model.invoke(f"question is{query} find the answer in {doc.page_content}n "))


    else:
        print(f"Vector store {store_name} nahi milaa ")


query3=("who wrote mataphores we live by")


query_vector_store("chroma_db_char", query3)

i am stuck here i tried using pinecone but i does not accept my api key