AttributeError: module 'ollama' has no attribute 'embeddings'

[rcontesti]

I'm running the following adaptation to the ollama example:

import os

from lightrag import LightRAG, QueryParam
from lightrag.llm import ollama_model_complete, ollama_embedding
from lightrag.utils import EmbeddingFunc

WORKING_DIR = "light_rag/dickens"
MODEL_NAME = "llama3.2:3b"

if not os.path.exists(WORKING_DIR):
    os.mkdir(WORKING_DIR)

rag = LightRAG(
    working_dir=WORKING_DIR,
    llm_model_func=ollama_model_complete,
    llm_model_name=MODEL_NAME,
    embedding_func=EmbeddingFunc(
        embedding_dim=768,
        max_token_size=8192,
        func=lambda texts: ollama_embedding(texts, embed_model="nomic-embed-text"),
    ),
)

with open("light_rag/dickens/book.txt") as f:
    rag.insert(f.read())

# Perform naive search
print(
    rag.query("What are the top themes in this story?", param=QueryParam(mode="naive"))
)

# Perform local search
print(
    rag.query("What are the top themes in this story?", param=QueryParam(mode="local"))
)

# Perform global search
print(
    rag.query("What are the top themes in this story?", param=QueryParam(mode="global"))
)

# Perform hybrid search
print(
    rag.query("What are the top themes in this story?", param=QueryParam(mode="hybrid"))
)

Unfortunately, I'm getting the following error:

INFO:lightrag:Logger initialized for working directory: light_rag/dickens
DEBUG:lightrag:LightRAG init with param:
  working_dir = light_rag/dickens,
  chunk_token_size = 1200,
  chunk_overlap_token_size = 100,
  tiktoken_model_name = gpt-4o-mini,
  entity_extract_max_gleaning = 1,
  entity_summary_to_max_tokens = 500,
  node_embedding_algorithm = node2vec,
  node2vec_params = {'dimensions': 1536, 'num_walks': 10, 'walk_length': 40, 'window_size': 2, 'iterations': 3, 'random_seed': 3},
  embedding_func = {'embedding_dim': 768, 'max_token_size': 8192, 'func': <function <lambda> at 0x1268d1440>},
  embedding_batch_num = 32,
  embedding_func_max_async = 16,
  llm_model_func = <function ollama_model_complete at 0x142289800>,
  llm_model_name = llama3.2:3b,
  llm_model_max_token_size = 32768,
  llm_model_max_async = 16,
  key_string_value_json_storage_cls = <class 'lightrag.storage.JsonKVStorage'>,
  vector_db_storage_cls = <class 'lightrag.storage.NanoVectorDBStorage'>,
  vector_db_storage_cls_kwargs = {},
  graph_storage_cls = <class 'lightrag.storage.NetworkXStorage'>,
  enable_llm_cache = True,
  addon_params = {},
  convert_response_to_json_func = <function convert_response_to_json at 0x141af6980>
INFO:lightrag:Load KV full_docs with 0 data
INFO:lightrag:Load KV text_chunks with 0 data
INFO:lightrag:Load KV llm_response_cache with 0 data
INFO:nano-vectordb:Init {'embedding_dim': 768, 'metric': 'cosine', 'storage_file': 'light_rag/dickens/vdb_entities.json'} 0 data
INFO:nano-vectordb:Init {'embedding_dim': 768, 'metric': 'cosine', 'storage_file': 'light_rag/dickens/vdb_relationships.json'} 0 data
INFO:nano-vectordb:Init {'embedding_dim': 768, 'metric': 'cosine', 'storage_file': 'light_rag/dickens/vdb_chunks.json'} 0 data
INFO:lightrag:Creating a new event loop in a sub-thread.
INFO:lightrag:[New Docs] inserting 1 docs
INFO:lightrag:[New Chunks] inserting 42 chunks
INFO:lightrag:Inserting 42 vectors to chunks
INFO:lightrag:Writing graph with 0 nodes, 0 edges
Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "light_rag/src/example.py", line 26, in <module>
    rag.insert(f.read())
  File "site-packages/lightrag/lightrag.py", line 162, in insert
    return loop.run_until_complete(self.ainsert(string_or_strings))
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/asyncio/base_events.py", line 653, in run_until_complete
    return future.result()
           ^^^^^^^^^^^^^^^
  File "site-packages/lightrag/lightrag.py", line 206, in ainsert
    await self.chunks_vdb.upsert(inserting_chunks)
  File "site-packages/lightrag/storage.py", line 92, in upsert
    embeddings_list = await asyncio.gather(
                      ^^^^^^^^^^^^^^^^^^^^^
  File "/site-packages/lightrag/utils.py", line 87, in wait_func
    result = await func(*args, **kwargs)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "site-packages/lightrag/utils.py", line 43, in __call__
    return await self.func(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "site-packages/lightrag/llm.py", line 421, in ollama_embedding
    data = ollama.embeddings(model=embed_model, prompt=text)
           ^^^^^^^^^^^^^^^^^
AttributeError: module 'ollama' has no attribute 'embeddings'

[LarFii]

You can try creating a new virtual environment and then install LightRAG in it.

[rcontesti]

You can try creating a new virtual environment and then install LightRAG in it.

Thanks, I was able to solve it that way. I'm surprised that it works that way since in both env I have installed the same ollama version. Any clues of what might be going on with ollama?