The Memory Layer for AI Agents - Drop-in memory infrastructure for AI agents and apps. Context that persists. Built for production.
Python agentic-memoryagentic-memory-systemagentsaiai-agentschatgptgenaillmlong-term-memorymemorymemory-managementpythonragstate-management
Allow ollama llm to take custom callback for handling streaming (#1376)
Aditya Veer Parmardc0d8e09324c
diff --git a/embedchain/llm/ollama.py b/embedchain/llm/ollama.pyindex 7de675cd6..c21c522dc 100644--- a/embedchain/llm/ollama.py+++ b/embedchain/llm/ollama.py@@ -33,14 +33,17 @@ class OllamaLlm(BaseLlm):@staticmethoddef _get_answer(prompt: str, config: BaseLlmConfig) -> Union[str, Iterable]:- callback_manager = [StreamingStdOutCallbackHandler()] if config.stream else [StdOutCallbackHandler()]+ if config.stream:+ callbacks = config.callbacks if config.callbacks else [StreamingStdOutCallbackHandler()]+ else:+ callbacks = [StdOutCallbackHandler()]llm = Ollama(model=config.model,system=config.system_prompt,temperature=config.temperature,top_p=config.top_p,- callback_manager=CallbackManager(callback_manager),+ callback_manager=CallbackManager(callbacks),base_url=config.base_url,)diff --git a/tests/llm/test_ollama.py b/tests/llm/test_ollama.pyindex ff16d1263..36a62b631 100644--- a/tests/llm/test_ollama.py+++ b/tests/llm/test_ollama.py@@ -2,6 +2,7 @@ import pytestfrom embedchain.config import BaseLlmConfigfrom embedchain.llm.ollama import OllamaLlm+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler@pytest.fixture@@ -31,3 +32,20 @@ def test_get_answer_mocked_ollama(ollama_llm_config, mocker):answer = llm.get_llm_model_answer(prompt)assert answer == "Mocked answer"+++def test_get_llm_model_answer_with_streaming(ollama_llm_config, mocker):+ ollama_llm_config.stream = True+ ollama_llm_config.callbacks = [StreamingStdOutCallbackHandler()]+ mocked_ollama_chat = mocker.patch("embedchain.llm.ollama.OllamaLlm._get_answer", return_value="Test answer")++ llm = OllamaLlm(ollama_llm_config)+ llm.get_llm_model_answer("Test query")++ mocked_ollama_chat.assert_called_once()+ call_args = mocked_ollama_chat.call_args+ config_arg = call_args[1]["config"]+ callbacks = config_arg.callbacks++ assert len(callbacks) == 1+ assert isinstance(callbacks[0], StreamingStdOutCallbackHandler)