@ -313,12 +313,12 @@ class ChatOllama(BaseChatModel, _OllamaCommon):
for stream_resp in self . _create_chat_stream ( messages , stop , * * kwargs ) :
for stream_resp in self . _create_chat_stream ( messages , stop , * * kwargs ) :
if stream_resp :
if stream_resp :
chunk = _chat_stream_response_to_chat_generation_chunk ( stream_resp )
chunk = _chat_stream_response_to_chat_generation_chunk ( stream_resp )
yield chunk
if run_manager :
if run_manager :
run_manager . on_llm_new_token (
run_manager . on_llm_new_token (
chunk . text ,
chunk . text ,
verbose = self . verbose ,
verbose = self . verbose ,
)
)
yield chunk
except OllamaEndpointNotFoundError :
except OllamaEndpointNotFoundError :
yield from self . _legacy_stream ( messages , stop , * * kwargs )
yield from self . _legacy_stream ( messages , stop , * * kwargs )
@ -332,12 +332,12 @@ class ChatOllama(BaseChatModel, _OllamaCommon):
async for stream_resp in self . _acreate_chat_stream ( messages , stop , * * kwargs ) :
async for stream_resp in self . _acreate_chat_stream ( messages , stop , * * kwargs ) :
if stream_resp :
if stream_resp :
chunk = _chat_stream_response_to_chat_generation_chunk ( stream_resp )
chunk = _chat_stream_response_to_chat_generation_chunk ( stream_resp )
yield chunk
if run_manager :
if run_manager :
await run_manager . on_llm_new_token (
await run_manager . on_llm_new_token (
chunk . text ,
chunk . text ,
verbose = self . verbose ,
verbose = self . verbose ,
)
)
yield chunk
@deprecated ( " 0.0.3 " , alternative = " _stream " )
@deprecated ( " 0.0.3 " , alternative = " _stream " )
def _legacy_stream (
def _legacy_stream (
@ -351,9 +351,9 @@ class ChatOllama(BaseChatModel, _OllamaCommon):
for stream_resp in self . _create_generate_stream ( prompt , stop , * * kwargs ) :
for stream_resp in self . _create_generate_stream ( prompt , stop , * * kwargs ) :
if stream_resp :
if stream_resp :
chunk = _stream_response_to_chat_generation_chunk ( stream_resp )
chunk = _stream_response_to_chat_generation_chunk ( stream_resp )
yield chunk
if run_manager :
if run_manager :
run_manager . on_llm_new_token (
run_manager . on_llm_new_token (
chunk . text ,
chunk . text ,
verbose = self . verbose ,
verbose = self . verbose ,
)
)
yield chunk