mirror of
https://git.mirrors.martin98.com/https://github.com/infiniflow/ragflow.git
synced 2025-04-22 14:10:01 +08:00
fix ollama max token issue (#1489)
### What problem does this PR solve? ### Type of change - [x] Bug Fix (non-breaking change which fixes an issue)
This commit is contained in:
parent
d5618749c9
commit
a5a617b7a3
@ -80,7 +80,7 @@ def chat(dialog, messages, stream=True, **kwargs):
|
||||
llm = TenantLLMService.query(tenant_id=dialog.tenant_id, llm_name=dialog.llm_id)
|
||||
if not llm:
|
||||
raise LookupError("LLM(%s) not found" % dialog.llm_id)
|
||||
max_tokens = 1024
|
||||
max_tokens = 8192
|
||||
else:
|
||||
max_tokens = llm[0].max_tokens
|
||||
kbs = KnowledgebaseService.get_by_ids(dialog.kb_ids)
|
||||
|
@ -94,7 +94,7 @@ if __name__ == '__main__':
|
||||
werkzeug_logger = logging.getLogger("werkzeug")
|
||||
for h in access_logger.handlers:
|
||||
werkzeug_logger.addHandler(h)
|
||||
run_simple(hostname=HOST, port=HTTP_PORT, application=app, threaded=True, use_reloader=RuntimeConfig.DEBUG, use_debugger=RuntimeConfig.DEBUG)
|
||||
run_simple(hostname=HOST, port=HTTP_PORT, application=app, processes=5, use_reloader=RuntimeConfig.DEBUG, use_debugger=RuntimeConfig.DEBUG)
|
||||
except Exception:
|
||||
traceback.print_exc()
|
||||
os.kill(os.getpid(), signal.SIGKILL)
|
@ -35,7 +35,7 @@ _IS_RAW_CONF = "_is_raw_conf"
|
||||
class ComponentParamBase(ABC):
|
||||
def __init__(self):
|
||||
self.output_var_name = "output"
|
||||
self.message_history_window_size = 4
|
||||
self.message_history_window_size = 22
|
||||
|
||||
def set_name(self, name: str):
|
||||
self._name = name
|
||||
|
Loading…
x
Reference in New Issue
Block a user