From b8fbe145c91534e03123803d3ddc6fcc56b62f8e Mon Sep 17 00:00:00 2001 From: James Ketrenos Date: Wed, 30 Apr 2025 23:24:09 -0700 Subject: [PATCH] Working! --- src/utils/agents/chat.py | 14 ++++++-------- 1 file changed, 6 insertions(+), 8 deletions(-) diff --git a/src/utils/agents/chat.py b/src/utils/agents/chat.py index 0c6a2a0..e6495c1 100644 --- a/src/utils/agents/chat.py +++ b/src/utils/agents/chat.py @@ -100,14 +100,14 @@ class Chat(Agent, ABC): options={ "num_ctx": message.metadata["ctx_size"] if message.metadata["ctx_size"] else defines.max_context }, stream=True, ): - logging.info(f"LLM: {'done' if response.done else 'thinking'} - {response.message.content}") message.response += response.message.content - message.metadata["eval_count"] += response["eval_count"] - message.metadata["eval_duration"] += response["eval_duration"] - message.metadata["prompt_eval_count"] += response["prompt_eval_count"] - message.metadata["prompt_eval_duration"] += response["prompt_eval_duration"] yield message if response.done: + message.metadata["eval_count"] += response.eval_count + message.metadata["eval_duration"] += response.eval_duration + message.metadata["prompt_eval_count"] += response.prompt_eval_count + message.metadata["prompt_eval_duration"] += response.prompt_eval_duration + self.context_tokens = response.prompt_eval_count + response.eval_count message.status = "done" if not response: @@ -116,8 +116,6 @@ class Chat(Agent, ABC): yield message self.context.processing = False return - - self.context_tokens = response["prompt_eval_count"] + response["eval_count"] yield message self.context.processing = False @@ -216,7 +214,7 @@ class Chat(Agent, ABC): yield message async for message in self.generate_llm_response(llm, model, message): - logging.info(f"LLM: {message.status} - {message.response}") + logging.info(f"LLM: {message.status} - {f'...{message.response[-20:]}' if len(message.response) > 20 else message.response}") if message.status == "error": return if message.status != "done":