diff --git a/agent/agent模式测试.ipynb b/agent/agent模式测试.ipynb
index 1fb3e01..239c3f7 100644
--- a/agent/agent模式测试.ipynb
+++ b/agent/agent模式测试.ipynb
@@ -2,13 +2,27 @@
"cells": [
{
"cell_type": "code",
- "execution_count": 2,
+ "execution_count": 1,
"id": "d2ff171c-f5f8-4590-9ce0-21c87e3d5b39",
"metadata": {},
- "outputs": [],
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "INFO 2023-06-01 20:26:48,576-1d: \n",
+ "loading model config\n",
+ "llm device: cuda\n",
+ "embedding device: cuda\n",
+ "dir: /media/gpt4-pdf-chatbot-langchain/dev-langchain-ChatGLM\n",
+ "flagging username: 7daba79785044bceb6896b9e6f8f9894\n",
+ "\n"
+ ]
+ }
+ ],
"source": [
"import sys\n",
- "sys.path.append('/media/gpt4-pdf-chatbot-langchain/langchain-ChatGLM/')\n",
+ "sys.path.append('/media/gpt4-pdf-chatbot-langchain/dev-langchain-ChatGLM/')\n",
"from langchain.llms.base import LLM\n",
"import torch\n",
"import transformers \n",
@@ -20,15 +34,9 @@
"from transformers.generation.logits_process import LogitsProcessor\n",
"from transformers.generation.utils import LogitsProcessorList, StoppingCriteriaList\n",
"from typing import Optional, List, Dict, Any\n",
- "from models.loader import LoaderCheckPoint\n",
- "from models.extensions.callback import (Iteratorize, Stream, FixedLengthQueue) \n",
+ "from models.loader import LoaderCheckPoint \n",
"from models.base import (BaseAnswer,\n",
- " AnswerResult,\n",
- " AnswerResultStream,\n",
- " AnswerResultQueueSentinelTokenListenerQueue)\n",
- "from langchain.callbacks.manager import (\n",
- " CallbackManagerForLLMRun\n",
- ")\n",
+ " AnswerResult)\n",
"\n"
]
},
@@ -38,29 +46,50 @@
"id": "68978c38-c0e9-4ae9-ba90-9c02aca335be",
"metadata": {},
"outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Loading vicuna-7b-hf...\n"
+ ]
+ },
{
"name": "stderr",
"output_type": "stream",
"text": [
- "Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in mixed int8. Either pass torch_dtype=torch.float16 or don't pass this argument at all to remove this warning.\n"
+ "Overriding torch_dtype=None with `torch_dtype=torch.float16` due to requirements of `bitsandbytes` to enable model loading in mixed int8. Either pass torch_dtype=torch.float16 or don't pass this argument at all to remove this warning.\n",
+ "/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/bitsandbytes/cuda_setup/main.py:149: UserWarning: /media/gpt4-pdf-chatbot-langchain/pyenv-langchain did not contain ['libcudart.so', 'libcudart.so.11.0', 'libcudart.so.12.0'] as expected! Searching further paths...\n",
+ " warn(msg)\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
- "Loading vicuna-13b-hf...\n"
+ "\n",
+ "===================================BUG REPORT===================================\n",
+ "Welcome to bitsandbytes. For bug reports, please run\n",
+ "\n",
+ "python -m bitsandbytes\n",
+ "\n",
+ " and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues\n",
+ "================================================================================\n",
+ "bin /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda118.so\n",
+ "CUDA SETUP: CUDA runtime path found: /opt/cuda/lib64/libcudart.so.11.0\n",
+ "CUDA SETUP: Highest compute capability among GPUs detected: 8.6\n",
+ "CUDA SETUP: Detected CUDA version 118\n",
+ "CUDA SETUP: Loading binary /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/bitsandbytes/libbitsandbytes_cuda118.so...\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
- "model_id": "999ea6baab394a6f9b2b4a815ead7ef4",
+ "model_id": "9b61d05e18044b009c72b862c84ab5cb",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
- "Loading checkpoint shards: 0%| | 0/3 [00:00 Dict[str, Any]:\n",
- " \"\"\"\n",
- " :return: 响应结构\n",
- " \"\"\"\n",
- " return {\n",
- " \"text\": \"\"\n",
+ "from jsonformer import Jsonformer\n",
+ "json_schema = {\n",
+ " \"type\": \"object\",\n",
+ " \"properties\": {\n",
+ " \"action\": {\"type\": \"string\"},\n",
+ " \"action_input\": {\"type\": \"string\"}\n",
" }\n",
+ "}\n",
"\n",
+ "prompt = \"\"\" Respond to the human as helpfully and accurately as possible. You have access to the following tools:\n",
"\n",
- "def _update_response(response: Dict[str, Any], stream_response: str) -> None:\n",
- " \"\"\"Update response from the stream response.\"\"\"\n",
- " response[\"text\"] += stream_response\n",
+ "State of Dialogue History System: 露ᥫᩣ, 张毛峰的对话 - 当需要查找露ᥫᩣ, 张毛峰之间的聊天内容时，这里面的回答是很有用的。输入应该是一个完整的问题。\n",
+ "Summary: useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\n",
"\n",
+ "The way you use the tools is by specifying a json blob.\n",
+ "Specifically, this json should have a `action` key (with the name of the tool to use) and a `action_input` key (with the input to the tool going here).\n",
"\n",
- "class InvalidScoreLogitsProcessor(LogitsProcessor):\n",
- " def __call__(self, input_ids: torch.LongTensor, scores: torch.FloatTensor) -> torch.FloatTensor:\n",
- " if torch.isnan(scores).any() or torch.isinf(scores).any():\n",
- " scores.zero_()\n",
- " scores[..., 5] = 5e4\n",
- " return scores\n",
+ "The only values that should be in the \"action\" field are: {tool_names}\n",
"\n",
+ "The $JSON_BLOB should only contain a SINGLE action, do NOT return a list of multiple actions. Here is an example of a valid $JSON_BLOB:\n",
"\n",
- "class LLamaLLM(BaseAnswer, LLM, ABC):\n",
- " checkPoint: LoaderCheckPoint = None\n",
- " history = []\n",
- " history_len: int = 3\n",
- " max_new_tokens: int = 500\n",
- " num_beams: int = 1\n",
- " temperature: float = 0.5\n",
- " top_p: float = 0.4\n",
- " top_k: int = 10\n",
- " repetition_penalty: float = 1.12\n",
- " encoder_repetition_penalty: int = 1\n",
- " min_length: int = 0\n",
- " logits_processor: LogitsProcessorList = None\n",
- " stopping_criteria: Optional[StoppingCriteriaList] = None\n",
+ "```\n",
+ "{{{{\n",
+ " \"action\": $TOOL_NAME,\n",
+ " \"action_input\": $INPUT\n",
+ "}}}}\n",
+ "```\n",
"\n",
- " state: object = {'max_new_tokens': 50,\n",
- " 'seed': 1,\n",
- " 'temperature': 0, 'top_p': 0.1,\n",
- " 'top_k': 40, 'typical_p': 1,\n",
- " 'repetition_penalty': 1.18,\n",
- " 'encoder_repetition_penalty': 1,\n",
- " 'no_repeat_ngram_size': 0,\n",
- " 'min_length': 0,\n",
- " 'penalty_alpha': 0,\n",
- " 'num_beams': 1,\n",
- " 'length_penalty': 1,\n",
- " 'early_stopping': False, 'add_bos_token': True, 'ban_eos_token': False,\n",
- " 'truncation_length': 2048, 'custom_stopping_strings': '',\n",
- " 'cpu_memory': 0, 'auto_devices': False, 'disk': False, 'cpu': False, 'bf16': False,\n",
- " 'load_in_8bit': False, 'wbits': 'None', 'groupsize': 'None', 'model_type': 'None',\n",
- " 'pre_layer': 0, 'gpu_memory_0': 0}\n",
+ "ALWAYS use the following format:\n",
"\n",
- " def __init__(self, checkPoint: LoaderCheckPoint = None):\n",
- " super().__init__()\n",
- " self.checkPoint = checkPoint\n",
+ "Question: the input question you must answer\n",
+ "Thought: you should always think about what to do\n",
+ "Action:\n",
+ "```\n",
+ "$JSON_BLOB\n",
+ "```\n",
+ "Observation: the result of the action\n",
+ "... (this Thought/Action/Observation can repeat N times)\n",
+ "Thought: I now know the final answer\n",
+ "Final Answer: the final answer to the original input question\n",
"\n",
- " @property\n",
- " def _llm_type(self) -> str:\n",
- " return \"LLamaLLM\"\n",
+ "Begin! Reminder to always use the exact characters `Final Answer` when responding.\n",
"\n",
- " @property\n",
- " def _check_point(self) -> LoaderCheckPoint:\n",
- " return self.checkPoint\n",
- "\n",
- " def encode(self, prompt, add_special_tokens=True, add_bos_token=True, truncation_length=None):\n",
- " input_ids = self.checkPoint.tokenizer.encode(str(prompt), return_tensors='pt',\n",
- " add_special_tokens=add_special_tokens)\n",
- " # This is a hack for making replies more creative.\n",
- " if not add_bos_token and input_ids[0][0] == self.checkPoint.tokenizer.bos_token_id:\n",
- " input_ids = input_ids[:, 1:]\n",
- "\n",
- " # Llama adds this extra token when the first character is '\\n', and this\n",
- " # compromises the stopping criteria, so we just remove it\n",
- " if type(self.checkPoint.tokenizer) is transformers.LlamaTokenizer and input_ids[0][0] == 29871:\n",
- " input_ids = input_ids[:, 1:]\n",
- "\n",
- " # Handling truncation\n",
- " if truncation_length is not None:\n",
- " input_ids = input_ids[:, -truncation_length:]\n",
- "\n",
- " return input_ids.cuda()\n",
- "\n",
- " def decode(self, output_ids):\n",
- " reply = self.checkPoint.tokenizer.decode(output_ids, skip_special_tokens=True)\n",
- " return reply\n",
- "\n",
- " def generate_with_callback(self, callback=None, **kwargs):\n",
- " self.checkPoint.clear_torch_cache()\n",
- " kwargs['stopping_criteria'].append(Stream(callback_func=callback))\n",
- " with torch.no_grad():\n",
- " self.checkPoint.model.generate(**kwargs)\n",
- " print(\"方法结束\")\n",
- "\n",
- " def generate_with_streaming(self, **kwargs):\n",
- " return Iteratorize(self.generate_with_callback, kwargs)\n",
- "\n",
- " # 将历史对话数组转换为文本格式\n",
- " def history_to_text(self, query):\n",
- " formatted_history = ''\n",
- " history = self.history[-self.history_len:] if self.history_len > 0 else []\n",
- " for i, (old_query, response) in enumerate(history):\n",
- " formatted_history += \"[Round {}]\\n问：{}\\n答：{}\\n\".format(i, old_query, response)\n",
- " formatted_history += \"[Round {}]\\n问：{}\\n答：\".format(len(history), query)\n",
- " return formatted_history\n",
- "\n",
- " def prepare_inputs_for_generation(self,\n",
- " input_ids: torch.LongTensor):\n",
- " \"\"\"\n",
- " 预生成注意力掩码和 输入序列中每个位置的索引的张量\n",
- " # TODO 没有思路\n",
- " :return:\n",
- " \"\"\"\n",
- "\n",
- " mask_positions = torch.zeros((1, input_ids.shape[1]), dtype=input_ids.dtype).to(self.checkPoint.model.device)\n",
- "\n",
- " attention_mask = self.get_masks(input_ids, input_ids.device)\n",
- "\n",
- " position_ids = self.get_position_ids(\n",
- " input_ids,\n",
- " device=input_ids.device,\n",
- " mask_positions=mask_positions\n",
- " )\n",
- "\n",
- " return input_ids, position_ids, attention_mask\n",
- "\n",
- " def get_position_ids(self, input_ids: torch.LongTensor, mask_positions, device):\n",
- " \"\"\"\n",
- " 注意力偏移量\n",
- " :param input_ids:\n",
- " :param mask_positions:\n",
- " :param device:\n",
- " :param use_gmasks:\n",
- " :return:\n",
- " \"\"\"\n",
- " batch_size, seq_length = input_ids.shape\n",
- " context_lengths = [seq.tolist().index(self.checkPoint.model_config.bos_token_id) for seq in input_ids]\n",
- " position_ids = torch.arange(seq_length, dtype=torch.long, device=device).unsqueeze(0).repeat(batch_size, 1)\n",
- " for i, context_length in enumerate(context_lengths):\n",
- " position_ids[i, context_length:] = mask_positions[i]\n",
- " block_position_ids = [torch.cat((\n",
- " torch.zeros(context_length, dtype=torch.long, device=device),\n",
- " torch.arange(seq_length - context_length, dtype=torch.long, device=device) + 1\n",
- " )) for context_length in context_lengths]\n",
- " block_position_ids = torch.stack(block_position_ids, dim=0)\n",
- " position_ids = torch.stack((position_ids, block_position_ids), dim=1)\n",
- " return position_ids\n",
- "\n",
- " def get_masks(self, input_ids, device):\n",
- " \"\"\"\n",
- " 获取注意力掩码\n",
- " :param input_ids:\n",
- " :param device:\n",
- " :return:\n",
- " \"\"\"\n",
- " batch_size, seq_length = input_ids.shape\n",
- " context_lengths = [seq.tolist().index(self.checkPoint.model_config.bos_token_id) for seq in input_ids]\n",
- " attention_mask = torch.ones((batch_size, seq_length, seq_length), device=device)\n",
- " attention_mask.tril_()\n",
- " for i, context_length in enumerate(context_lengths):\n",
- " attention_mask[i, :, :context_length] = 1\n",
- " attention_mask.unsqueeze_(1)\n",
- " attention_mask = (attention_mask < 0.5).bool()\n",
- " return attention_mask\n",
- "\n",
- " def generate_softprompt_history_tensors(self, query):\n",
- " \"\"\"\n",
- " 历史对话软提示\n",
- " 这段代码首先定义了一个名为 history_to_text 的函数，用于将 self.history\n",
- " 数组转换为所需的文本格式。然后，我们将格式化后的历史文本\n",
- " 再用 self.encode 将其转换为向量表示。最后，将历史对话向量与当前输入的对话向量拼接在一起。\n",
- " :return:\n",
- " \"\"\"\n",
- "\n",
- " # 对话内容\n",
- " # 处理历史对话\n",
- " formatted_history = self.history_to_text(query)\n",
- " return formatted_history\n",
- "\n",
- " def _call(self,\n",
- " prompt: str,\n",
- " stop: Optional[List[str]] = None,\n",
- " run_manager: Optional[CallbackManagerForLLMRun] = None) -> str:\n",
- " print(f\"__call:{prompt}\")\n",
- " if self.logits_processor is None:\n",
- " self.logits_processor = LogitsProcessorList()\n",
- " self.logits_processor.append(InvalidScoreLogitsProcessor())\n",
- "\n",
- " gen_kwargs = {\n",
- " \"max_new_tokens\": self.max_new_tokens,\n",
- " \"num_beams\": self.num_beams,\n",
- " \"top_p\": self.top_p,\n",
- " \"top_k\": self.top_k,\n",
- " \"repetition_penalty\": self.repetition_penalty,\n",
- " \"encoder_repetition_penalty\": self.encoder_repetition_penalty,\n",
- " \"min_length\": self.min_length,\n",
- " \"temperature\": self.temperature,\n",
- " \"logits_processor\": self.logits_processor}\n",
- "\n",
- " # 向量拼接\n",
- " input_ids = self.encode(prompt, add_bos_token=self.state['add_bos_token'], truncation_length=self.max_new_tokens)\n",
- " # input_ids, position_ids, attention_mask = self.prepare_inputs_for_generation(input_ids=filler_input_ids)\n",
- "\n",
- " # 对话模型prompt\n",
- " gen_kwargs.update({'inputs': input_ids})\n",
- " # 注意力掩码\n",
- " # gen_kwargs.update({'attention_mask': attention_mask})\n",
- " # gen_kwargs.update({'position_ids': position_ids})\n",
- " if self.stopping_criteria is None:\n",
- " self.stopping_criteria = transformers.StoppingCriteriaList()\n",
- " # 观测输出\n",
- " gen_kwargs.update({'stopping_criteria': self.stopping_criteria})\n",
- " shared.stop_everything = False\n",
- " stopped = False\n",
- " response_template = _streaming_response_template()\n",
- "\n",
- " # TODO 此流输出方法需要重写！！！！！！！！！！！！！！！！！！！！！！！！！！！！！！！！！\n",
- " # stopping_criteria方法不可控制 迭代器的变量无法共享\n",
- " with self.generate_with_streaming(**gen_kwargs) as generator:\n",
- " last_reply_len = 0\n",
- " reply_index = 0\n",
- " # Create a FixedLengthQueue with the desired stop sequence and a maximum length.\n",
- " queue = FixedLengthQueue(stop)\n",
- " for output in generator:\n",
- " new_tokens = len(output) - len(input_ids[0])\n",
- " reply = self.decode(output[-new_tokens:])\n",
- "\n",
- " new_reply = len(reply) - last_reply_len\n",
- " output_reply = reply[-new_reply:]\n",
- " queue.add(reply_index, output_reply)\n",
- " queue.contains_replace_sequence()\n",
- " if stop:\n",
- " pos = queue.contains_stop_sequence()\n",
- " if pos != -1:\n",
- " shared.stop_everything = True\n",
- " stopped = True\n",
- "\n",
- " #print(f\"{reply_index}：reply {output_reply}\")\n",
- " english_reply = queue.put_replace_out(reply_index)\n",
- " #print(f\"{reply_index}：english_reply {english_reply}\")\n",
- " _update_response(response_template, english_reply)\n",
- " last_reply_len = len(reply)\n",
- "\n",
- " reply_index += 1\n",
- " if new_tokens == self.max_new_tokens - 1 or stopped:\n",
- " break\n",
- "\n",
- " response = response_template['text']\n",
- " print(f\"response:{response}\")\n",
- " self.history = self.history + [[None, response]]\n",
- " return response\n",
- "\n",
- " def _generate_answer(self, prompt: str,\n",
- " history: List[List[str]] = [],\n",
- " streaming: bool = False,\n",
- " generate_with_callback: AnswerResultStream = None) -> None:\n",
- " if history:\n",
- " self.history = history\n",
- " # Create the StoppingCriteriaList with the stopping strings\n",
- " self.stopping_criteria = transformers.StoppingCriteriaList()\n",
- " # 定义模型stopping_criteria 队列，在每次响应时将 torch.LongTensor, torch.FloatTensor同步到AnswerResult\n",
- " listenerQueue = AnswerResultQueueSentinelTokenListenerQueue()\n",
- " self.stopping_criteria.append(listenerQueue)\n",
- " # TODO 需要实现chat对话模块和注意力模型，目前_call为langchain的LLM拓展的api，默认为无提示词模式，如果需要操作注意力模型，可以参考chat_glm的实现\n",
- " softprompt = self.generate_softprompt_history_tensors(prompt)\n",
- " response = self._call(prompt=softprompt, stop=['\\n###'])\n",
- " answer_result = AnswerResult()\n",
- " answer_result.history = self.history\n",
- " if listenerQueue.listenerQueue.__len__() > 0:\n",
- " answer_result.listenerToken = listenerQueue.listenerQueue.pop()\n",
- " answer_result.llm_output = {\"answer\": response}\n",
- " generate_with_callback(answer_result)\n"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "id": "306450e6-b1fd-4c9c-9083-7419094a14f5",
- "metadata": {},
- "outputs": [],
- "source": [
- "\n",
- "llm_model_ins = LLamaLLM(checkPoint=shared.loaderCheckPoint) "
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 6,
- "id": "7180ae6a-7050-48a0-b89a-82e51bec7db1",
- "metadata": {},
- "outputs": [],
- "source": [
- "\n",
- "from langchain.chains import LLMChain\n",
- "from langchain.memory import ConversationBufferMemory, ReadOnlySharedMemory\n",
- "from langchain.prompts import PromptTemplate\n",
- "\n",
- "template = \"\"\"This is a conversation between a human and a bot:\n",
- "\n",
- "{chat_history}\n",
- "\n",
- "Write a summary of the conversation for {input}:\n",
+ "Question: 我想查看关于露露的摘要信息\n",
"\"\"\"\n",
+ "jsonformer = Jsonformer(shared.loaderCheckPoint.model, shared.loaderCheckPoint.tokenizer, json_schema, prompt)\n",
+ "generated_data = jsonformer()\n",
"\n",
- "prompt = PromptTemplate(\n",
- " input_variables=[\"input\", \"chat_history\"],\n",
- " template=template\n",
- ")\n",
- "memory = ConversationBufferMemory(memory_key=\"chat_history\")\n",
- "readonlymemory = ReadOnlySharedMemory(memory=memory)\n",
- "summry_chain = LLMChain(\n",
- " llm=llm_model_ins,\n",
- " prompt=prompt,\n",
- " verbose=True,\n",
- " memory=readonlymemory, # use the read-only memory to prevent the tool from modifying the memory\n",
- ")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 7,
- "id": "8516d438-8f9c-4cb7-b921-a7ee216648d5",
- "metadata": {},
- "outputs": [],
- "source": [
- "from langchain.agents import ZeroShotAgent, Tool, AgentExecutor\n",
- "from typing import List, Set\n",
- "\n",
- "\n",
- "class CustomLLMSingleActionAgent(ZeroShotAgent):\n",
- " allowed_tools: List[str]\n",
- "\n",
- " def __init__(self, *args, **kwargs):\n",
- " super(CustomLLMSingleActionAgent, self).__init__(*args, **kwargs)\n",
- " self.allowed_tools = kwargs['allowed_tools']\n",
- "\n",
- " def get_allowed_tools(self) -> Set[str]:\n",
- " return set(self.allowed_tools)\n",
- " \n",
- " \n",
- "tools = [ \n",
- " Tool(\n",
- " name=\"Summary\",\n",
- " func=summry_chain.run,\n",
- " description=\"useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\"\n",
- " )\n",
- " ]\n",
- "\n",
- "prefix = \"\"\"Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\"\"\"\n",
- "suffix = \"\"\"Begin!\n",
- " \n",
- "Question: {input}\n",
- "{agent_scratchpad}\"\"\"\n",
- "\n",
- "\n",
- "prompt = ZeroShotAgent.create_prompt(\n",
- " tools,\n",
- " prefix=prefix,\n",
- " suffix=suffix,\n",
- " input_variables=[\"input\", \"agent_scratchpad\"]\n",
- ")\n",
- "tool_names = [tool.name for tool in tools]\n",
- "llm_chain = LLMChain(llm=llm_model_ins, prompt=prompt)\n",
- "agent = CustomLLMSingleActionAgent(llm_chain=llm_chain, tools=tools, allowed_tools=tool_names)\n",
- "agent_chain = AgentExecutor.from_agent_and_tools(agent=agent, tools=tools)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 8,
- "id": "233c3097-66cb-48b0-8de7-d34177e60bd6",
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "__call:Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\n",
- "\n",
- "Summary: useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\n",
- "\n",
- "Use the following format:\n",
- "\n",
- "Question: the input question you must answer\n",
- "Thought: you should always think about what to do\n",
- "Action: the action to take, should be one of [Summary]\n",
- "Action Input: the input to the action\n",
- "Observation: the result of the action\n",
- "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
- "Thought: I now know the final answer\n",
- "Final Answer: the final answer to the original input question\n",
- "\n",
- "Begin!\n",
- " \n",
- "Question: 你好\n",
- "\n",
- "response:Thought: 我必��hought: 我必须回��hought: 我必须回答这个问题。\n",
- "Action: 问��hought: 我必须回答这个问题。\n",
- "Action: 问她想知道��hought: 我必须回答这个问题。\n",
- "Action: 问她想知道什么。\n",
- "Action Input: 没有需要的输入。\n",
- "Observation:\n",
- "__call:Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\n",
- "\n",
- "Summary: useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\n",
- "\n",
- "Use the following format:\n",
- "\n",
- "Question: the input question you must answer\n",
- "Thought: you should always think about what to do\n",
- "Action: the action to take, should be one of [Summary]\n",
- "Action Input: the input to the action\n",
- "Observation: the result of the action\n",
- "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
- "Thought: I now know the final answer\n",
- "Final Answer: the final answer to the original input question\n",
- "\n",
- "Begin!\n",
- " \n",
- "Question: 你好\n",
- "Thought: 我必��hought: 我必须回��hought: 我必须回答这个问题。\n",
- "Action: 问��hought: 我必须回答这个问题。\n",
- "Action: 问她想知道��hought: 我必须回答这个问题。\n",
- "Action: 问她想知道什么。\n",
- "Action Input: 没有需要的输入。\n",
- "Observation:\n",
- "Observation: 问��hought: 我必须回答这个问题。\n",
- "Action: 问她想知道��hought: 我必须回答这个问题。\n",
- "Action: 问她想知道什么。 is not a valid tool, try another one.\n",
- "Thought:\n",
- "traceback.print_exc()\n"
- ]
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Traceback (most recent call last):\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/langchain-ChatGLM/models/extensions/callback.py\", line 188, in gen\n",
- " ret = self.mfunc(callback=_callback, **self.kwargs)\n",
- " File \"/tmp/ipykernel_10879/1809555145.py\", line 114, in generate_with_callback\n",
- " self.checkPoint.model.generate(**kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/torch/utils/_contextlib.py\", line 115, in decorate_context\n",
- " return func(*args, **kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 1437, in generate\n",
- " return self.greedy_search(\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 2245, in greedy_search\n",
- " model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py\", line 737, in prepare_inputs_for_generation\n",
- " position_ids.masked_fill_(attention_mask == 0, 1)\n",
- "SystemExit\n"
- ]
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "方法结束\n",
- "invalid thread id\n",
- "response:我不能回��不能回答这个问题，因为我是一个人工智能程序。\n",
- "Final Answer: 我不能回��不能回答这个问题，因为我是一个人工智能程序。\n",
- "Final Answer: 我不能回答这个问题，因为我是一个人工智能程序。\n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "'我不能回答这个问题，因为我是一个人工智能程序。'"
- ]
- },
- "execution_count": 8,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "\n",
- "agent_chain.run(input=\"你好\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 8,
- "id": "71a4259f-f589-4aa6-b868-3e10b4f2b22c",
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "__call:Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\n",
- "\n",
- "Summary: useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\n",
- "\n",
- "Use the following format:\n",
- "\n",
- "Question: the input question you must answer\n",
- "Thought: you should always think about what to do\n",
- "Action: the action to take, should be one of [Summary]\n",
- "Action Input: the input to the action\n",
- "Observation: the result of the action\n",
- "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
- "Thought: I now know the final answer\n",
- "Final Answer: the final answer to the original input question\n",
- "\n",
- "Begin!\n",
- " \n",
- "Question: 你是谁?\n",
- "\n",
- "response:Thought: 我需要回��hought: 我需要回答这个问题。\n",
- "Action: ��hought: 我需要回答这个问题。\n",
- "Action: 执行以下操作:\n",
- "Action Input: 输入自��hought: 我需要回答这个问题。\n",
- "Action: 执行以下操作:\n",
- "Action Input: 输入自己的名字。\n",
- "Observation:\n",
- "__call:Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\n",
- "\n",
- "Summary: useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\n",
- "\n",
- "Use the following format:\n",
- "\n",
- "Question: the input question you must answer\n",
- "Thought: you should always think about what to do\n",
- "Action: the action to take, should be one of [Summary]\n",
- "Action Input: the input to the action\n",
- "Observation: the result of the action\n",
- "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
- "Thought: I now know the final answer\n",
- "Final Answer: the final answer to the original input question\n",
- "\n",
- "Begin!\n",
- " \n",
- "Question: 你是谁?\n",
- "Thought: 我需要回��hought: 我需要回答这个问题。\n",
- "Action: ��hought: 我需要回答这个问题。\n",
- "Action: 执行以下操作:\n",
- "Action Input: 输入自��hought: 我需要回答这个问题。\n",
- "Action: 执行以下操作:\n",
- "Action Input: 输入自己的名字。\n",
- "Observation:\n",
- "Observation: ��hought: 我需要回答这个问题。\n",
- "Action: 执行以下操作: is not a valid tool, try another one.\n",
- "Thought:\n",
- "traceback.print_exc()\n"
- ]
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Traceback (most recent call last):\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/langchain-ChatGLM/models/extensions/callback.py\", line 188, in gen\n",
- " ret = self.mfunc(callback=_callback, **self.kwargs)\n",
- " File \"/tmp/ipykernel_13699/1809555145.py\", line 114, in generate_with_callback\n",
- " self.checkPoint.model.generate(**kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/torch/utils/_contextlib.py\", line 115, in decorate_context\n",
- " return func(*args, **kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 1437, in generate\n",
- " return self.greedy_search(\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 2245, in greedy_search\n",
- " model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py\", line 737, in prepare_inputs_for_generation\n",
- " position_ids.masked_fill_(attention_mask == 0, 1)\n",
- "SystemExit\n"
- ]
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "方法结束\n",
- "invalid thread id\n",
- "response:我不知道该如何回��不知道该如何回答这个问题。\n",
- "Final Answer: 我不知道该如何回��不知道该如何回答这个问题。\n",
- "Final Answer: 我不知道该如何回答这个问题。\n"
- ]
- },
- {
- "data": {
- "text/plain": [
- "'我不知道该如何回答这个问题。'"
- ]
- },
- "execution_count": 8,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "agent_chain.run(input=\"你是谁?\")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 9,
- "id": "e0cd4b1d-a7c8-432f-93d4-ef78b3dd851a",
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "__call:Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\n",
- "\n",
- "Summary: useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\n",
- "\n",
- "Use the following format:\n",
- "\n",
- "Question: the input question you must answer\n",
- "Thought: you should always think about what to do\n",
- "Action: the action to take, should be one of [Summary]\n",
- "Action Input: the input to the action\n",
- "Observation: the result of the action\n",
- "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
- "Thought: I now know the final answer\n",
- "Final Answer: the final answer to the original input question\n",
- "\n",
- "Begin!\n",
- " \n",
- "Question: 我们之前聊了什么?\n",
- "\n",
- "response:Thought: 我需要回��hought: 我需要回顾我们之前的对话以确定问题的��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 检查我们之前的对话记录\n",
- "Action Input: 无\n",
- "Observation:\n",
- "__call:Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\n",
- "\n",
- "Summary: useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\n",
- "\n",
- "Use the following format:\n",
- "\n",
- "Question: the input question you must answer\n",
- "Thought: you should always think about what to do\n",
- "Action: the action to take, should be one of [Summary]\n",
- "Action Input: the input to the action\n",
- "Observation: the result of the action\n",
- "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
- "Thought: I now know the final answer\n",
- "Final Answer: the final answer to the original input question\n",
- "\n",
- "Begin!\n",
- " \n",
- "Question: 我们之前聊了什么?\n",
- "Thought: 我需要回��hought: 我需要回顾我们之前的对话以确定问题的��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 检查我们之前的对话记录\n",
- "Action Input: 无\n",
- "Observation:\n",
- "Observation: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 检查我们之前的对话记录 is not a valid tool, try another one.\n",
- "Thought:\n",
- "traceback.print_exc()\n"
- ]
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Traceback (most recent call last):\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/langchain-ChatGLM/models/extensions/callback.py\", line 188, in gen\n",
- " ret = self.mfunc(callback=_callback, **self.kwargs)\n",
- " File \"/tmp/ipykernel_13699/1809555145.py\", line 114, in generate_with_callback\n",
- " self.checkPoint.model.generate(**kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/torch/utils/_contextlib.py\", line 115, in decorate_context\n",
- " return func(*args, **kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 1437, in generate\n",
- " return self.greedy_search(\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 2245, in greedy_search\n",
- " model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py\", line 737, in prepare_inputs_for_generation\n",
- " position_ids.masked_fill_(attention_mask == 0, 1)\n",
- "SystemExit\n"
- ]
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "response:我需要回��需要回顾我们之前的对话以确定问题的��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 找出我们之前��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 找出我们之前聊的主题\n",
- "Action Input: 无\n",
- "Observation:\n",
- "__call:Have a conversation with a human, answering the following questions as best you can. You have access to the following tools:\n",
- "\n",
- "Summary: useful for when you summarize a conversation. The input to this tool should be a string, representing who will read this summary.\n",
- "\n",
- "Use the following format:\n",
- "\n",
- "Question: the input question you must answer\n",
- "Thought: you should always think about what to do\n",
- "Action: the action to take, should be one of [Summary]\n",
- "Action Input: the input to the action\n",
- "Observation: the result of the action\n",
- "... (this Thought/Action/Action Input/Observation can repeat N times)\n",
- "Thought: I now know the final answer\n",
- "Final Answer: the final answer to the original input question\n",
- "\n",
- "Begin!\n",
- " \n",
- "Question: 我们之前聊了什么?\n",
- "Thought: 我需要回��hought: 我需要回顾我们之前的对话以确定问题的��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 检查我们之前的对话记录\n",
- "Action Input: 无\n",
- "Observation:\n",
- "Observation: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 检查我们之前的对话记录 is not a valid tool, try another one.\n",
- "Thought:我需要回��需要回顾我们之前的对话以确定问题的��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 找出我们之前��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 找出我们之前聊的主题\n",
- "Action Input: 无\n",
- "Observation:\n",
- "Observation: ��hought: 我需要回��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 找出我们之前��需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: ��hought: 我需要回顾我们之前的对话以确定问题的具体内容。\n",
- "Action: 找出我们之前聊的主题 is not a valid tool, try another one.\n",
- "Thought:\n",
- "traceback.print_exc()\n"
- ]
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Traceback (most recent call last):\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/langchain-ChatGLM/models/extensions/callback.py\", line 188, in gen\n",
- " ret = self.mfunc(callback=_callback, **self.kwargs)\n",
- " File \"/tmp/ipykernel_13699/1809555145.py\", line 114, in generate_with_callback\n",
- " self.checkPoint.model.generate(**kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/torch/utils/_contextlib.py\", line 115, in decorate_context\n",
- " return func(*args, **kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 1437, in generate\n",
- " return self.greedy_search(\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 2245, in greedy_search\n",
- " model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py\", line 737, in prepare_inputs_for_generation\n",
- " position_ids.masked_fill_(attention_mask == 0, 1)\n",
- "SystemExit\n"
- ]
- },
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "response:������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������������\n",
- "traceback.print_exc()\n"
- ]
- },
- {
- "name": "stderr",
- "output_type": "stream",
- "text": [
- "Traceback (most recent call last):\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/langchain-ChatGLM/models/extensions/callback.py\", line 188, in gen\n",
- " ret = self.mfunc(callback=_callback, **self.kwargs)\n",
- " File \"/tmp/ipykernel_13699/1809555145.py\", line 114, in generate_with_callback\n",
- " self.checkPoint.model.generate(**kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/torch/utils/_contextlib.py\", line 115, in decorate_context\n",
- " return func(*args, **kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 1437, in generate\n",
- " return self.greedy_search(\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/generation/utils.py\", line 2245, in greedy_search\n",
- " model_inputs = self.prepare_inputs_for_generation(input_ids, **model_kwargs)\n",
- " File \"/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/transformers/models/llama/modeling_llama.py\", line 739, in prepare_inputs_for_generation\n",
- " position_ids = position_ids[:, -1].unsqueeze(-1)\n",
- "SystemExit\n"
- ]
- },
- {
- "data": {
- "text/html": [
- "╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮\n",
- "│ /tmp/ipykernel_13699/3633147670.py:1 in <module> │\n",
- "│ │\n",
- "│ [Errno 2] No such file or directory: '/tmp/ipykernel_13699/3633147670.py' │\n",
- "│ │\n",
- "│ /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/chains/ │\n",
- "│ base.py:241 in run │\n",
- "│ │\n",
- "│ 238 │ │ │ return self(args[0], callbacks=callbacks)[self.output_keys[0]] │\n",
- "│ 239 │ │ │\n",
- "│ 240 │ │ if kwargs and not args: │\n",
- "│ ❱ 241 │ │ │ return self(kwargs, callbacks=callbacks)[self.output_keys[0]] │\n",
- "│ 242 │ │ │\n",
- "│ 243 │ │ raise ValueError( │\n",
- "│ 244 │ │ │ f\"`run` supported with either positional arguments or keyword arguments\" │\n",
- "│ │\n",
- "│ /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/chains/ │\n",
- "│ base.py:142 in __call__ │\n",
- "│ │\n",
- "│ 139 │ │ │ ) │\n",
- "│ 140 │ │ except (KeyboardInterrupt, Exception) as e: │\n",
- "│ 141 │ │ │ run_manager.on_chain_error(e) │\n",
- "│ ❱ 142 │ │ │ raise e │\n",
- "│ 143 │ │ run_manager.on_chain_end(outputs) │\n",
- "│ 144 │ │ return self.prep_outputs(inputs, outputs, return_only_outputs) │\n",
- "│ 145 │\n",
- "│ │\n",
- "│ /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/chains/ │\n",
- "│ base.py:136 in __call__ │\n",
- "│ │\n",
- "│ 133 │ │ ) │\n",
- "│ 134 │ │ try: │\n",
- "│ 135 │ │ │ outputs = ( │\n",
- "│ ❱ 136 │ │ │ │ self._call(inputs, run_manager=run_manager) │\n",
- "│ 137 │ │ │ │ if new_arg_supported │\n",
- "│ 138 │ │ │ │ else self._call(inputs) │\n",
- "│ 139 │ │ │ ) │\n",
- "│ │\n",
- "│ /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/ │\n",
- "│ agent.py:904 in _call │\n",
- "│ │\n",
- "│ 901 │ │ start_time = time.time() │\n",
- "│ 902 │ │ # We now enter the agent loop (until it returns something). │\n",
- "│ 903 │ │ while self._should_continue(iterations, time_elapsed): │\n",
- "│ ❱ 904 │ │ │ next_step_output = self._take_next_step( │\n",
- "│ 905 │ │ │ │ name_to_tool_map, │\n",
- "│ 906 │ │ │ │ color_mapping, │\n",
- "│ 907 │ │ │ │ inputs, │\n",
- "│ │\n",
- "│ /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/ │\n",
- "│ agent.py:748 in _take_next_step │\n",
- "│ │\n",
- "│ 745 │ │ │ ) │\n",
- "│ 746 │ │ except Exception as e: │\n",
- "│ 747 │ │ │ if not self.handle_parsing_errors: │\n",
- "│ ❱ 748 │ │ │ │ raise e │\n",
- "│ 749 │ │ │ text = str(e).split(\"`\")[1] │\n",
- "│ 750 │ │ │ observation = \"Invalid or incomplete response\" │\n",
- "│ 751 │ │ │ output = AgentAction(\"_Exception\", observation, text) │\n",
- "│ │\n",
- "│ /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/ │\n",
- "│ agent.py:741 in _take_next_step │\n",
- "│ │\n",
- "│ 738 │ │ \"\"\" │\n",
- "│ 739 │ │ try: │\n",
- "│ 740 │ │ │ # Call the LLM to see what to do. │\n",
- "│ ❱ 741 │ │ │ output = self.agent.plan( │\n",
- "│ 742 │ │ │ │ intermediate_steps, │\n",
- "│ 743 │ │ │ │ callbacks=run_manager.get_child() if run_manager else None, │\n",
- "│ 744 │ │ │ │ **inputs, │\n",
- "│ │\n",
- "│ /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/ │\n",
- "│ agent.py:426 in plan │\n",
- "│ │\n",
- "│ 423 │ │ \"\"\" │\n",
- "│ 424 │ │ full_inputs = self.get_full_inputs(intermediate_steps, **kwargs) │\n",
- "│ 425 │ │ full_output = self.llm_chain.predict(callbacks=callbacks, **full_inputs) │\n",
- "│ ❱ 426 │ │ return self.output_parser.parse(full_output) │\n",
- "│ 427 │ │\n",
- "│ 428 │ async def aplan( │\n",
- "│ 429 │ │ self, │\n",
- "│ │\n",
- "│ /media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/ │\n",
- "│ mrkl/output_parser.py:26 in parse │\n",
- "│ │\n",
- "│ 23 │ │ ) │\n",
- "│ 24 │ │ match = re.search(regex, text, re.DOTALL) │\n",
- "│ 25 │ │ if not match: │\n",
- "│ ❱ 26 │ │ │ raise OutputParserException(f\"Could not parse LLM output: `{text}`\") │\n",
- "│ 27 │ │ action = match.group(1).strip() │\n",
- "│ 28 │ │ action_input = match.group(2) │\n",
- "│ 29 │ │ return AgentAction(action, action_input.strip(\" \").strip('\"'), text) │\n",
- "╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\n",
- "OutputParserException: Could not parse LLM output: \n",
- "`������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�����������������������������������������������������������������������������`\n",
- "\n"
- ],
- "text/plain": [
- "\u001b[31m╭─\u001b[0m\u001b[31m──────────────────────────────\u001b[0m\u001b[31m \u001b[0m\u001b[1;31mTraceback \u001b[0m\u001b[1;2;31m(most recent call last)\u001b[0m\u001b[31m \u001b[0m\u001b[31m───────────────────────────────\u001b[0m\u001b[31m─╮\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/tmp/ipykernel_13699/\u001b[0m\u001b[1;33m3633147670.py\u001b[0m:\u001b[94m1\u001b[0m in \u001b[92m\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[3;31m[Errno 2] No such file or directory: '/tmp/ipykernel_13699/3633147670.py'\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/chains/\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[1;33mbase.py\u001b[0m:\u001b[94m241\u001b[0m in \u001b[92mrun\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m238 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m \u001b[96mself\u001b[0m(args[\u001b[94m0\u001b[0m], callbacks=callbacks)[\u001b[96mself\u001b[0m.output_keys[\u001b[94m0\u001b[0m]] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m239 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m240 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m kwargs \u001b[95mand\u001b[0m \u001b[95mnot\u001b[0m args: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m241 \u001b[2m│ │ │ \u001b[0m\u001b[94mreturn\u001b[0m \u001b[96mself\u001b[0m(kwargs, callbacks=callbacks)[\u001b[96mself\u001b[0m.output_keys[\u001b[94m0\u001b[0m]] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m242 \u001b[0m\u001b[2m│ │ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m243 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mraise\u001b[0m \u001b[96mValueError\u001b[0m( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m244 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[33mf\u001b[0m\u001b[33m\"\u001b[0m\u001b[33m`run` supported with either positional arguments or keyword arguments\u001b[0m\u001b[33m\"\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/chains/\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[1;33mbase.py\u001b[0m:\u001b[94m142\u001b[0m in \u001b[92m__call__\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m139 \u001b[0m\u001b[2m│ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m140 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mexcept\u001b[0m (\u001b[96mKeyboardInterrupt\u001b[0m, \u001b[96mException\u001b[0m) \u001b[94mas\u001b[0m e: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m141 \u001b[0m\u001b[2m│ │ │ \u001b[0mrun_manager.on_chain_error(e) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m142 \u001b[2m│ │ │ \u001b[0m\u001b[94mraise\u001b[0m e \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m143 \u001b[0m\u001b[2m│ │ \u001b[0mrun_manager.on_chain_end(outputs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m144 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m \u001b[96mself\u001b[0m.prep_outputs(inputs, outputs, return_only_outputs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m145 \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/chains/\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[1;33mbase.py\u001b[0m:\u001b[94m136\u001b[0m in \u001b[92m__call__\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m133 \u001b[0m\u001b[2m│ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m134 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mtry\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m135 \u001b[0m\u001b[2m│ │ │ \u001b[0moutputs = ( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m136 \u001b[2m│ │ │ │ \u001b[0m\u001b[96mself\u001b[0m._call(inputs, run_manager=run_manager) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m137 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94mif\u001b[0m new_arg_supported \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m138 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m\u001b[94melse\u001b[0m \u001b[96mself\u001b[0m._call(inputs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m139 \u001b[0m\u001b[2m│ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[1;33magent.py\u001b[0m:\u001b[94m904\u001b[0m in \u001b[92m_call\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m901 \u001b[0m\u001b[2m│ │ \u001b[0mstart_time = time.time() \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m902 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[2m# We now enter the agent loop (until it returns something).\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m903 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mwhile\u001b[0m \u001b[96mself\u001b[0m._should_continue(iterations, time_elapsed): \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m904 \u001b[2m│ │ │ \u001b[0mnext_step_output = \u001b[96mself\u001b[0m._take_next_step( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m905 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mname_to_tool_map, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m906 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mcolor_mapping, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m907 \u001b[0m\u001b[2m│ │ │ │ \u001b[0minputs, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[1;33magent.py\u001b[0m:\u001b[94m748\u001b[0m in \u001b[92m_take_next_step\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m745 \u001b[0m\u001b[2m│ │ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m746 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mexcept\u001b[0m \u001b[96mException\u001b[0m \u001b[94mas\u001b[0m e: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m747 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m \u001b[96mself\u001b[0m.handle_parsing_errors: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m748 \u001b[2m│ │ │ │ \u001b[0m\u001b[94mraise\u001b[0m e \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m749 \u001b[0m\u001b[2m│ │ │ \u001b[0mtext = \u001b[96mstr\u001b[0m(e).split(\u001b[33m\"\u001b[0m\u001b[33m`\u001b[0m\u001b[33m\"\u001b[0m)[\u001b[94m1\u001b[0m] \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m750 \u001b[0m\u001b[2m│ │ │ \u001b[0mobservation = \u001b[33m\"\u001b[0m\u001b[33mInvalid or incomplete response\u001b[0m\u001b[33m\"\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m751 \u001b[0m\u001b[2m│ │ │ \u001b[0moutput = AgentAction(\u001b[33m\"\u001b[0m\u001b[33m_Exception\u001b[0m\u001b[33m\"\u001b[0m, observation, text) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[1;33magent.py\u001b[0m:\u001b[94m741\u001b[0m in \u001b[92m_take_next_step\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m738 \u001b[0m\u001b[2;33m│ │ \u001b[0m\u001b[33m\"\"\"\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m739 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mtry\u001b[0m: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m740 \u001b[0m\u001b[2m│ │ │ \u001b[0m\u001b[2m# Call the LLM to see what to do.\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m741 \u001b[2m│ │ │ \u001b[0moutput = \u001b[96mself\u001b[0m.agent.plan( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m742 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mintermediate_steps, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m743 \u001b[0m\u001b[2m│ │ │ │ \u001b[0mcallbacks=run_manager.get_child() \u001b[94mif\u001b[0m run_manager \u001b[94melse\u001b[0m \u001b[94mNone\u001b[0m, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m744 \u001b[0m\u001b[2m│ │ │ │ \u001b[0m**inputs, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[1;33magent.py\u001b[0m:\u001b[94m426\u001b[0m in \u001b[92mplan\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m423 \u001b[0m\u001b[2;33m│ │ \u001b[0m\u001b[33m\"\"\"\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m424 \u001b[0m\u001b[2m│ │ \u001b[0mfull_inputs = \u001b[96mself\u001b[0m.get_full_inputs(intermediate_steps, **kwargs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m425 \u001b[0m\u001b[2m│ │ \u001b[0mfull_output = \u001b[96mself\u001b[0m.llm_chain.predict(callbacks=callbacks, **full_inputs) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m426 \u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m \u001b[96mself\u001b[0m.output_parser.parse(full_output) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m427 \u001b[0m\u001b[2m│ \u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m428 \u001b[0m\u001b[2m│ \u001b[0m\u001b[94masync\u001b[0m \u001b[94mdef\u001b[0m \u001b[92maplan\u001b[0m( \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m429 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[96mself\u001b[0m, \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33m/media/gpt4-pdf-chatbot-langchain/pyenv-langchain/lib/python3.10/site-packages/langchain/agents/\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2;33mmrkl/\u001b[0m\u001b[1;33moutput_parser.py\u001b[0m:\u001b[94m26\u001b[0m in \u001b[92mparse\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m23 \u001b[0m\u001b[2m│ │ \u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m24 \u001b[0m\u001b[2m│ │ \u001b[0mmatch = re.search(regex, text, re.DOTALL) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m25 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mif\u001b[0m \u001b[95mnot\u001b[0m match: \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[31m❱ \u001b[0m26 \u001b[2m│ │ │ \u001b[0m\u001b[94mraise\u001b[0m OutputParserException(\u001b[33mf\u001b[0m\u001b[33m\"\u001b[0m\u001b[33mCould not parse LLM output: `\u001b[0m\u001b[33m{\u001b[0mtext\u001b[33m}\u001b[0m\u001b[33m`\u001b[0m\u001b[33m\"\u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m27 \u001b[0m\u001b[2m│ │ \u001b[0maction = match.group(\u001b[94m1\u001b[0m).strip() \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m28 \u001b[0m\u001b[2m│ │ \u001b[0maction_input = match.group(\u001b[94m2\u001b[0m) \u001b[31m│\u001b[0m\n",
- "\u001b[31m│\u001b[0m \u001b[2m29 \u001b[0m\u001b[2m│ │ \u001b[0m\u001b[94mreturn\u001b[0m AgentAction(action, action_input.strip(\u001b[33m\"\u001b[0m\u001b[33m \u001b[0m\u001b[33m\"\u001b[0m).strip(\u001b[33m'\u001b[0m\u001b[33m\"\u001b[0m\u001b[33m'\u001b[0m), text) \u001b[31m│\u001b[0m\n",
- "\u001b[31m╰──────────────────────────────────────────────────────────────────────────────────────────────────╯\u001b[0m\n",
- "\u001b[1;91mOutputParserException: \u001b[0mCould not parse LLM output: \n",
- "`������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�������������������������������������������������������������������������������������������������������������������\n",
- "�����������������������������������������������������������������������������`\n"
- ]
- },
- "metadata": {},
- "output_type": "display_data"
- }
- ],
- "source": [
- "agent_chain.run(input=\"我们之前聊了什么?\")"
+ "print(generated_data)"
]
},
{
"cell_type": "code",
"execution_count": null,
- "id": "096f0378-b7eb-46b6-9985-95c3f3521ecd",
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "a3c964f3-fb14-40bd-8df9-ae3c452260bb",
- "metadata": {},
- "outputs": [],
- "source": []
- },
- {
- "cell_type": "code",
- "execution_count": null,
- "id": "e31b13c0-af47-4614-93d0-090a69579cc1",
+ "id": "e089a828-b662-4d9a-8d88-4bf95ccadbab",
"metadata": {},
"outputs": [],
"source": []
diff --git a/configs/model_config.py b/configs/model_config.py
index 1ca4932..af29cd6 100644
--- a/configs/model_config.py
+++ b/configs/model_config.py
@@ -91,14 +91,10 @@ llm_model_dict = {
# LLM 名称
LLM_MODEL = "chatglm-6b"
-# 如果你需要加载本地的model，指定这个参数 ` --no-remote-model`，或者下方参数修改为 `True`
-NO_REMOTE_MODEL = False
# 量化加载8bit 模型
LOAD_IN_8BIT = False
# Load the model with bfloat16 precision. Requires NVIDIA Ampere GPU.
BF16 = False
-# 本地模型存放的位置
-MODEL_DIR = "model/"
# 本地lora存放的位置
LORA_DIR = "loras/"
diff --git a/models/loader/args.py b/models/loader/args.py
index 1db7fe9..8e05d20 100644
--- a/models/loader/args.py
+++ b/models/loader/args.py
@@ -35,14 +35,13 @@ parser = argparse.ArgumentParser(prog='langchina-ChatGLM',
description='About langchain-ChatGLM, local knowledge based ChatGLM with langchain ｜ '
'基于本地知识库的 ChatGLM 问答')
-parser.add_argument('--no-remote-model', action='store_true', default=NO_REMOTE_MODEL, help='remote in the model on '
- 'loader checkpoint, '
- 'if your load local '
- 'model to add the ` '
- '--no-remote-model`')
-parser.add_argument('--model', type=str, default=LLM_MODEL, help='Name of the model to load by default.')
+parser.add_argument('--no-remote-model', action='store_true', help='remote in the model on '
+ 'loader checkpoint, '
+ 'if your load local '
+ 'model to add the ` '
+ '--no-remote-model`')
+parser.add_argument('--model-name', type=str, default=LLM_MODEL, help='Name of the model to load by default.')
parser.add_argument('--lora', type=str, help='Name of the LoRA to apply to the model by default.')
-parser.add_argument("--model-dir", type=str, default=MODEL_DIR, help="Path to directory with all the models")
parser.add_argument("--lora-dir", type=str, default=LORA_DIR, help="Path to directory with all the loras")
# Accelerate/transformers
diff --git a/models/loader/loader.py b/models/loader/loader.py
index 47c365b..c68e71a 100644
--- a/models/loader/loader.py
+++ b/models/loader/loader.py
@@ -26,7 +26,6 @@ class LoaderCheckPoint:
model: object = None
model_config: object = None
lora_names: set = []
- model_dir: str = None
lora_dir: str = None
ptuning_dir: str = None
use_ptuning_v2: bool = False
@@ -45,28 +44,30 @@ class LoaderCheckPoint:
模型初始化
:param params:
"""
- self.model_path = None
self.model = None
self.tokenizer = None
self.params = params or {}
+ self.model_name = params.get('model_name', False)
+ self.model_path = params.get('model_path', None)
self.no_remote_model = params.get('no_remote_model', False)
- self.model_name = params.get('model', '')
self.lora = params.get('lora', '')
self.use_ptuning_v2 = params.get('use_ptuning_v2', False)
- self.model_dir = params.get('model_dir', '')
self.lora_dir = params.get('lora_dir', '')
self.ptuning_dir = params.get('ptuning_dir', 'ptuning-v2')
self.load_in_8bit = params.get('load_in_8bit', False)
self.bf16 = params.get('bf16', False)
def _load_model_config(self, model_name):
- checkpoint = Path(f'{self.model_dir}/{model_name}')
if self.model_path:
checkpoint = Path(f'{self.model_path}')
else:
if not self.no_remote_model:
checkpoint = model_name
+ else:
+ raise ValueError(
+ "本地模型local_model_path未配置路径"
+ )
model_config = AutoConfig.from_pretrained(checkpoint, trust_remote_code=True)
@@ -81,16 +82,17 @@ class LoaderCheckPoint:
print(f"Loading {model_name}...")
t0 = time.time()
- checkpoint = Path(f'{self.model_dir}/{model_name}')
-
- self.is_llamacpp = len(list(checkpoint.glob('ggml*.bin'))) > 0
-
if self.model_path:
checkpoint = Path(f'{self.model_path}')
else:
if not self.no_remote_model:
checkpoint = model_name
+ else:
+ raise ValueError(
+ "本地模型local_model_path未配置路径"
+ )
+ self.is_llamacpp = len(list(Path(f'{checkpoint}').glob('ggml*.bin'))) > 0
if 'chatglm' in model_name.lower():
LoaderClass = AutoModel
else:
@@ -274,13 +276,16 @@ class LoaderCheckPoint:
"`pip install bitsandbytes``pip install accelerate`."
) from exc
- checkpoint = Path(f'{self.model_dir}/{model_name}')
-
if self.model_path:
checkpoint = Path(f'{self.model_path}')
else:
if not self.no_remote_model:
checkpoint = model_name
+ else:
+ raise ValueError(
+ "本地模型local_model_path未配置路径"
+ )
+
cls = get_class_from_dynamic_module(class_reference="fnlp/moss-moon-003-sft--modeling_moss.MossForCausalLM",
pretrained_model_name_or_path=checkpoint)