检查其他资源

• 我为这个问题添加了一个非常描述性的标题。
• 我在LangChain文档中使用集成搜索进行搜索。
• 我使用GitHub搜索找到了一个类似的问题，但没有找到。
• 我确信这是LangChain中的一个bug,而不是我的代码。
• 通过更新到LangChain的最新稳定版本(或特定集成包)无法解决此bug。

示例代码

import os
import json
from pathlib import Path
from langchain_community.cache import SQLiteCache
from typing import Callable, List

model_list = [
    'ChatAnthropic',  # <- has several instance of this bug, not only SQLiteCache
    'ChatBaichuan',
    'ChatCohere',
    'ChatCoze',
    'ChatDeepInfra',
    'ChatEverlyAI',
    'ChatFireworks',
    'ChatFriendli',
    'ChatGooglePalm',
    'ChatHunyuan',
    'ChatLiteLLM',
    'ChatOctoAI',
    'ChatOllama',
    'ChatOpenAI',
    'ChatPerplexity',
    'ChatYuan2',
    'ChatZhipuAI'

    # Below are the models I didn't test, as well as the reason why I haven't
    # 'ChatAnyscale',  # needs a model name
    # 'ChatDatabricks',  # needs some params
    # 'ChatHuggingFace',  # needs a modelname
    # 'ChatJavelinAIGateway',  # needs some params
    # 'ChatKinetica',  # not installed
    # 'ChatKonko',  # not installed
    # 'ChatLiteLLMRouter',  # needs router arg
    # 'ChatLlamaCpp',  #needs some params
    # 'ChatMLflowAIGateway',  # not installed
    # 'ChatMaritalk',  # needs some params
    # 'ChatMlflow',  # not installed
    # 'ChatMLX',  # needs some params
    # 'ChatPremAI',  # not installed
    # 'ChatSparkLLM',  # issue with api key
    # 'ChatTongyi',  # not installed
    # 'ChatVertexAI',  # not insalled
    # 'ChatYandexGPT',  # needs some params
]

# import the models
for m in model_list:
    exec(f"from langchain_community.chat_models import {m}")

# set fake api keys
for m in model_list:
    backend = m[4:].upper()
    os.environ[f"{backend}_API_KEY"] = "aaaaaa"
    os.environ[f"{backend}_API_TOKEN"] = "aaaaaa"
    os.environ[f"{backend}_TOKEN"] = "aaaaaa"
os.environ["GOOGLE_API_KEY"] = "aaaaaa"
os.environ["HUNYUAN_APP_ID"] = "aaaaaa"
os.environ["HUNYUAN_SECRET_ID"] = "aaaaaa"
os.environ["HUNYUAN_SECRET_KEY"] = "aaaaaa"
os.environ["PPLX_API_KEY"] = "aaaaaa"
os.environ["IFLYTEK_SPARK_APP_ID"] = "aaaaaa"
os.environ["SPARK_API_KEY"] = "aaaaaa"
os.environ["DASHSCOPE_API_KEY"] = "aaaaaa"
os.environ["YC_API_KEY"] = "aaaaaa"

# create two brand new cache
Path("test_cache.db").unlink(missing_ok=True)
c1 = SQLiteCache(database_path="test_cache.db")
c2 = SQLiteCache(database_path="test_cache.db")

def recur_dict_check(val: dict) -> List[str]:
    "find which object is causing the issue"
    found = []
    for k, v in val.items():
        if " object at " in str(v):
            if isinstance(v, dict):
                found.append(recur_dict_check(v))
            else:
                found.append(v)
    # flatten the list
    out = []
    for f in found:
        if isinstance(f, list):
            out.extend(f)
        else:
            out.append(f)
    assert out
    out = [str(o) for o in out]
    return out

def check(chat_model: Callable, verbose: bool = False) -> bool:
    "check a given chatmodel"
    llm1 = chat_model(
        cache=c1,
        )
    llm2 = chat_model(
        cache=c2,
    )
    backend = llm1.get_lc_namespace()[-1]
 
    str1 = llm1._get_llm_string().split("---")[0]
    str2 = llm2._get_llm_string().split("---")[0]

    if verbose:
        print(f"LLM1:\n{str1}")
        print(f"LLM2:\n{str2}")

    if str1 == str2:
        print(f"{backend.title()} does not have the bug")
        return True
    else:
        print(f"{backend.title()} HAS the bug")
        j1, j2 = json.loads(str1), json.loads(str2)
        assert j1.keys() == j2.keys()
        diff1 = recur_dict_check(j1)
        diff2 = recur_dict_check(j2)
        assert len(diff1) == len(diff2)
        diffs = [str(v).split("object at ")[0] for v in diff1 + diff2]
        assert all(diffs.count(elem) == 2 for elem in diffs)

        print(f"List of buggy objects for model {backend.title()}:")
        for d in diff1:
            print(f"    - {d}")

        # for k, v in j1

        return False

failed = []
for model in model_list:
    if not check(locals()[model]):
        failed.append(model)

print(f"The culprit is at least SQLiteCache repr string:\n{c1}\n{c2}")
c1.__class__.__repr__ = lambda x=None : "<langchain_community.cache.SQLiteCache>"
c2.__class__.__repr__ = lambda x=None : "<langchain_community.cache.SQLiteCache>"
print(f"Now fixed:\n{c1}\n{c2}\n")

# Anthropic still has issues
assert not check(locals()["ChatAnthropic"])

for model in failed:
    if model == "ChatAnthropic":  # anthropic actually has more issues!
        continue
    assert check(locals()[model]), model
print("Fixed it for most models!")

print(f"Models with the issue: {len(failed)} / {len(model_list)}")
for f in failed:
    print(f"    - {f}")

错误信息和堆栈跟踪(如果适用)

• 无响应*

描述

受到this bug的影响，在my DocToolsLLM project中，我最终使用了ChatOpenAI,而不仅仅是ChatLiteLLM,如果模型无论如何都是由openai提供的。
有一天我注意到我的SQLiteCcache系统地被ChatOpenAI忽略，最后找出了罪魁祸首：

• 要判断缓存中是否存在值，需要使用提示和描述LLM的字符串字符。
• 用于描述LLM的方法是_get_llm_string()
• 此方法在聊天模型中的实现不一致，导致输出包含未过滤的repr对象，例如缓存、回调等。
• 问题在于，对于许多示例，repr返回类似于<langchain_community.cache.SQLiteCache object at SOME_ADRESS>的内容。
• 我发现手动设置这些对象超类的repr是一个可行的解决方法。

为了帮助您尽快解决此问题，我编写了一个循环，检查所有聊天模型并告诉您哪个示例导致了问题。

系统信息

python -m langchain_core.sys_info

系统信息

操作系统：Linux
OS版本：#35 ~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Tue May 7 09:00:52 UTC 2
Python版本：3.11.7 (main, Jun 12 2024, 12:57:34) [GCC 11.4.0]

软件包信息

langchain_core: 0.2.7
langchain: 0.2.5
langchain_community: 0.2.5
langsmith: 0.1.77
langchain_mistralai: 0.1.8
langchain_openai: 0.1.8
langchain_text_splitters: 0.2.1

没有安装的软件包(不一定是个问题)

以下软件包未找到：
langgraph
langserve