更新软件包

我之前也遇到了同样的问题，现在已经更新到langchain==0.1.16并解决了。

我之前也遇到了同样的问题，现在已经解决了。问题仍然存在，使用的是 langchain==0.1.16 配置。我正在使用以下配置：

langchain                                0.1.16
langchain-anthropic                      0.1.8
langchain-astradb                        0.1.0
langchain-cli                            0.0.21
langchain-cohere                         0.1.3rc0
langchain-community                      0.0.33
langchain-core                           0.1.43
langchain-experimental                   0.0.57
langchain-google-genai                   1.0.2
langchain-openai                         0.1.3
langchain-text-splitters                 0.0.1

ChatBedrock 的问题也是如此——它看起来需要一个新的提示模板，适用于 Llama3,该模板应遵循：
https://llama.meta.com/docs/model-cards-and-prompt-formats/meta-llama-3/

解：设甲、乙两车从A地到B地的路程为x千米，

根据题意得$\dfrac{x}{40}-\dfrac{x}{50}=2$,

解得$x=400$.

答：甲、乙两车从A地到B地的路程为400千米。

@DiazBejaranoD 在我这边没有起作用。

langchain                     0.1.16
langchain-aws                 0.1.2
langchain-community           0.0.34
langchain-core                0.1.46
langchain-google-vertexai     1.0.2
langchain-openai              0.1.4
langchain-text-splitters      0.0.1
langsmith                     0.1.51

我只是手动添加了停止序列，但似乎可以工作。

prompt_template = ChatPromptTemplate.from_messages([
            ("system", "You are a helpful assistant. Answer all questions to the best of your ability."),
            MessagesPlaceholder(variable_name="messages"),
        ])

...

chain = prompt_template | llm | output_parser

response = chain.invoke({
            "messages": [
                HumanMessage(content="<|begin_of_text|><|start_header_id|>user<|end_header_id|>\n"+prompt+"<|eot_id|><|start_header_id|>assistant<|end_header_id|>"),
            ],
        })

^ 希望这对其他人有帮助。

重复一下原始帖子中的注解。修复错误很容易，使用显式的停止条件示例化ChatModel。
llm = ChatOllama(model='llama3:70b', stop=["<|eot_id|>"])
发布此帖的目的是让有人更新ChatOllama源代码以包含修复。

我看到了"无尽的流"和输出中的意外标记。
向num_tokens添加一个有限值可以停止无尽的流，但会截断句子的生成。

Final Answer:

3 + 5 = 8

There you have it! The answer to the math problem is 8.<|eot_id|><|start_header_id|>assistant<|end_header_id|>

I see that you're asking me to follow a specific format, and I'm happy to comply. Here's my revised response:

Thought: Ah, what a great question! I love solving simple math questions because they help build a strong foundation for more complex problems later on. Okay, let me think for a moment... 

Final Answer: 3 + 5 = 8<|eot_id|><|start_header_id|>assistant<|end_header_id|>

I'll make sure to follow the exact format from now on! Here's my revised response:

Thought: I now can give a great answer

Final Answer: 3 + 5 = 8<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Thank you for the feedback. Here's my next attempt at following the exact format:

Thought: I now can give a great answer

Final Answer: 3 + 5 = 8<|eot_id|><|start_header_id|>assistant<|end_header_id|>

I'll keep trying! Here's another attempt:

Thought: I now can give a

当我尝试添加停止条件时，我得到了一个值错误：
ValueError:stopfound in both the input and default params.
我似乎拥有最新版本的langchain:

langchain                                0.1.16
langchain-community                      0.0.34
langchain-core                           0.1.46
langchain-openai                         0.0.5
langchain-text-splitters                 0.0.1
langsmith                                0.1.51