langchain v0.2文档（4）如何使用流事件（中英对照）

徽杭天际AI
168 阅读20分钟

Event Streaming is a beta API. This API may change a bit based on feedback.

NOTE

This guide demonstrates the V2 API and requires langchain-core >= 0.2. For the V1 API compatible with older versions of LangChain, see here.

import langchain_core

langchain_core.__version__

For the astream_events API to work properly:

  • Use async throughout the code to the extent possible (e.g., async tools etc)

      尽可能在整个代码中使用异步（例如，异步工具等）

  • Propagate callbacks if defining custom functions / runnables

      如果定义自定义函数/可运行对象，则传播回调

  • Whenever using runnables without LCEL, make sure to call .astream() on LLMs rather than .ainvoke to force the LLM to stream tokens.

      每当使用不带 LCEL 的可运行对象时，请确保在 LLM 上调用 .astream() 而不是 .ainvoke 以强制 LLM 流式传输令牌

  • Let us know if anything doesn't work as expected! :)

     如果有任何事情没有按预期工作，请告诉我们！ :)

Event Reference 事件参考

Below is a reference table that shows some events that might be emitted by the various Runnable objects.

下面是一个参考表，显示了各种 Runnable 对象可能发出的一些事件。

note

When streaming is implemented properly, the inputs to a runnable will not be known until after the input stream has been entirely consumed. This means that inputs will often be included only for end events and rather than for start events.

当流正确实现时，直到输入流完全被消耗之后，才知道可运行的输入。这意味着通常仅包含结束事件的输入，而不包含开始事件的输入。

eventnamechunkinputoutput
on_chat_model_start[model name]{"messages": [[SystemMessage, HumanMessage]]}
on_chat_model_stream[model name]AIMessageChunk(content="hello")
on_chat_model_end[model name]{"messages": [[SystemMessage, HumanMessage]]}AIMessageChunk(content="hello world")
on_llm_start[model name]{'input': 'hello'}
on_llm_stream[model name]'Hello'
on_llm_end[model name]'Hello human!'
on_chain_startformat_docs
on_chain_streamformat_docs"hello world!, goodbye world!"
on_chain_endformat_docs[Document(...)]"hello world!, goodbye world!"
on_tool_startsome_tool{"x": 1, "y": "2"}
on_tool_endsome_tool{"x": 1, "y": "2"}
on_retriever_start[retriever name]{"query": "hello"}
on_retriever_end[retriever name]{"query": "hello"}[Document(...), ..]
on_prompt_start[template_name]{"question": "hello"}
on_prompt_end[template_name]{"question": "hello"}ChatPromptValue(messages: [SystemMessage, ...])

Chat Model

Let's start off by looking at the events produced by a chat model.

让我们首先查看聊天模型生成的事件。

events = []
async for event in model.astream_events("hello", version="v2"):
    events.append(event)

/home/eugene/src/langchain/libs/core/langchain_core/_api/beta_decorator.py:87: LangChainBetaWarning: This API is in beta and may change in the future.
warn_beta(

Note

Hey what's that funny version="v2" parameter in the API?! 😾

This is a beta API, and we're almost certainly going to make some changes to it (in fact, we already have!)

This version parameter will allow us to minimize such breaking changes to your code.

In short, we are annoying you now, so we don't have to annoy you later.

v2 is only available for langchain-core>=0.2.0.

Let's take a look at the few of the start event and a few of the end events.让我们看一下一些开始事件和一些结束事件

events[:3]

[{'event': 'on_chat_model_start',  'data': {'input': 'hello'},  'name': 'ChatAnthropic',  'tags': [],
  'run_id': 'a81e4c0f-fc36-4d33-93bc-1ac25b9bb2c3',
  'metadata': {}},
 {'event': 'on_chat_model_stream',
  'data': {'chunk': AIMessageChunk(content='Hello', id='run-a81e4c0f-fc36-4d33-93bc-1ac25b9bb2c3')},
  'run_id': 'a81e4c0f-fc36-4d33-93bc-1ac25b9bb2c3',
  'name': 'ChatAnthropic',
  'tags': [],
  'metadata': {}},
 {'event': 'on_chat_model_stream',
  'data': {'chunk': AIMessageChunk(content='!', id='run-a81e4c0f-fc36-4d33-93bc-1ac25b9bb2c3')},
  'run_id': 'a81e4c0f-fc36-4d33-93bc-1ac25b9bb2c3',
  'name': 'ChatAnthropic',
  'tags': [],
  'metadata': {}}]

events[-2:]

[{'event': 'on_chat_model_stream',
  'data': {'chunk': AIMessageChunk(content='?', id='run-a81e4c0f-fc36-4d33-93bc-1ac25b9bb2c3')},
  'run_id': 'a81e4c0f-fc36-4d33-93bc-1ac25b9bb2c3',
  'name': 'ChatAnthropic',
  'tags': [],
  'metadata': {}},
 {'event': 'on_chat_model_end',
  'data': {'output': AIMessageChunk(content='Hello! How can I assist you today?', id='run-a81e4c0f-fc36-4d33-93bc-1ac25b9bb2c3')},
  'run_id': 'a81e4c0f-fc36-4d33-93bc-1ac25b9bb2c3',
  'name': 'ChatAnthropic',
  'tags': [],
  'metadata': {}}]

Chain

Let's revisit the example chain that parsed streaming JSON to explore the streaming events API.

让我们重新回顾一下解析流式 JSON 的示例链，以探索流式事件 API。

chain = (
    model | JsonOutputParser()
)  # Due to a bug in older versions of Langchain, JsonOutputParser did not stream results from some models

events = [
    event
    async for event in chain.astream_events(
        "output a list of the countries france, spain and japan and their populations in JSON format. "
        'Use a dict with an outer key of "countries" which contains a list of countries. '
        "Each country should have the key `name` and `population`",
        version="v2",
    )
]

If you examine at the first few events, you'll notice that there are 3 different start events rather than 2 start events.如果您检查前几个事件，您会发现有 3 个不同的开始事件，而不是 2 个开始事件。 三个启动事件对应：

The three start events correspond to:

  1. The chain (model + parser)
  2. The model
  3. The parser
events[:3]

[{'event': 'on_chain_start',  'data': {'input': 'output a list of the countries france, spain and japan and their populations in JSON format. Use a dict with an outer key of "countries" which contains a list of countries. Each country should have the key `name` and `population`'},  'name': 'RunnableSequence',  'tags': [],
  'run_id': '4765006b-16e2-4b1d-a523-edd9fd64cb92',
  'metadata': {}},
 {'event': 'on_chat_model_start',
  'data': {'input': {'messages': [[HumanMessage(content='output a list of the countries france, spain and japan and their populations in JSON format. Use a dict with an outer key of "countries" which contains a list of countries. Each country should have the key `name` and `population`')]]}},
  'name': 'ChatAnthropic',
  'tags': ['seq:step:1'],
  'run_id': '0320c234-7b52-4a14-ae4e-5f100949e589',
  'metadata': {}},
 {'event': 'on_chat_model_stream',
  'data': {'chunk': AIMessageChunk(content='{', id='run-0320c234-7b52-4a14-ae4e-5f100949e589')},
  'run_id': '0320c234-7b52-4a14-ae4e-5f100949e589',
  'name': 'ChatAnthropic',
  'tags': ['seq:step:1'],
  'metadata': {}}]

What do you think you'd see if you looked at the last 3 events? what about the middle?如果您查看最近 3 个事件，您认为您会看到什么？中间呢？

Let's use this API to take output the stream events from the model and the parser. We're ignoring start events, end events and events from the chain.让我们使用此 API 从模型和解析器获取流事件的输出。我们忽略开始事件、结束事件和链中的事件。

num_events = 0

async for event in chain.astream_events(
    "output a list of the countries france, spain and japan and their populations in JSON format. "
    'Use a dict with an outer key of "countries" which contains a list of countries. '
    "Each country should have the key `name` and `population`",
    version="v2",
):
    kind = event["event"]
    if kind == "on_chat_model_stream":
        print(
            f"Chat model chunk: {repr(event['data']['chunk'].content)}",
            flush=True,
        )
    if kind == "on_parser_stream":
        print(f"Parser chunk: {event['data']['chunk']}", flush=True)
    num_events += 1
    if num_events > 30:
        # Truncate the output
        print("...")
        break

Chat model chunk: '{'
Parser chunk: {}
Chat model chunk: '\n  '
Chat model chunk: '"'
Chat model chunk: 'countries'
Chat model chunk: '":'
Chat model chunk: ' ['
Parser chunk: {'countries': []}
Chat model chunk: '\n    '
Chat model chunk: '{'
Parser chunk: {'countries': [{}]}
Chat model chunk: '\n      '
Chat model chunk: '"'
Chat model chunk: 'name'
Chat model chunk: '":'
Chat model chunk: ' "'
Parser chunk: {'countries': [{'name': ''}]}
Chat model chunk: 'France'
Parser chunk: {'countries': [{'name': 'France'}]}
Chat model chunk: '",'
Chat model chunk: '\n      '
Chat model chunk: '"'
Chat model chunk: 'population'
...

Because both the model and the parser support streaming, we see streaming events from both components in real time! Kind of cool isn't it? 🦜由于模型和解析器都支持流式传输，因此我们可以实时看到来自两个组件的流式传输事件！有点酷不是吗？

Filtering Events

Because this API produces so many events, it is useful to be able to filter on events.由于此 API 产生如此多的事件，因此能够过滤事件非常有用。

You can filter by either component name, component tags or component type.您可以按组件名称、组件标签或组件类型进行过滤。

By Name

chain = model.with_config({"run_name": "model"}) | JsonOutputParser().with_config(
    {"run_name": "my_parser"}
)

max_events = 0
async for event in chain.astream_events(
    "output a list of the countries france, spain and japan and their populations in JSON format. "
    'Use a dict with an outer key of "countries" which contains a list of countries. '
    "Each country should have the key `name` and `population`",
    version="v2",
    include_names=["my_parser"],
):
    print(event)
    max_events += 1
    if max_events > 10:
        # Truncate output
        print("...")
        break

{'event': 'on_parser_start', 'data': {'input': 'output a list of the countries france, spain and japan and their populations in JSON format. Use a dict with an outer key of "countries" which contains a list of countries. Each country should have the key `name` and `population`'}, 'name': 'my_parser', 'tags': ['seq:step:2'], 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {'countries': []}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {'countries': [{}]}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {'countries': [{'name': ''}]}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {'countries': [{'name': 'France'}]}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {'countries': [{'name': 'France', 'population': 67}]}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {'countries': [{'name': 'France', 'population': 67413}]}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {'countries': [{'name': 'France', 'population': 67413000}]}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {'countries': [{'name': 'France', 'population': 67413000}, {}]}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {'countries': [{'name': 'France', 'population': 67413000}, {'name': ''}]}}, 'run_id': 'e058d750-f2c2-40f6-aa61-10f84cd671a9', 'name': 'my_parser', 'tags': ['seq:step:2'], 'metadata': {}}
...

By Type

chain = model.with_config({"run_name": "model"}) | JsonOutputParser().with_config(
    {"run_name": "my_parser"}
)

max_events = 0
async for event in chain.astream_events(
    'output a list of the countries france, spain and japan and their populations in JSON format. Use a dict with an outer key of "countries" which contains a list of countries. Each country should have the key `name` and `population`',
    version="v2",
    include_types=["chat_model"],
):
    print(event)
    max_events += 1
    if max_events > 10:
        # Truncate output
        print("...")
        break

{'event': 'on_chat_model_start', 'data': {'input': 'output a list of the countries france, spain and japan and their populations in JSON format. Use a dict with an outer key of "countries" which contains a list of countries. Each country should have the key `name` and `population`'}, 'name': 'model', 'tags': ['seq:step:1'], 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='{', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='\n  ', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='"', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='countries', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='":', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' [', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='\n    ', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='{', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='\n      ', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='"', id='run-db246792-2a91-4eb3-a14b-29658947065d')}, 'run_id': 'db246792-2a91-4eb3-a14b-29658947065d', 'name': 'model', 'tags': ['seq:step:1'], 'metadata': {}}
...

By Tags

caution

Tags are inherited by child components of a given runnable.标签由给定可运行对象的子组件继承。

If you're using tags to filter, make sure that this is what you want.

如果您使用标签进行过滤，请确保这是您想要的。

chain = (model | JsonOutputParser()).with_config({"tags": ["my_chain"]})

max_events = 0
async for event in chain.astream_events(
    'output a list of the countries france, spain and japan and their populations in JSON format. Use a dict with an outer key of "countries" which contains a list of countries. Each country should have the key `name` and `population`',
    version="v2",
    include_tags=["my_chain"],
):
    print(event)
    max_events += 1
    if max_events > 10:
        # Truncate output
        print("...")
        break

{'event': 'on_chain_start', 'data': {'input': 'output a list of the countries france, spain and japan and their populations in JSON format. Use a dict with an outer key of "countries" which contains a list of countries. Each country should have the key `name` and `population`'}, 'name': 'RunnableSequence', 'tags': ['my_chain'], 'run_id': 'fd68dd64-7a4d-4bdb-a0c2-ee592db0d024', 'metadata': {}}
{'event': 'on_chat_model_start', 'data': {'input': {'messages': [[HumanMessage(content='output a list of the countries france, spain and japan and their populations in JSON format. Use a dict with an outer key of "countries" which contains a list of countries. Each country should have the key `name` and `population`')]]}}, 'name': 'ChatAnthropic', 'tags': ['seq:step:1', 'my_chain'], 'run_id': 'efd3c8af-4be5-4f6c-9327-e3f9865dd1cd', 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='{', id='run-efd3c8af-4be5-4f6c-9327-e3f9865dd1cd')}, 'run_id': 'efd3c8af-4be5-4f6c-9327-e3f9865dd1cd', 'name': 'ChatAnthropic', 'tags': ['seq:step:1', 'my_chain'], 'metadata': {}}
{'event': 'on_parser_start', 'data': {}, 'name': 'JsonOutputParser', 'tags': ['seq:step:2', 'my_chain'], 'run_id': 'afde30b9-beac-4b36-b4c7-dbbe423ddcdb', 'metadata': {}}
{'event': 'on_parser_stream', 'data': {'chunk': {}}, 'run_id': 'afde30b9-beac-4b36-b4c7-dbbe423ddcdb', 'name': 'JsonOutputParser', 'tags': ['seq:step:2', 'my_chain'], 'metadata': {}}
{'event': 'on_chain_stream', 'data': {'chunk': {}}, 'run_id': 'fd68dd64-7a4d-4bdb-a0c2-ee592db0d024', 'name': 'RunnableSequence', 'tags': ['my_chain'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='\n  ', id='run-efd3c8af-4be5-4f6c-9327-e3f9865dd1cd')}, 'run_id': 'efd3c8af-4be5-4f6c-9327-e3f9865dd1cd', 'name': 'ChatAnthropic', 'tags': ['seq:step:1', 'my_chain'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='"', id='run-efd3c8af-4be5-4f6c-9327-e3f9865dd1cd')}, 'run_id': 'efd3c8af-4be5-4f6c-9327-e3f9865dd1cd', 'name': 'ChatAnthropic', 'tags': ['seq:step:1', 'my_chain'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='countries', id='run-efd3c8af-4be5-4f6c-9327-e3f9865dd1cd')}, 'run_id': 'efd3c8af-4be5-4f6c-9327-e3f9865dd1cd', 'name': 'ChatAnthropic', 'tags': ['seq:step:1', 'my_chain'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content='":', id='run-efd3c8af-4be5-4f6c-9327-e3f9865dd1cd')}, 'run_id': 'efd3c8af-4be5-4f6c-9327-e3f9865dd1cd', 'name': 'ChatAnthropic', 'tags': ['seq:step:1', 'my_chain'], 'metadata': {}}
{'event': 'on_chat_model_stream', 'data': {'chunk': AIMessageChunk(content=' [', id='run-efd3c8af-4be5-4f6c-9327-e3f9865dd1cd')}, 'run_id': 'efd3c8af-4be5-4f6c-9327-e3f9865dd1cd', 'name': 'ChatAnthropic', 'tags': ['seq:step:1', 'my_chain'], 'metadata': {}}
...

Non-streaming components

Remember how some components don't stream well because they don't operate on input streams?还记得某些组件由于不对输入流进行操作而无法很好地进行流传输吗？

While such components can break streaming of the final output when using astream, astream_events will still yield streaming events from intermediate steps that support streaming!虽然在使用 astream 时此类组件可能会中断最终输出的流式传输，但 astream_events 仍将从支持流式传输的中间步骤产生流式事件！

# Function that does not support streaming.
# It operates on the finalizes inputs rather than
# operating on the input stream.
def _extract_country_names(inputs):
    """A function that does not operates on input streams and breaks streaming."""
    if not isinstance(inputs, dict):
        return ""

    if "countries" not in inputs:
        return ""

    countries = inputs["countries"]

    if not isinstance(countries, list):
        return ""

    country_names = [
        country.get("name") for country in countries if isinstance(country, dict)
    ]
    return country_names

chain = (
    model | JsonOutputParser() | _extract_country_names
)  # This parser only works with OpenAI right now

As expected, the astream API doesn't work correctly because _extract_country_names doesn't operate on streams.正如预期的那样，astream API 无法正常工作，因为 _extract_country_names 不适用于流。

async for chunk in chain.astream(
    "output a list of the countries france, spain and japan and their populations in JSON format. "
    'Use a dict with an outer key of "countries" which contains a list of countries. '
    "Each country should have the key `name` and `population`",
):
    print(chunk, flush=True)

['France', 'Spain', 'Japan']

Now, let's confirm that with astream_events we're still seeing streaming output from the model and the parser.现在，让我们确认通过 astream_events 我们仍然可以看到来自模型和解析器的流输出。

num_events = 0

async for event in chain.astream_events(
    "output a list of the countries france, spain and japan and their populations in JSON format. "
    'Use a dict with an outer key of "countries" which contains a list of countries. '
    "Each country should have the key `name` and `population`",
    version="v2",
):
    kind = event["event"]
    if kind == "on_chat_model_stream":
        print(
            f"Chat model chunk: {repr(event['data']['chunk'].content)}",
            flush=True,
        )
    if kind == "on_parser_stream":
        print(f"Parser chunk: {event['data']['chunk']}", flush=True)
    num_events += 1
    if num_events > 30:
        # Truncate the output
        print("...")
        break

Chat model chunk: '{'
Parser chunk: {}
Chat model chunk: '\n  '
Chat model chunk: '"'
Chat model chunk: 'countries'
Chat model chunk: '":'
Chat model chunk: ' ['
Parser chunk: {'countries': []}
Chat model chunk: '\n    '
Chat model chunk: '{'
Parser chunk: {'countries': [{}]}
Chat model chunk: '\n      '
Chat model chunk: '"'
Chat model chunk: 'name'
Chat model chunk: '":'
Chat model chunk: ' "'
Parser chunk: {'countries': [{'name': ''}]}
Chat model chunk: 'France'
Parser chunk: {'countries': [{'name': 'France'}]}
Chat model chunk: '",'
Chat model chunk: '\n      '
Chat model chunk: '"'
Chat model chunk: 'population'
Chat model chunk: '":'
Chat model chunk: ' '
Chat model chunk: '67'
Parser chunk: {'countries': [{'name': 'France', 'population': 67}]}
...

Propagating Callbacks传播回调

If you're using invoking runnables inside your tools, you need to propagate callbacks to the runnable; otherwise, no stream events will be generated.如果您在工具中使用调用可运行对象，则需要将回调传播到可运行对象；否则，不会生成任何流事件。

When using RunnableLambdas or @chain decorator, callbacks are propagated automatically behind the scenes. 当使用 RunnableLambdas 或 @chain 装饰器时，回调会在幕后自动传播。

from langchain_core.runnables import RunnableLambda
from langchain_core.tools import tool

def reverse_word(word: str):
    return word[::-1]

reverse_word = RunnableLambda(reverse_word)

@tool
def bad_tool(word: str):
    """Custom tool that doesn't propagate callbacks."""
    return reverse_word.invoke(word)

async for event in bad_tool.astream_events("hello", version="v2"):
    print(event)

API Reference: RunnableLambda | tool

{'event': 'on_tool_start', 'data': {'input': 'hello'}, 'name': 'bad_tool', 'tags': [], 'run_id': 'ea900472-a8f7-425d-b627-facdef936ee8', 'metadata': {}}
{'event': 'on_chain_start', 'data': {'input': 'hello'}, 'name': 'reverse_word', 'tags': [], 'run_id': '77b01284-0515-48f4-8d7c-eb27c1882f86', 'metadata': {}}
{'event': 'on_chain_end', 'data': {'output': 'olleh', 'input': 'hello'}, 'run_id': '77b01284-0515-48f4-8d7c-eb27c1882f86', 'name': 'reverse_word', 'tags': [], 'metadata': {}}
{'event': 'on_tool_end', 'data': {'output': 'olleh'}, 'run_id': 'ea900472-a8f7-425d-b627-facdef936ee8', 'name': 'bad_tool', 'tags': [], 'metadata': {}}

Here's a re-implementation that does propagate callbacks correctly. You'll notice that now we're getting events from the reverse_word runnable as well.这是正确传播回调的重新实现。您会注意到，现在我们也从reverse_word runnable 获取事件。

@tool
def correct_tool(word: str, callbacks):
    """A tool that correctly propagates callbacks."""
    return reverse_word.invoke(word, {"callbacks": callbacks})

async for event in correct_tool.astream_events("hello", version="v2"):
    print(event)

{'event': 'on_tool_start', 'data': {'input': 'hello'}, 'name': 'correct_tool', 'tags': [], 'run_id': 'd5ea83b9-9278-49cc-9f1d-aa302d671040', 'metadata': {}}
{'event': 'on_chain_start', 'data': {'input': 'hello'}, 'name': 'reverse_word', 'tags': [], 'run_id': '44dafbf4-2f87-412b-ae0e-9f71713810df', 'metadata': {}}
{'event': 'on_chain_end', 'data': {'output': 'olleh', 'input': 'hello'}, 'run_id': '44dafbf4-2f87-412b-ae0e-9f71713810df', 'name': 'reverse_word', 'tags': [], 'metadata': {}}
{'event': 'on_tool_end', 'data': {'output': 'olleh'}, 'run_id': 'd5ea83b9-9278-49cc-9f1d-aa302d671040', 'name': 'correct_tool', 'tags': [], 'metadata': {}}

If you're invoking runnables from within Runnable Lambdas or @chains, then callbacks will be passed automatically on your behalf.如果您从 Runnable Lambda 或 @chains 中调用 Runnable，则回调将代表您自动传递。

from langchain_core.runnables import RunnableLambda

async def reverse_and_double(word: str):
    return await reverse_word.ainvoke(word) * 2

reverse_and_double = RunnableLambda(reverse_and_double)

await reverse_and_double.ainvoke("1234")

async for event in reverse_and_double.astream_events("1234", version="v2"):
    print(event)

API Reference: RunnableLambda

{'event': 'on_chain_start', 'data': {'input': '1234'}, 'name': 'reverse_and_double', 'tags': [], 'run_id': '03b0e6a1-3e60-42fc-8373-1e7829198d80', 'metadata': {}}
{'event': 'on_chain_start', 'data': {'input': '1234'}, 'name': 'reverse_word', 'tags': [], 'run_id': '5cf26fc8-840b-4642-98ed-623dda28707a', 'metadata': {}}
{'event': 'on_chain_end', 'data': {'output': '4321', 'input': '1234'}, 'run_id': '5cf26fc8-840b-4642-98ed-623dda28707a', 'name': 'reverse_word', 'tags': [], 'metadata': {}}
{'event': 'on_chain_stream', 'data': {'chunk': '43214321'}, 'run_id': '03b0e6a1-3e60-42fc-8373-1e7829198d80', 'name': 'reverse_and_double', 'tags': [], 'metadata': {}}
{'event': 'on_chain_end', 'data': {'output': '43214321'}, 'run_id': '03b0e6a1-3e60-42fc-8373-1e7829198d80', 'name': 'reverse_and_double', 'tags': [], 'metadata': {}}

And with the @chain decorator:

from langchain_core.runnables import chain

@chain
async def reverse_and_double(word: str):
    return await reverse_word.ainvoke(word) * 2

await reverse_and_double.ainvoke("1234")

async for event in reverse_and_double.astream_events("1234", version="v2"):
    print(event)

API Reference: chain

{'event': 'on_chain_start', 'data': {'input': '1234'}, 'name': 'reverse_and_double', 'tags': [], 'run_id': '1bfcaedc-f4aa-4d8e-beee-9bba6ef17008', 'metadata': {}}
{'event': 'on_chain_start', 'data': {'input': '1234'}, 'name': 'reverse_word', 'tags': [], 'run_id': '64fc99f0-5d7d-442b-b4f5-4537129f67d1', 'metadata': {}}
{'event': 'on_chain_end', 'data': {'output': '4321', 'input': '1234'}, 'run_id': '64fc99f0-5d7d-442b-b4f5-4537129f67d1', 'name': 'reverse_word', 'tags': [], 'metadata': {}}
{'event': 'on_chain_stream', 'data': {'chunk': '43214321'}, 'run_id': '1bfcaedc-f4aa-4d8e-beee-9bba6ef17008', 'name': 'reverse_and_double', 'tags': [], 'metadata': {}}
{'event': 'on_chain_end', 'data': {'output': '43214321'}, 'run_id': '1bfcaedc-f4aa-4d8e-beee-9bba6ef17008', 'name': 'reverse_and_double', 'tags': [], 'metadata': {}}
avatar
文章
阅读
粉丝