chinese-nlp-book / rasa_chinese_book_code Goto Github PK

第五章，查询天气，

如果使用webapi怎么请求呢，
第一步：发送：
http://localhost:5005/conversations/0/messages
{
  "sender": "user",
  "text": "上海的天气怎么样"
}

第二步：调用http://localhost:5005/conversations/0/predict
第三步：取第二步得分最高的action开始执行：
http://localhost:5005/conversations/0/execute
{
  "name": "weather_form"
}
得到需要确认日期，
第四步：
http://localhost:5005/conversations/0/messages
{
  "sender": "user",
  "text": "明天的"
}

到这里之后，slots都有了，怎么触发查询天气呢？

The problem resolved!

第三章 README.md:

 ##启动Rasa动作服务器
 ```shell
-rasa run action
+rasa run actions
 ``
 
 ##启动Rasa服务器和客户端

第四章 README.md:

尝试输入一些查询，例如“如何检查面试结果？”并查看回复。

玩得开心！

+## 运行服务(网页)具体步骤:
+### 运行Rasa服务器
+```bash
+rasa run --cors "*"
+``
+### 运行网页客户端
+```bash
+python -m http.server
+`` 
+### 使用浏览器打开链接:http://localhost:8000/

请教一下，第三章的报时机器人，为什么会出现下面的问题呢？python是3.9，系统是windows11.

Your input -> 现在几点了？
2022-05-06 16:40:28 ERROR rasa.core.actions.action - Failed to run custom action 'action_query_date'. Couldn't connect to the server at 'http://localhost:5055/webhook'. Is the server running? Error: Cannot connect to host localhost:5055 ssl:default [远程计算机拒绝网络连接。]
2022-05-06 16:40:28 ERROR rasa.core.processor - Encountered an exception while running action 'action_query_date'.Bot will continue, but the actions events are lost. Please check the logs of your action server for more information.dows_events.py", line 599, in finish_connect
Traceback (most recent call last):
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\connector.py", line 969, in _wrap_create_connection
return await self._loop.create_connection(*args, **kwargs) # type: ignore # noqa
File "D:\anaconda\envs\rasa2\lib\asyncio\base_events.py", line 1056, in create_connection
raise exceptions[0]
File "D:\anaconda\envs\rasa2\lib\asyncio\base_events.py", line 1041, in create_connection
sock = await self._connect_sock(ite-packages\rasa\core\actions\action.py", line 742, in run
File "D:\anaconda\envs\rasa2\lib\asyncio\base_events.py", line 955, in _connect_sock
await self.sock_connect(sock, address)ckages\rasa\utils\endpoints.py", line 164, in request
File "D:\anaconda\envs\rasa2\lib\asyncio\proactor_events.py", line 702, in sock_connect
return await self._proactor.connect(sock, address)tp\client.py", line 1117, in aenter
File "D:\anaconda\envs\rasa2\lib\asyncio\windows_events.py", line 812, in _poll
value = callback(transferred, key, ov)ckages\aiohttp\client.py", line 520, in _request
File "D:\anaconda\envs\rasa2\lib\asyncio\windows_events.py", line 599, in finish_connect
ov.getresult()a\envs\rasa2\lib\site-packages\aiohttp\connector.py", line 535, in connect
ConnectionRefusedError: [WinError 1225] 远程计算机拒绝网络连接。
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\connector.py", line 892, in _create_connection
The above exception was the direct cause of the following exception:eout)
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\connector.py", line 1051, in _create_direct_connection
Traceback (most recent call last):
File "D:\anaconda\envs\rasa2\lib\site-packages\rasa\core\actions\action.py", line 742, in runirect_connection
response: Any = await self.action_endpoint.request(
File "D:\anaconda\envs\rasa2\lib\site-packages\rasa\utils\endpoints.py", line 164, in requestte_connection
async with session.request(ection_key, exc) from exc
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\client.py", line 1117, in __aenter__ault [远程计算机拒绝网络连接。]
self._resp = await self._coro
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\client.py", line 520, in _request
conn = await self._connector.connect(
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\connector.py", line 535, in connect
proto = await self._create_connection(req, traces, timeout)essor.py", line 869, in _run_action
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\connector.py", line 892, in _create_connection
_, proto = await self._create_direct_connection(req, traces, timeout).py", line 774, in run
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\connector.py", line 1051, in _create_direct_connection
raise last_excions.RasaException: Failed to execute custom action.
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\connector.py", line 1020, in _create_direct_connection
transp, proto = await self._wrap_create_connection(
File "D:\anaconda\envs\rasa2\lib\site-packages\aiohttp\connector.py", line 975, in _wrap_create_connection
raise client_error(req.connection_key, exc) from exc
aiohttp.client_exceptions.ClientConnectorError: Cannot connect to host localhost:5055 ssl:default [远程计算机拒绝网络连接。]

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\anaconda\envs\rasa2\lib\site-packages\rasa\core\processor.py", line 869, in _run_action
events = await action.run(
File "D:\anaconda\envs\rasa2\lib\site-packages\rasa\core\actions\action.py", line 774, in run
raise RasaException("Failed to execute custom action.")
rasa.shared.exceptions.RasaException: Failed to execute custom action.

正确的应该是上海到北京，北京到上海的例子都写，并且应该添加更多的例子帮助训练。否则可能会出现实体role提取错误的情况

No definition of templates found in domain.yml.

环境是windows10,启动动作服务器时遇到如下问题
无法将“SENIVERSE_KEY=xxx”项识别为 cmdlet、函数、脚本文件或可运行程序的名称。请检查名称的拼写，如果包括路径，请确保路径正确，然后再试一次。

书上的

实际代码的

多轮对话确定一个推荐，怎么实现？
人：你好
AI：你好
人：我要找大学
AI：你什么学历
人：高中
AI：你什么年龄
人：18岁
AI：你想读什么专业
人：计算机
AI：你想再什么地区
人：北京
AI：推荐你北京大学

如果要实现多轮条件合并才能推出结果，怎么实现呢?

windows10系统， rasa run actions 和 rasa run --enable-api都已经正常启动，并且5005/model/parse NLU模块访问成功， 请教一下5005/webhooks/rest/webhook模块还需要开启什么服务才能访问吗？

第6章代码示例，我在网页端已经启动了，actions也启动了，我问了“有哪些歌手”，出来的答案是对的，但是我问“有哪些男歌手”时，actions服务报错：
2024-01-25 15:34:00 INFO rasa_sdk.endpoint - Starting action endpoint server...
using Neo4jKnowledgeBase
2024-01-25 15:34:00 INFO rasa_sdk.executor - Registered function for 'action_response_query'.
2024-01-25 15:34:00 INFO rasa_sdk.endpoint - Starting plugins...
2024-01-25 15:34:00 INFO rasa_sdk.endpoint - Action endpoint is up and running on http://0.0.0.0:5055
2024-01-25 15:34:48 ERROR rasa_sdk.endpoint - Exception occurred during execution of request <Request: POST /webhook>
Traceback (most recent call last):
File "handle_request", line 83, in handle_request
)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa_sdk\endpoint.py", line 113, in webhook
result = await executor.run(action_call)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa_sdk\executor.py", line 398, in run
events = await utils.call_potential_coroutine(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa_sdk\utils.py", line 297, in call_potential_coroutine
return await coroutine_or_return_value
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa_sdk\knowledge_base\actions.py", line 146, in run
object_types = self.knowledge_base.get_object_types()
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa_sdk\knowledge_base\storage.py", line 116, in get_object_types
raise NotImplementedError("Method is not implemented.")
NotImplementedError: Method is not implemented.

第五章的代码是不是没实现unhappy path

nlu:

• lookup: cities
  应该改address,与nlu文件中的实体类型一致

/Chapter06/neo4j_knowledge_base.py中
result = loop.run_until_complete(kb.get_object("singer", "周杰伦")) print(result)

代码报错，看起来是neo4j的匹配语句出问题导致的
query = "MATCH (o:{object_type} {{{key}:{value}}}) RETURN o, ID(o)".format(
object_type=object_type, key=key_attribute, value=object_identifier
)
这里得到key和value不知道是哪个出了问题
MATCH (o:Singer {id:周杰伦}) RETURN o, ID(o)

可以帮忙看看怎么修改么？实际运行的pythonweb服务也是报错的

你好，我运行rasa train nul时报网络连接huggingface错误，所以我自行下载了bert-base-chinese到本地，但是我不知道如何加载，谢谢。

(rasa3) D:\rasa3\hospital>rasa train nlu
D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\core\tracker_store.py:1044: MovedIn20Warning: Deprecated API features detected! These feature(s) are not compatible with SQLAlchemy 2.0. To prevent incompatible upgrades prior to updating applications, ensure requirements files are pinned to "sqlalchemy<2.0". Set environment variable SQLALCHEMY_WARN_20=1 to show all deprecation warnings. Set environment variable SQLALCHEMY_SILENCE_UBER_WARNING=1 to silence this message. (Background on SQLAlchemy 2.0 at: https://sqlalche.me/e/b8d9)
Base: DeclarativeMeta = declarative_base()
D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\shared\utils\validation.py:134: DeprecationWarning: pkg_resources is deprecated as an API. See https://setuptools.pypa.io/en/latest/pkg_resources.html
import pkg_resources
D:\Anaconda3\envs\rasa3\lib\site-packages\pkg_resources_init_.py:2871: DeprecationWarning: Deprecated call to pkg_resources.declare_namespace('mpl_toolkits').
Implementing implicit namespace packages (as specified in PEP 420) is preferred to pkg_resources.declare_namespace. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages
declare_namespace(pkg)
D:\Anaconda3\envs\rasa3\lib\site-packages\pkg_resources_init_.py:2871: DeprecationWarning: Deprecated call to pkg_resources.declare_namespace('ruamel').
Implementing implicit namespace packages (as specified in PEP 420) is preferred to pkg_resources.declare_namespace. See https://setuptools.pypa.io/en/latest/references/keywords.html#keyword-namespace-packages
declare_namespace(pkg)
2024-01-23 15:20:58 INFO rasa.engine.training.hooks - Restored component 'JiebaTokenizer' from cache.
Building prefix dict from the default dictionary ...
Loading model from cache C:\Users\ZZ\AppData\Local\Temp\jieba.cache
Loading model cost 0.556 seconds.
Prefix dict has been built successfully.
Traceback (most recent call last):
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\connection.py", line 174, in _new_conn
conn = connection.create_connection(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\util\connection.py", line 95, in create_connection
raise err
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\util\connection.py", line 85, in create_connection
sock.connect(sa)
socket.timeout: timed out

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\connectionpool.py", line 715, in urlopen
httplib_response = self._make_request(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\connectionpool.py", line 404, in _make_request
self._validate_conn(conn)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\connectionpool.py", line 1058, in _validate_conn
conn.connect()
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\connection.py", line 363, in connect
self.sock = conn = self._new_conn()
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\connection.py", line 179, in _new_conn
raise ConnectTimeoutError(
urllib3.exceptions.ConnectTimeoutError: (<urllib3.connection.HTTPSConnection object at 0x000001F4B7251640>, 'Connection to huggingface.co timed out. (connect timeout=10)')

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\Anaconda3\envs\rasa3\lib\site-packages\requests\adapters.py", line 486, in send
resp = conn.urlopen(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\connectionpool.py", line 799, in urlopen
retries = retries.increment(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\urllib3\util\retry.py", line 592, in increment
raise MaxRetryError(_pool, url, error or ResponseError(cause))
urllib3.exceptions.MaxRetryError: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /bert-base-chinese/resolve/main/pytorch_model.bin (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x000001F4B7251640>, 'Connection to huggingface.co timed out. (connect timeout=10)'))

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\engine\graph.py", line 403, in _load_component
self._component: GraphComponent = constructor( # type: ignore[no-redef]
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\engine\graph.py", line 221, in load
return cls.create(config, model_storage, resource, execution_context)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\nlu\featurizers\dense_featurizer\lm_featurizer.py", line 100, in create
return cls(config, execution_context)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\nlu\featurizers\dense_featurizer\lm_featurizer.py", line 67, in init
self._load_model_instance()
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\nlu\featurizers\dense_featurizer\lm_featurizer.py", line 155, in _load_model_instance
self.model = model_class_dict[self.model_name].from_pretrained(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\transformers\modeling_tf_utils.py", line 2668, in from_pretrained
if has_file(pretrained_model_name_or_path, WEIGHTS_NAME, **has_file_kwargs):
File "D:\Anaconda3\envs\rasa3\lib\site-packages\transformers\utils\hub.py", line 609, in has_file
r = requests.head(url, headers=headers, allow_redirects=False, proxies=proxies, timeout=10)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\requests\api.py", line 100, in head
return request("head", url, **kwargs)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\requests\api.py", line 59, in request
return session.request(method=method, url=url, **kwargs)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\requests\sessions.py", line 589, in request
resp = self.send(prep, **send_kwargs)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\requests\sessions.py", line 703, in send
r = adapter.send(request, **kwargs)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\requests\adapters.py", line 507, in send
raise ConnectTimeout(e, request=request)
requests.exceptions.ConnectTimeout: HTTPSConnectionPool(host='huggingface.co', port=443): Max retries exceeded with url: /bert-base-chinese/resolve/main/pytorch_model.bin (Caused by ConnectTimeoutError(<urllib3.connection.HTTPSConnection object at 0x000001F4B7251640>, 'Connection to huggingface.co timed out. (connect timeout=10)'))

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
File "D:\Anaconda3\envs\rasa3\lib\runpy.py", line 197, in _run_module_as_main
return run_code(code, main_globals, None,
File "D:\Anaconda3\envs\rasa3\lib\runpy.py", line 87, in run_code
exec(code, run_globals)
File "D:\Anaconda3\envs\rasa3\Scripts\rasa.exe_main.py", line 7, in
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa_main.py", line 133, in main
cmdline_arguments.func(cmdline_arguments)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\cli\train.py", line 202, in run_nlu_training
return train_nlu(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\model_training.py", line 453, in train_nlu
return _train_graph(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\model_training.py", line 286, in _train_graph
trainer.train(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\engine\training\graph_trainer.py", line 105, in train
graph_runner.run(inputs={PLACEHOLDER_IMPORTER: importer})
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\engine\runner\dask.py", line 101, in run
dask_result = dask.get(run_graph, run_targets)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\dask\local.py", line 557, in get_sync
return get_async(
File "D:\Anaconda3\envs\rasa3\lib\site-packages\dask\local.py", line 500, in get_async
for key, res_info, failed in queue_get(queue).result():
File "D:\Anaconda3\envs\rasa3\lib\concurrent\futures_base.py", line 439, in result
return self.__get_result()
File "D:\Anaconda3\envs\rasa3\lib\concurrent\futures_base.py", line 391, in __get_result
raise self._exception
File "D:\Anaconda3\envs\rasa3\lib\site-packages\dask\local.py", line 542, in submit
fut.set_result(fn(*args, **kwargs))
File "D:\Anaconda3\envs\rasa3\lib\site-packages\dask\local.py", line 238, in batch_execute_tasks
return [execute_task(*a) for a in it]
File "D:\Anaconda3\envs\rasa3\lib\site-packages\dask\local.py", line 238, in
return [execute_task(a) for a in it]
File "D:\Anaconda3\envs\rasa3\lib\site-packages\dask\local.py", line 229, in execute_task
result = pack_exception(e, dumps)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\dask\local.py", line 224, in execute_task
result = _execute_task(task, data)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\dask\core.py", line 119, in _execute_task
return func((_execute_task(a, cache) for a in args))
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\engine\graph.py", line 483, in call
self._load_component(**constructor_kwargs)
File "D:\Anaconda3\envs\rasa3\lib\site-packages\rasa\engine\graph.py", line 416, in _load_component
raise GraphComponentException(
rasa.engine.exceptions.GraphComponentException: Error initializing graph component for node run_LanguageModelFeaturizer1.