UnicodeEncodeError in the third get_started tutorial #1992
Description
[Y] I have checked the documentation and related resources and couldn't resolve my bug.
Describe the bug
A clear and concise description of what the bug is.
Ragas version: 0.2.14
Python version: 3.12
Code to Reproduce
Share code to reproduce the issue
dataset.upload()
Error trace
UnicodeEncodeError Traceback (most recent call last)
Cell In[5], line 1
----> 1 dataset.upload()
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/ragas/testset/synthesizers/testset_schema.py:141, in Testset.upload(self, verbose)
139 def upload(self, verbose: bool = True) -> str:
140 packet = TestsetPacket(samples_original=self.samples, run_id=self.run_id)
--> 141 response = upload_packet(
142 path="/alignment/testset",
143 data_json_string=packet.model_dump_json(),
144 )
145 app_url = get_app_url()
147 testset_endpoint = f"{app_url}/dashboard/alignment/testset/{self.run_id}"
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/ragas/sdk.py:102, in upload_packet(path, data_json_string)
99 print(f" {data_json_string}")
100 print(section_delimiter)
--> 102 response = requests.post(
103 f"{base_url}/api/v1{path}",
104 data=data_json_string,
105 headers=headers,
106 timeout=(connection_timeout, read_timeout),
107 )
109 if enable_http_log:
110 try:
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/requests/api.py:115, in post(url, data, json, **kwargs)
103 def post(url, data=None, json=None, **kwargs):
104 r"""Sends a POST request.
105
106 :param url: URL for the new :class:Request object.
(...) 112 :rtype: requests.Response
113 """
--> 115 return request("post", url, data=data, json=json, **kwargs)
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/requests/api.py:59, in request(method, url, **kwargs)
55 # By using the 'with' statement we are sure the session is closed, thus we
56 # avoid leaving sockets open which can trigger a ResourceWarning in some
57 # cases, and look like a memory leak in others.
58 with sessions.Session() as session:
---> 59 return session.request(method=method, url=url, **kwargs)
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/requests/sessions.py:589, in Session.request(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)
584 send_kwargs = {
585 "timeout": timeout,
586 "allow_redirects": allow_redirects,
587 }
588 send_kwargs.update(settings)
--> 589 resp = self.send(prep, **send_kwargs)
591 return resp
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/requests/sessions.py:703, in Session.send(self, request, **kwargs)
700 start = preferred_clock()
702 # Send the request
--> 703 r = adapter.send(request, **kwargs)
705 # Total elapsed time of the request (approximately)
706 elapsed = preferred_clock() - start
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/requests/adapters.py:667, in HTTPAdapter.send(self, request, stream, timeout, verify, cert, proxies)
664 timeout = TimeoutSauce(connect=timeout, read=timeout)
666 try:
--> 667 resp = conn.urlopen(
668 method=request.method,
669 url=url,
670 body=request.body,
671 headers=request.headers,
672 redirect=False,
673 assert_same_host=False,
674 preload_content=False,
675 decode_content=False,
676 retries=self.max_retries,
677 timeout=timeout,
678 chunked=chunked,
679 )
681 except (ProtocolError, OSError) as err:
682 raise ConnectionError(err, request=request)
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/urllib3/connectionpool.py:715, in HTTPConnectionPool.urlopen(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)
712 self._prepare_proxy(conn)
714 # Make the request on the httplib connection object.
--> 715 httplib_response = self._make_request(
716 conn,
717 method,
718 url,
719 timeout=timeout_obj,
720 body=body,
721 headers=headers,
722 chunked=chunked,
723 )
725 # If we're going to release the connection in finally:, then
726 # the response doesn't need to know about the connection. Otherwise
727 # it will also try to release it and we'll have a double-release
728 # mess.
729 response_conn = conn if not release_conn else None
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/urllib3/connectionpool.py:416, in HTTPConnectionPool._make_request(self, conn, method, url, timeout, chunked, **httplib_request_kw)
414 conn.request_chunked(method, url, **httplib_request_kw)
415 else:
--> 416 conn.request(method, url, **httplib_request_kw)
418 # We are swallowing BrokenPipeError (errno.EPIPE) since the server is
419 # legitimately able to close the connection after sending a valid response.
420 # With this behaviour, the received response is still readable.
421 except BrokenPipeError:
422 # Python 3
File ~/miniforge3/envs/lc/lib/python3.12/site-packages/urllib3/connection.py:244, in HTTPConnection.request(self, method, url, body, headers)
242 if "user-agent" not in (six.ensure_str(k.lower()) for k in headers):
243 headers["User-Agent"] = _get_default_user_agent()
--> 244 super(HTTPConnection, self).request(method, url, body=body, headers=headers)
File ~/miniforge3/envs/lc/lib/python3.12/http/client.py:1338, in HTTPConnection.request(self, method, url, body, headers, encode_chunked)
1335 def request(self, method, url, body=None, headers={}, *,
1336 encode_chunked=False):
1337 """Send a complete request to the server."""
-> 1338 self._send_request(method, url, body, headers, encode_chunked)
File ~/miniforge3/envs/lc/lib/python3.12/http/client.py:1383, in HTTPConnection._send_request(self, method, url, body, headers, encode_chunked)
1379 self.putheader(hdr, value)
1380 if isinstance(body, str):
1381 # RFC 2616 Section 3.7.1 says that text default has a
1382 # default charset of iso-8859-1.
-> 1383 body = _encode(body, 'body')
1384 self.endheaders(body, encode_chunked=encode_chunked)
File ~/miniforge3/envs/lc/lib/python3.12/http/client.py:166, in _encode(data, name)
164 return data.encode("latin-1")
165 except UnicodeEncodeError as err:
--> 166 raise UnicodeEncodeError(
167 err.encoding,
168 err.object,
169 err.start,
170 err.end,
171 "%s (%.20r) is not valid Latin-1. Use %s.encode('utf-8') "
172 "if you want to send it encoded in UTF-8." %
173 (name.title(), data[err.start:err.end], name)) from None
UnicodeEncodeError: 'latin-1' codec can't encode character '\u2019' in position 2654: Body ('’') is not valid Latin-1. Use body.encode('utf-8') if you want to send it encoded in UTF-8.
Expected behavior
A clear and concise description of what you expected to happen.
The example dataset should be uploaded smoothly.
Everything should be robust at least in the get_started docs.
Additional context
Add any other context about the problem here.