SSLCertVerificationError when using LlamaParse

[bhishanpdl]

I am trying to run the basic llama-parse notebooks from the official example. But, my computer is running behind a firewall and needs certificates to access the websites.

I got SSL certificate error when running simple LlamaParse function.

My attempts

• Downloaded certificates for llamaindex.ai website. Also tried cloud_llamaindex.ai website. Both did not work.
• Can we pass the parameter such as verify=path_to_cafile (as like in requests.get)
• I do not see any website name in the error message for which the SSL verification is failing.

Code

import os

# environment setup
# os.environ["REQUESTS_CA_BUNDLE"] = os.path.expanduser('~/.certificates/llamaindex_ai.crt')
os.environ["REQUESTS_CA_BUNDLE"] = os.path.expanduser('~/.certificates/cloud_llamaindex_ai.crt')

#========= cloud key
config = {'token_llama': 'my actual api key'}
os.environ['LLAMA_CLOUD_API_KEY'] = config.get('token_llama')

#============= async
# llama-parse is async-first, running the sync code in a notebook requires the use of nest_asyncio
import nest_asyncio
nest_asyncio.apply()

# main code
from llama_parse import LlamaParse
documents = LlamaParse(result_type="text").load_data("./attention.pdf")

Another failed attempt

# main code
from llama_parse import LlamaParse
documents = LlamaParse(result_type="text",verify=False).load_data("./attention.pdf")

Error

Error while parsing the file './attention.pdf': [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self-signed certificate in certificate chain (_ssl.c:1006)
---------------------------------------------------------------------------
SSLCertVerificationError                  Traceback (most recent call last)
Cell In[7], line 3
      1 from llama_parse import LlamaParse
----> 3 documents = LlamaParse(result_type="text").load_data("./attention.pdf")

File [~\venv\py311_llama_index\Lib\site-packages\llama_parse\base.py:330](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/llama_parse/base.py#line=329), in LlamaParse.load_data(self, file_path, extra_info)
    328 """Load data from the input path."""
    329 try:
--> 330     return asyncio.run(self.aload_data(file_path, extra_info))
    331 except RuntimeError as e:
    332     if nest_asyncio_err in str(e):

File [~\venv\py311_llama_index\Lib\site-packages\nest_asyncio.py:30](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/nest_asyncio.py#line=29), in _patch_asyncio.<locals>.run(main, debug)
     28 task = asyncio.ensure_future(main)
     29 try:
---> 30     return loop.run_until_complete(task)
     31 finally:
     32     if not task.done():

File [~\venv\py311_llama_index\Lib\site-packages\nest_asyncio.py:98](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/nest_asyncio.py#line=97), in _patch_loop.<locals>.run_until_complete(self, future)
     95 if not f.done():
     96     raise RuntimeError(
     97         'Event loop stopped before Future completed.')
---> 98 return f.result()

File [~\AppData\Local\Programs\Python\Python311\Lib\asyncio\futures.py:203](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/AppData/Local/Programs/Python/Python311/Lib/asyncio/futures.py#line=202), in Future.result(self)
    201 self.__log_traceback = False
    202 if self._exception is not None:
--> 203     raise self._exception.with_traceback(self._exception_tb)
    204 return self._result

File [~\AppData\Local\Programs\Python\Python311\Lib\asyncio\tasks.py:277](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/AppData/Local/Programs/Python/Python311/Lib/asyncio/tasks.py#line=276), in Task.__step(***failed resolving arguments***)
    273 try:
    274     if exc is None:
    275         # We use the `send` method directly, because coroutines
    276         # don't have `__iter__` and `__next__` methods.
--> 277         result = coro.send(None)
    278     else:
    279         result = coro.throw(exc)

File [~\venv\py311_llama_index\Lib\site-packages\llama_parse\base.py:311](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/llama_parse/base.py#line=310), in LlamaParse.aload_data(self, file_path, extra_info)
    309 """Load data from the input path."""
    310 if isinstance(file_path, (str, Path)):
--> 311     return await self._aload_data(file_path, extra_info=extra_info)
    312 elif isinstance(file_path, list):
    313     jobs = [self._aload_data(f, extra_info=extra_info) for f in file_path]

File [~\venv\py311_llama_index\Lib\site-packages\llama_parse\base.py:304](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/llama_parse/base.py#line=303), in LlamaParse._aload_data(self, file_path, extra_info)
    302 except Exception as e:
    303     print(f"Error while parsing the file '{file_path}':", e)
--> 304     raise e
    305     return []

File [~\venv\py311_llama_index\Lib\site-packages\llama_parse\base.py:289](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/llama_parse/base.py#line=288), in LlamaParse._aload_data(self, file_path, extra_info)
    287 """Load data from the input path."""
    288 try:
--> 289     job_id = await self._create_job(file_path, extra_info=extra_info)
    290     if self.verbose:
    291         print("Started parsing the file under job_id %s" % job_id)

File [~\venv\py311_llama_index\Lib\site-packages\llama_parse\base.py:249](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/llama_parse/base.py#line=248), in LlamaParse._create_job(self, file_path, extra_info)
    247 url = f"{self.base_url}/api/parsing/upload"
    248 async with httpx.AsyncClient(timeout=self.max_timeout) as client:
--> 249     response = await client.post(url, files=files, headers=headers, data={"language": self.language.value, "parsing_instruction": self.parsing_instruction})
    250     if not response.is_success:
    251         raise Exception(f"Failed to parse the file: {response.text}")

File [~\venv\py311_llama_index\Lib\site-packages\httpx\_client.py:1892](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpx/_client.py#line=1891), in AsyncClient.post(self, url, content, data, files, json, params, headers, cookies, auth, follow_redirects, timeout, extensions)
   1871 async def post(
   1872     self,
   1873     url: URLTypes,
   (...)
   1885     extensions: RequestExtensions | None = None,
   1886 ) -> Response:
   1887     """
   1888     Send a `POST` request.
   1889 
   1890     **Parameters**: See `httpx.request`.
   1891     """
-> 1892     return await self.request(
   1893         "POST",
   1894         url,
   1895         content=content,
   1896         data=data,
   1897         files=files,
   1898         json=json,
   1899         params=params,
   1900         headers=headers,
   1901         cookies=cookies,
   1902         auth=auth,
   1903         follow_redirects=follow_redirects,
   1904         timeout=timeout,
   1905         extensions=extensions,
   1906     )

File [~\venv\py311_llama_index\Lib\site-packages\httpx\_client.py:1574](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpx/_client.py#line=1573), in AsyncClient.request(self, method, url, content, data, files, json, params, headers, cookies, auth, follow_redirects, timeout, extensions)
   1559     warnings.warn(message, DeprecationWarning)
   1561 request = self.build_request(
   1562     method=method,
   1563     url=url,
   (...)
   1572     extensions=extensions,
   1573 )
-> 1574 return await self.send(request, auth=auth, follow_redirects=follow_redirects)

File [~\venv\py311_llama_index\Lib\site-packages\httpx\_client.py:1661](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpx/_client.py#line=1660), in AsyncClient.send(self, request, stream, auth, follow_redirects)
   1653 follow_redirects = (
   1654     self.follow_redirects
   1655     if isinstance(follow_redirects, UseClientDefault)
   1656     else follow_redirects
   1657 )
   1659 auth = self._build_request_auth(request, auth)
-> 1661 response = await self._send_handling_auth(
   1662     request,
   1663     auth=auth,
   1664     follow_redirects=follow_redirects,
   1665     history=[],
   1666 )
   1667 try:
   1668     if not stream:

File [~\venv\py311_llama_index\Lib\site-packages\httpx\_client.py:1689](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpx/_client.py#line=1688), in AsyncClient._send_handling_auth(self, request, auth, follow_redirects, history)
   1686 request = await auth_flow.__anext__()
   1688 while True:
-> 1689     response = await self._send_handling_redirects(
   1690         request,
   1691         follow_redirects=follow_redirects,
   1692         history=history,
   1693     )
   1694     try:
   1695         try:

File [~\venv\py311_llama_index\Lib\site-packages\httpx\_client.py:1726](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpx/_client.py#line=1725), in AsyncClient._send_handling_redirects(self, request, follow_redirects, history)
   1723 for hook in self._event_hooks["request"]:
   1724     await hook(request)
-> 1726 response = await self._send_single_request(request)
   1727 try:
   1728     for hook in self._event_hooks["response"]:

File [~\venv\py311_llama_index\Lib\site-packages\httpx\_client.py:1763](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpx/_client.py#line=1762), in AsyncClient._send_single_request(self, request)
   1758     raise RuntimeError(
   1759         "Attempted to send an sync request with an AsyncClient instance."
   1760     )
   1762 with request_context(request=request):
-> 1763     response = await transport.handle_async_request(request)
   1765 assert isinstance(response.stream, AsyncByteStream)
   1766 response.request = request

File [~\venv\py311_llama_index\Lib\site-packages\httpx\_transports\default.py:373](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpx/_transports/default.py#line=372), in AsyncHTTPTransport.handle_async_request(self, request)
    360 req = httpcore.Request(
    361     method=request.method,
    362     url=httpcore.URL(
   (...)
    370     extensions=request.extensions,
    371 )
    372 with map_httpcore_exceptions():
--> 373     resp = await self._pool.handle_async_request(req)
    375 assert isinstance(resp.stream, typing.AsyncIterable)
    377 return Response(
    378     status_code=resp.status,
    379     headers=resp.headers,
    380     stream=AsyncResponseStream(resp.stream),
    381     extensions=resp.extensions,
    382 )

File [~\venv\py311_llama_index\Lib\site-packages\httpcore\_async\connection_pool.py:216](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpcore/_async/connection_pool.py#line=215), in AsyncConnectionPool.handle_async_request(self, request)
    213         closing = self._assign_requests_to_connections()
    215     await self._close_connections(closing)
--> 216     raise exc from None
    218 # Return the response. Note that in this case we still have to manage
    219 # the point at which the response is closed.
    220 assert isinstance(response.stream, AsyncIterable)

File [~\venv\py311_llama_index\Lib\site-packages\httpcore\_async\connection_pool.py:196](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpcore/_async/connection_pool.py#line=195), in AsyncConnectionPool.handle_async_request(self, request)
    192 connection = await pool_request.wait_for_connection(timeout=timeout)
    194 try:
    195     # Send the request on the assigned connection.
--> 196     response = await connection.handle_async_request(
    197         pool_request.request
    198     )
    199 except ConnectionNotAvailable:
    200     # In some cases a connection may initially be available to
    201     # handle a request, but then become unavailable.
    202     #
    203     # In this case we clear the connection and try again.
    204     pool_request.clear_connection()

File [~\venv\py311_llama_index\Lib\site-packages\httpcore\_async\connection.py:99](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpcore/_async/connection.py#line=98), in AsyncHTTPConnection.handle_async_request(self, request)
     97 except BaseException as exc:
     98     self._connect_failed = True
---> 99     raise exc
    101 return await self._connection.handle_async_request(request)

File [~\venv\py311_llama_index\Lib\site-packages\httpcore\_async\connection.py:76](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpcore/_async/connection.py#line=75), in AsyncHTTPConnection.handle_async_request(self, request)
     74 async with self._request_lock:
     75     if self._connection is None:
---> 76         stream = await self._connect(request)
     78         ssl_object = stream.get_extra_info("ssl_object")
     79         http2_negotiated = (
     80             ssl_object is not None
     81             and ssl_object.selected_alpn_protocol() == "h2"
     82         )

File [~\venv\py311_llama_index\Lib\site-packages\httpcore\_async\connection.py:154](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpcore/_async/connection.py#line=153), in AsyncHTTPConnection._connect(self, request)
    147     kwargs = {
    148         "ssl_context": ssl_context,
    149         "server_hostname": sni_hostname
    150         or self._origin.host.decode("ascii"),
    151         "timeout": timeout,
    152     }
    153     async with Trace("start_tls", logger, request, kwargs) as trace:
--> 154         stream = await stream.start_tls(**kwargs)
    155         trace.return_value = stream
    156 return stream

File [~\venv\py311_llama_index\Lib\site-packages\httpcore\_backends\anyio.py:80](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpcore/_backends/anyio.py#line=79), in AnyIOStream.start_tls(self, ssl_context, server_hostname, timeout)
     78     except Exception as exc:  # pragma: nocover
     79         await self.aclose()
---> 80         raise exc
     81 return AnyIOStream(ssl_stream)

File [~\venv\py311_llama_index\Lib\site-packages\httpcore\_backends\anyio.py:71](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/httpcore/_backends/anyio.py#line=70), in AnyIOStream.start_tls(self, ssl_context, server_hostname, timeout)
     69 try:
     70     with anyio.fail_after(timeout):
---> 71         ssl_stream = await anyio.streams.tls.TLSStream.wrap(
     72             self._stream,
     73             ssl_context=ssl_context,
     74             hostname=server_hostname,
     75             standard_compatible=False,
     76             server_side=False,
     77         )
     78 except Exception as exc:  # pragma: nocover
     79     await self.aclose()

File [~\venv\py311_llama_index\Lib\site-packages\anyio\streams\tls.py:132](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/anyio/streams/tls.py#line=131), in TLSStream.wrap(cls, transport_stream, server_side, hostname, ssl_context, standard_compatible)
    122 ssl_object = ssl_context.wrap_bio(
    123     bio_in, bio_out, server_side=server_side, server_hostname=hostname
    124 )
    125 wrapper = cls(
    126     transport_stream=transport_stream,
    127     standard_compatible=standard_compatible,
   (...)
    130     _write_bio=bio_out,
    131 )
--> 132 await wrapper._call_sslobject_method(ssl_object.do_handshake)
    133 return wrapper

File [~\venv\py311_llama_index\Lib\site-packages\anyio\streams\tls.py:140](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/venv/py311_llama_index/Lib/site-packages/anyio/streams/tls.py#line=139), in TLSStream._call_sslobject_method(self, func, *args)
    138 while True:
    139     try:
--> 140         result = func(*args)
    141     except ssl.SSLWantReadError:
    142         try:
    143             # Flush any pending writes first

File [~\AppData\Local\Programs\Python\Python311\Lib\ssl.py:979](http://localhost:8888/lab/tree/aa_Learn/LLM/model_Llama/llama_parse/Resources/official_examples/~/AppData/Local/Programs/Python/Python311/Lib/ssl.py#line=978), in SSLObject.do_handshake(self)
    977 def do_handshake(self):
    978     """Start the SSL/TLS handshake."""
--> 979     self._sslobj.do_handshake()

SSLCertVerificationError: [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: self-signed certificate in certificate chain (_ssl.c:1006)