Better handling of max tokens error

[bryanjtc]

My pull request was a little bit too big for the request. I propose handling this error by adding the InvalidRequestError as a comment to the pull request. Although the error happened, the model generated a lot of bullet points. This points should be included in the pr in the case the max tokens error happens. Another suggested change is to send the text in chunks to avoid hitting the limit.

│ /home/runner/.local/lib/python3.10/site-packages/openai/api_requestor.py:687 │
│ in _interpret_response_line                                                  │
│                                                                              │
│   684 │   │   # to better handle the "error while streaming" case.           │
│   685 │   │   stream_error = stream and "error" in resp.data                 │
│   686 │   │   if stream_error or not 200 <= rcode < 300:                     │
│ ❱ 687 │   │   │   raise self.handle_error_response(                          │
│   688 │   │   │   │   rbody, rcode, resp.data, rheaders, stream_error=stream │
│   689 │   │   │   )                                                          │
│   690 │   │   return resp                                                    │
│                                                                              │
│ ╭───────────────────────────────── locals ─────────────────────────────────╮ │
│ │         data = {                                                         │ │
│ │                │   'error': {                                            │ │
│ │                │   │   'message': "This model's maximum context length   │ │
│ │                is 4097 tokens, however you requested 6505 t"+102,        │ │
│ │                │   │   'type': 'invalid_request_error',                  │ │
│ │                │   │   'param': None,                                    │ │
│ │                │   │   'code': None                                      │ │
│ │                │   }                                                     │ │
│ │                }                                                         │ │
│ │        rbody = '{\n  "error": {\n    "message": "This model\'s maximum   │ │
│ │                context length is 4097 token'+215                         │ │
│ │        rcode = 400                                                       │ │
│ │         resp = <openai.openai_response.OpenAIResponse object at          │ │
│ │                0x7f1ce43086d0>                                           │ │
│ │     rheaders = {'Date': 'Thu, 06 Jul 2023 06:33:38 GMT', 'Content-Type': │ │
│ │                'application/json', 'Content-Length': '295',              │ │
│ │                'Connection': 'keep-alive',                               │ │
│ │                'access-control-allow-origin': '*', 'openai-model':       │ │
│ │                'text-davinci-003', 'openai-organization':                │ │
│ │                'micros-0zhpga', 'openai-processing-ms': '227',           │ │
│ │                'openai-version': '2020-10-01',                           │ │
│ │                'strict-transport-security': 'max-age=15724800;           │ │
│ │                includeSubDomains', 'x-ratelimit-limit-requests': '3000', │ │
│ │                'x-ratelimit-limit-tokens': '250000',                     │ │
│ │                'x-ratelimit-remaining-requests': '2999',                 │ │
│ │                'x-ratelimit-remaining-tokens': '248[975](https://github.com/paymesoft/PayMeSoftWeb/actions/runs/5472276542/jobs/9964282465?pr=143#step:3:980)',                 │ │
│ │                'x-ratelimit-reset-requests': '20ms',                     │ │
│ │                'x-ratelimit-reset-tokens': '245ms', 'x-request-id':      │ │
│ │                'aeca0586a2d4ff8604a152b2554c5d07', 'CF-Cache-Status':    │ │
│ │                'DYNAMIC', 'Server': 'cloudflare', 'CF-RAY':              │ │
│ │                '7e25d13f2dd4065a-IAD', 'alt-svc': 'h3=":443"; ma=86400'} │ │
│ │         self = <openai.api_requestor.APIRequestor object at              │ │
│ │                0x7f1ce430a020>                                           │ │
│ │       stream = False                                                     │ │
│ │ stream_error = False                                                     │ │
│ ╰──────────────────────────────────────────────────────────────────────────╯ │
╰──────────────────────────────────────────────────────────────────────────────╯
InvalidRequestError: This model's maximum context length is 4097 tokens, however
you requested 6505 tokens (5481 in your prompt; 1024 for the completion). Please
reduce your prompt; or completion length.

[cosydney]

+1, I submitted a 90,000 line PR and maxed out on my GPT limits to 30$