Lots of CLI changes (openai#22)

* Add CLI option to download files (openai#34)

* Option to check if file has been uploaded in the past before uploading (openai#33)

The check is done based on filename, file purpose and file size

* Add fine-tuning hparams directly into the fine-tunes CLI (openai#35)

* update fine_tunes cli use_packing argument (openai#38)

* A file verification and remediation tool.

It applies the following validations:
- prints the number of examples, and warns if it's lower than 100
- ensures prompt and completion columns are present
- optionally removes any additional columns
- ensures all completions are non-empty
- infers which type of fine-tuning the data is most likely in (classification, conditional generation and open-ended generation)
- optionally removes duplicate rows
- infers the existence of a common suffix, and if there is none, suggests one for classification and conditional generation
- optionally prepends a space to each completion, to make tokenization better
- optionally splits into training and validation set for the classification use case
- optionally ensures there's an ending string for all completions
- optionally lowercases completions or prompts if more than a 1/3 of alphanumeric characters are upper case

It interactively asks the user to accept or reject recommendations. If the user is happy, then it saves the modified output file as a jsonl, which is ready for being used in fine-tuning with the printed command.

* Completion: remove  from kwargs before passing to EngineAPI (openai#37)

* Version bump before pushing to external

Co-authored-by: Todor Markov <[email protected]>
Co-authored-by: Boris Power <[email protected]>
Co-authored-by: Dave Cummings <[email protected]>

Author: 4 people

bin/openai

@@ -1,13 +1,11 @@
 #!/usr/bin/env python
 import argparse
-import json
 import logging
-import os
 import sys
 
 import openai
 from openai.cli import display_error
-from openai.cli import register as api_register
+from openai.cli import api_register, tools_register
 
 logger = logging.getLogger()
 formatter = logging.Formatter("[%(asctime)s] %(message)s")
@@ -40,9 +38,11 @@ def main():
     parser.set_defaults(func=help)
 
     subparsers = parser.add_subparsers()
-    sub = subparsers.add_parser("api", help="Direct API calls")
+    sub_api = subparsers.add_parser("api", help="Direct API calls")
+    sub_tools = subparsers.add_parser("tools", help="Client side tools for convenience")
 
-    api_register(sub)
+    api_register(sub_api)
+    tools_register(sub_tools)
 
     args = parser.parse_args()
     if args.verbosity == 1:

openai/api_resources/completion.py

@@ -19,7 +19,7 @@ def create(cls, *args, **kwargs):
         of valid parameters.
         """
         start = time.time()
-        timeout = kwargs.get("timeout", None)
+        timeout = kwargs.pop("timeout", None)
         if kwargs.get("model", None) is None and kwargs.get("engine", None) is None:
             raise InvalidRequestError(
                 "Must provide an 'engine' or 'model' parameter to create a Completion.",

openai/api_resources/file.py

@@ -1,5 +1,8 @@
 from __future__ import absolute_import, division, print_function
 
+import json
+import os
+
 import openai
 from openai import api_requestor, util
 from openai.api_resources.abstract import (
@@ -29,3 +32,59 @@ def create(
         return util.convert_to_openai_object(
             response, api_key, api_version, organization
         )
+
+    @classmethod
+    def download(
+        cls, id, api_key=None, api_base=None, api_version=None, organization=None
+    ):
+        requestor = api_requestor.APIRequestor(
+            api_key,
+            api_base=api_base or openai.file_api_base or openai.api_base,
+            api_version=api_version,
+            organization=organization,
+        )
+        url = f"{cls.class_url()}/{id}/content"
+        rbody, rcode, rheaders, _, _ = requestor.request_raw("get", url)
+        if not 200 <= rcode < 300:
+            raise requestor.handle_error_response(
+                rbody, rcode, json.loads(rbody), rheaders, stream_error=False
+            )
+        return rbody
+
+    @classmethod
+    def find_matching_files(
+        cls,
+        api_key=None,
+        api_base=None,
+        api_version=None,
+        organization=None,
+        file=None,
+        purpose=None,
+    ):
+        if file is None:
+            raise openai.error.InvalidRequestError(
+                "'file' is a required property", "file"
+            )
+        if purpose is None:
+            raise openai.error.InvalidRequestError(
+                "'purpose' is a required property", "purpose"
+            )
+        all_files = cls.list(
+            api_key=api_key,
+            api_base=api_base or openai.file_api_base or openai.api_base,
+            api_version=api_version,
+            organization=organization,
+        ).get("data", [])
+        matching_files = []
+        for f in all_files:
+            if f["purpose"] != purpose:
+                continue
+            if not hasattr(file, "name") or f["filename"] != file.name:
+                continue
+            file.seek(0, os.SEEK_END)
+            if f["bytes"] != file.tell():
+                file.seek(0)
+                continue
+            file.seek(0)
+            matching_files.append(f)
+        return matching_files