Skip to content

Github

GitHubRepositoryCollaboratorsReader #

Bases: BaseReader

GitHub repository collaborators reader.

Retrieves the list of collaborators of a GitHub repository and returns a list of documents.

Examples:

>>> reader = GitHubRepositoryCollaboratorsReader("owner", "repo")
>>> colabs = reader.load_data()
>>> print(colabs)
Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/collaborators/base.py 
 42
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
class GitHubRepositoryCollaboratorsReader(BaseReader):
    """
    GitHub repository collaborators reader.

    Retrieves the list of collaborators of a GitHub repository and returns a list of documents.

    Examples:
        >>> reader = GitHubRepositoryCollaboratorsReader("owner", "repo")
        >>> colabs = reader.load_data()
        >>> print(colabs)

    """

    class FilterType(enum.Enum):
        """
        Filter type.

        Used to determine whether the filter is inclusive or exclusive.
        """

        EXCLUDE = enum.auto()
        INCLUDE = enum.auto()

    def __init__(
        self,
        github_client: BaseGitHubCollaboratorsClient,
        owner: str,
        repo: str,
        verbose: bool = False,
    ):
        """
        Initialize params.

        Args:
            - github_client (BaseGitHubCollaboratorsClient): GitHub client.
            - owner (str): Owner of the repository.
            - repo (str): Name of the repository.
            - verbose (bool): Whether to print verbose messages.

        Raises:
            - `ValueError`: If the github_token is not provided and
                the GITHUB_TOKEN environment variable is not set.

        """
        super().__init__()

        self._owner = owner
        self._repo = repo
        self._verbose = verbose

        # Set up the event loop
        try:
            self._loop = asyncio.get_running_loop()
        except RuntimeError:
            # If there is no running loop, create a new one
            self._loop = asyncio.new_event_loop()
            asyncio.set_event_loop(self._loop)

        self._github_client = github_client

    def load_data(
        self,
    ) -> List[Document]:
        """
        GitHub repository collaborators reader.

        Retrieves the list of collaborators in a GitHub repository and converts them to documents.

        Each collaborator is converted to a document by doing the following:

            - The text of the document is the login.
            - The title of the document is also the login.
            - The extra_info of the document is a dictionary with the following keys:
                - login: str, the login of the user
                - type: str, the type of user e.g. "User"
                - site_admin: bool, whether the user has admin permissions
                - role_name: str, e.g. "admin"
                - name: str, the name of the user, if available
                - email: str, the email of the user, if available
                - permissions: str, the permissions of the user, if available


        :return: list of documents
        """
        documents = []
        page = 1
        # Loop until there are no more collaborators
        while True:
            collaborators: Dict = self._loop.run_until_complete(
                self._github_client.get_collaborators(
                    self._owner, self._repo, page=page
                )
            )

            if len(collaborators) == 0:
                print_if_verbose(self._verbose, "No more collaborators found, stopping")

                break
            print_if_verbose(
                self._verbose,
                f"Found {len(collaborators)} collaborators in the repo page {page}",
            )
            page += 1
            for collab in collaborators:
                extra_info = {
                    "login": collab["login"],
                    "type": collab["type"],
                    "site_admin": collab["site_admin"],
                    "role_name": collab["role_name"],
                }
                if collab.get("name") is not None:
                    extra_info["name"] = collab["name"]
                if collab.get("email") is not None:
                    extra_info["email"] = collab["email"]
                if collab.get("permissions") is not None:
                    extra_info["permissions"] = collab["permissions"]
                document = Document(
                    doc_id=str(collab["login"]),
                    text=str(collab["login"]),  # unsure for this
                    extra_info=extra_info,
                )
                documents.append(document)

            print_if_verbose(self._verbose, f"Resulted in {len(documents)} documents")

        return documents

FilterType #

Bases: Enum

Filter type.

Used to determine whether the filter is inclusive or exclusive.

Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/collaborators/base.py 
55
56
57
58
59
60
61
62
63
class FilterType(enum.Enum):
    """
    Filter type.

    Used to determine whether the filter is inclusive or exclusive.
    """

    EXCLUDE = enum.auto()
    INCLUDE = enum.auto()

load_data #

load_data() -> List[Document]

GitHub repository collaborators reader.

Retrieves the list of collaborators in a GitHub repository and converts them to documents.

Each collaborator is converted to a document by doing the following:

- The text of the document is the login.
- The title of the document is also the login.
- The extra_info of the document is a dictionary with the following keys:
    - login: str, the login of the user
    - type: str, the type of user e.g. "User"
    - site_admin: bool, whether the user has admin permissions
    - role_name: str, e.g. "admin"
    - name: str, the name of the user, if available
    - email: str, the email of the user, if available
    - permissions: str, the permissions of the user, if available

:return: list of documents

Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/collaborators/base.py 
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
def load_data(
    self,
) -> List[Document]:
    """
    GitHub repository collaborators reader.

    Retrieves the list of collaborators in a GitHub repository and converts them to documents.

    Each collaborator is converted to a document by doing the following:

        - The text of the document is the login.
        - The title of the document is also the login.
        - The extra_info of the document is a dictionary with the following keys:
            - login: str, the login of the user
            - type: str, the type of user e.g. "User"
            - site_admin: bool, whether the user has admin permissions
            - role_name: str, e.g. "admin"
            - name: str, the name of the user, if available
            - email: str, the email of the user, if available
            - permissions: str, the permissions of the user, if available


    :return: list of documents
    """
    documents = []
    page = 1
    # Loop until there are no more collaborators
    while True:
        collaborators: Dict = self._loop.run_until_complete(
            self._github_client.get_collaborators(
                self._owner, self._repo, page=page
            )
        )

        if len(collaborators) == 0:
            print_if_verbose(self._verbose, "No more collaborators found, stopping")

            break
        print_if_verbose(
            self._verbose,
            f"Found {len(collaborators)} collaborators in the repo page {page}",
        )
        page += 1
        for collab in collaborators:
            extra_info = {
                "login": collab["login"],
                "type": collab["type"],
                "site_admin": collab["site_admin"],
                "role_name": collab["role_name"],
            }
            if collab.get("name") is not None:
                extra_info["name"] = collab["name"]
            if collab.get("email") is not None:
                extra_info["email"] = collab["email"]
            if collab.get("permissions") is not None:
                extra_info["permissions"] = collab["permissions"]
            document = Document(
                doc_id=str(collab["login"]),
                text=str(collab["login"]),  # unsure for this
                extra_info=extra_info,
            )
            documents.append(document)

        print_if_verbose(self._verbose, f"Resulted in {len(documents)} documents")

    return documents

GitHubRepositoryIssuesReader #

Bases: BaseReader

GitHub repository issues reader.

Retrieves the list of issues of a GitHub repository and returns a list of documents.

Examples:

>>> reader = GitHubRepositoryIssuesReader("owner", "repo")
>>> issues = reader.load_data()
>>> print(issues)
Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/issues/base.py 
 43
 44
 45
 46
 47
 48
 49
 50
 51
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
class GitHubRepositoryIssuesReader(BaseReader):
    """
    GitHub repository issues reader.

    Retrieves the list of issues of a GitHub repository and returns a list of documents.

    Examples:
        >>> reader = GitHubRepositoryIssuesReader("owner", "repo")
        >>> issues = reader.load_data()
        >>> print(issues)

    """

    class IssueState(enum.Enum):
        """
        Issue type.

        Used to decide what issues to retrieve.

        Attributes:
            - OPEN: Just open issues. This is the default.
            - CLOSED: Just closed issues.
            - ALL: All issues, open and closed.

        """

        OPEN = "open"
        CLOSED = "closed"
        ALL = "all"

    class FilterType(enum.Enum):
        """
        Filter type.

        Used to determine whether the filter is inclusive or exclusive.
        """

        EXCLUDE = enum.auto()
        INCLUDE = enum.auto()

    def __init__(
        self,
        github_client: BaseGitHubIssuesClient,
        owner: str,
        repo: str,
        verbose: bool = False,
    ):
        """
        Initialize params.

        Args:
            - github_client (BaseGitHubIssuesClient): GitHub client.
            - owner (str): Owner of the repository.
            - repo (str): Name of the repository.
            - verbose (bool): Whether to print verbose messages.

        Raises:
            - `ValueError`: If the github_token is not provided and
                the GITHUB_TOKEN environment variable is not set.

        """
        super().__init__()

        self._owner = owner
        self._repo = repo
        self._verbose = verbose

        # Set up the event loop
        try:
            self._loop = asyncio.get_running_loop()
        except RuntimeError:
            # If there is no running loop, create a new one
            self._loop = asyncio.new_event_loop()
            asyncio.set_event_loop(self._loop)

        self._github_client = github_client

    def load_data(
        self,
        state: Optional[IssueState] = IssueState.OPEN,
        labelFilters: Optional[List[Tuple[str, FilterType]]] = None,
    ) -> List[Document]:
        """
        Load issues from a repository and converts them to documents.

        Each issue is converted to a document by doing the following:

        - The text of the document is the concatenation of the title and the body of the issue.
        - The title of the document is the title of the issue.
        - The doc_id of the document is the issue number.
        - The extra_info of the document is a dictionary with the following keys:
            - state: State of the issue.
            - created_at: Date when the issue was created.
            - closed_at: Date when the issue was closed. Only present if the issue is closed.
            - url: URL of the issue.
            - assignee: Login of the user assigned to the issue. Only present if the issue is assigned.
        - The embedding of the document is None.
        - The doc_hash of the document is None.

        Args:
            - state (IssueState): State of the issues to retrieve. Default is IssueState.OPEN.
            - labelFilters: an optional list of filters to apply to the issue list based on labels.

        :return: list of documents

        """
        documents = []
        page = 1
        # Loop until there are no more issues
        while True:
            issues: Dict = self._loop.run_until_complete(
                self._github_client.get_issues(
                    self._owner, self._repo, state=state.value, page=page
                )
            )

            if len(issues) == 0:
                print_if_verbose(self._verbose, "No more issues found, stopping")

                break
            print_if_verbose(
                self._verbose, f"Found {len(issues)} issues in the repo page {page}"
            )
            page += 1
            filterCount = 0
            for issue in issues:
                if not self._must_include(labelFilters, issue):
                    filterCount += 1
                    continue
                title = issue["title"]
                body = issue["body"]
                document = Document(
                    doc_id=str(issue["number"]),
                    text=f"{title}\n{body}",
                )
                extra_info = {
                    "state": issue["state"],
                    "created_at": issue["created_at"],
                    # url is the API URL
                    "url": issue["url"],
                    # source is the HTML URL, more convenient for humans
                    "source": issue["html_url"],
                }
                if issue["closed_at"] is not None:
                    extra_info["closed_at"] = issue["closed_at"]
                if issue["assignee"] is not None:
                    extra_info["assignee"] = issue["assignee"]["login"]
                if issue["labels"] is not None:
                    extra_info["labels"] = [label["name"] for label in issue["labels"]]
                document.extra_info = extra_info
                documents.append(document)

            print_if_verbose(self._verbose, f"Resulted in {len(documents)} documents")
            if labelFilters is not None:
                print_if_verbose(self._verbose, f"Filtered out {filterCount} issues")

        return documents

    def _must_include(self, labelFilters, issue):
        if labelFilters is None:
            return True
        labels = [label["name"] for label in issue["labels"]]
        for labelFilter in labelFilters:
            label = labelFilter[0]
            filterType = labelFilter[1]
            # Only include issues with the label and value
            if filterType == self.FilterType.INCLUDE:
                return label in labels
            elif filterType == self.FilterType.EXCLUDE:
                return label not in labels

        return True

IssueState #

Bases: Enum

Issue type.

Used to decide what issues to retrieve.

Attributes:

Name Type Description
- OPEN

Just open issues. This is the default.
- CLOSED

Just closed issues.
- ALL

All issues, open and closed.
Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/issues/base.py 
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
class IssueState(enum.Enum):
    """
    Issue type.

    Used to decide what issues to retrieve.

    Attributes:
        - OPEN: Just open issues. This is the default.
        - CLOSED: Just closed issues.
        - ALL: All issues, open and closed.

    """

    OPEN = "open"
    CLOSED = "closed"
    ALL = "all"

FilterType #

Bases: Enum

Filter type.

Used to determine whether the filter is inclusive or exclusive.

Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/issues/base.py 
73
74
75
76
77
78
79
80
81
class FilterType(enum.Enum):
    """
    Filter type.

    Used to determine whether the filter is inclusive or exclusive.
    """

    EXCLUDE = enum.auto()
    INCLUDE = enum.auto()

load_data #

load_data(state: Optional[IssueState] = OPEN, labelFilters: Optional[List[Tuple[str, FilterType]]] = None) -> List[Document]

Load issues from a repository and converts them to documents.

Each issue is converted to a document by doing the following:

  • The text of the document is the concatenation of the title and the body of the issue.
  • The title of the document is the title of the issue.
  • The doc_id of the document is the issue number.
  • The extra_info of the document is a dictionary with the following keys:
    • state: State of the issue.
    • created_at: Date when the issue was created.
    • closed_at: Date when the issue was closed. Only present if the issue is closed.
    • url: URL of the issue.
    • assignee: Login of the user assigned to the issue. Only present if the issue is assigned.
  • The embedding of the document is None.
  • The doc_hash of the document is None.

Parameters:

Name Type Description Default
- state (IssueState

State of the issues to retrieve. Default is IssueState.OPEN.

 required
- labelFilters

an optional list of filters to apply to the issue list based on labels.

 required

:return: list of documents

Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/issues/base.py 
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
def load_data(
    self,
    state: Optional[IssueState] = IssueState.OPEN,
    labelFilters: Optional[List[Tuple[str, FilterType]]] = None,
) -> List[Document]:
    """
    Load issues from a repository and converts them to documents.

    Each issue is converted to a document by doing the following:

    - The text of the document is the concatenation of the title and the body of the issue.
    - The title of the document is the title of the issue.
    - The doc_id of the document is the issue number.
    - The extra_info of the document is a dictionary with the following keys:
        - state: State of the issue.
        - created_at: Date when the issue was created.
        - closed_at: Date when the issue was closed. Only present if the issue is closed.
        - url: URL of the issue.
        - assignee: Login of the user assigned to the issue. Only present if the issue is assigned.
    - The embedding of the document is None.
    - The doc_hash of the document is None.

    Args:
        - state (IssueState): State of the issues to retrieve. Default is IssueState.OPEN.
        - labelFilters: an optional list of filters to apply to the issue list based on labels.

    :return: list of documents

    """
    documents = []
    page = 1
    # Loop until there are no more issues
    while True:
        issues: Dict = self._loop.run_until_complete(
            self._github_client.get_issues(
                self._owner, self._repo, state=state.value, page=page
            )
        )

        if len(issues) == 0:
            print_if_verbose(self._verbose, "No more issues found, stopping")

            break
        print_if_verbose(
            self._verbose, f"Found {len(issues)} issues in the repo page {page}"
        )
        page += 1
        filterCount = 0
        for issue in issues:
            if not self._must_include(labelFilters, issue):
                filterCount += 1
                continue
            title = issue["title"]
            body = issue["body"]
            document = Document(
                doc_id=str(issue["number"]),
                text=f"{title}\n{body}",
            )
            extra_info = {
                "state": issue["state"],
                "created_at": issue["created_at"],
                # url is the API URL
                "url": issue["url"],
                # source is the HTML URL, more convenient for humans
                "source": issue["html_url"],
            }
            if issue["closed_at"] is not None:
                extra_info["closed_at"] = issue["closed_at"]
            if issue["assignee"] is not None:
                extra_info["assignee"] = issue["assignee"]["login"]
            if issue["labels"] is not None:
                extra_info["labels"] = [label["name"] for label in issue["labels"]]
            document.extra_info = extra_info
            documents.append(document)

        print_if_verbose(self._verbose, f"Resulted in {len(documents)} documents")
        if labelFilters is not None:
            print_if_verbose(self._verbose, f"Filtered out {filterCount} issues")

    return documents

GithubRepositoryReader #

Bases: BaseReader

Github repository reader.

Retrieves the contents of a Github repository and returns a list of documents. The documents are either the contents of the files in the repository or the text extracted from the files using the parser.

Examples:

>>> from llama_index.core.instrumentation import get_dispatcher
>>> from llama_index.core.instrumentation.event_handlers import BaseEventHandler
>>>
>>> # Set up event handler
>>> class GitHubEventHandler(BaseEventHandler):
...     def handle(self, event):
...         if isinstance(event, GitHubFileProcessedEvent):
...             print(f"Processed file: {event.file_path}")
...
>>> dispatcher = get_dispatcher()
>>> handler = GitHubEventHandler()
>>> dispatcher.add_event_handler(handler)
>>>
>>> client = github_client = GithubClient(
...    github_token=os.environ["GITHUB_TOKEN"],
...    verbose=True
... )
>>> reader = GithubRepositoryReader(
...    github_client=github_client,
...    owner="run-llama",
...    repo="llama_index",
... )
>>> # Load all files from a branch
>>> branch_documents = reader.load_data(branch="main")
>>> # Load all files from a commit
>>> commit_documents = reader.load_data(commit_sha="commit_sha")
Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/repository/base.py 
 52
 53
 54
 55
 56
 57
 58
 59
 60
 61
 62
 63
 64
 65
 66
 67
 68
 69
 70
 71
 72
 73
 74
 75
 76
 77
 78
 79
 80
 81
 82
 83
 84
 85
 86
 87
 88
 89
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
class GithubRepositoryReader(BaseReader):
    """
    Github repository reader.

    Retrieves the contents of a Github repository and returns a list of documents.
    The documents are either the contents of the files in the repository or the text
    extracted from the files using the parser.

    Examples:
        >>> from llama_index.core.instrumentation import get_dispatcher
        >>> from llama_index.core.instrumentation.event_handlers import BaseEventHandler
        >>>
        >>> # Set up event handler
        >>> class GitHubEventHandler(BaseEventHandler):
        ...     def handle(self, event):
        ...         if isinstance(event, GitHubFileProcessedEvent):
        ...             print(f"Processed file: {event.file_path}")
        ...
        >>> dispatcher = get_dispatcher()
        >>> handler = GitHubEventHandler()
        >>> dispatcher.add_event_handler(handler)
        >>>
        >>> client = github_client = GithubClient(
        ...    github_token=os.environ["GITHUB_TOKEN"],
        ...    verbose=True
        ... )
        >>> reader = GithubRepositoryReader(
        ...    github_client=github_client,
        ...    owner="run-llama",
        ...    repo="llama_index",
        ... )
        >>> # Load all files from a branch
        >>> branch_documents = reader.load_data(branch="main")
        >>> # Load all files from a commit
        >>> commit_documents = reader.load_data(commit_sha="commit_sha")

    """

    class FilterType(enum.Enum):
        """
        Filter type.

        Used to determine whether the filter is inclusive or exclusive.

        Attributes:
            - EXCLUDE: Exclude the files in the directories or with the extensions.
            - INCLUDE: Include only the files in the directories or with the extensions.

        """

        EXCLUDE = enum.auto()
        INCLUDE = enum.auto()

    def __init__(
        self,
        github_client: BaseGithubClient,
        owner: str,
        repo: str,
        use_parser: bool = False,
        verbose: bool = False,
        concurrent_requests: int = 5,
        timeout: Optional[int] = 5,
        retries: int = 0,
        filter_directories: Optional[Tuple[List[str], FilterType]] = None,
        filter_file_extensions: Optional[Tuple[List[str], FilterType]] = None,
        filter_file_paths: Optional[Tuple[List[str], FilterType]] = None,
        custom_parsers: Optional[Dict[str, BaseReader]] = None,
        process_file_callback: Optional[Callable[[str, int], tuple[bool, str]]] = None,
        custom_folder: Optional[str] = None,
        logger: Optional[logging.Logger] = None,
        fail_on_error: bool = True,
    ):
        """
        Initialize params.

        Args:
            - github_client (BaseGithubClient): Github client.
            - owner (str): Owner of the repository.
            - repo (str): Name of the repository.
            - use_parser (bool): Whether to use the parser to extract
                the text from the files.
            - verbose (bool): Whether to print verbose messages.
            - concurrent_requests (int): Number of concurrent requests to
                make to the Github API.
            - timeout (int or None): Timeout for the requests to the Github API. Default is 5.
            - retries (int): Number of retries for requests made to the Github API. Default is 0.
              This limit applies individually to each request made by this class.
            - filter_directories (Optional[Tuple[List[str], FilterType]]): Tuple
                containing a list of directories and a FilterType. If the FilterType
                is INCLUDE, only the files in the directories in the list will be
                included. If the FilterType is EXCLUDE, the files in the directories
                in the list will be excluded.
            - filter_file_extensions (Optional[Tuple[List[str], FilterType]]): Tuple
                containing a list of file extensions and a FilterType. If the
                FilterType is INCLUDE, only the files with the extensions in the list
                will be included. If the FilterType is EXCLUDE, the files with the
                extensions in the list will be excluded.
            - custom_parsers (Optional[Dict[str, BaseReader]]): Dictionary mapping
                file types to custom parsers for processing specific file extensions.
            - process_file_callback (Optional[Callable[[str, int], tuple[bool, str]]]): Callback function
                to determine if a file should be processed. Takes file_path and file_size
                Returns a tuple of (should_process: bool, reason: str).
            - custom_folder (Optional[str]): Custom folder path for temporary file storage in custom parsers.
                Defaults to current working directory.
            - logger (Optional[logging.Logger]): Custom logger instance.
            - fail_on_error (bool): Whether to raise exceptions on processing errors.
                If False, errors are logged and processing continues.

        Note:
            The reader uses LlamaIndex's instrumentation system for event notifications.
            Events are automatically dispatched to any registered event handlers via the global dispatcher.
            Available events include:
            - GitHubRepositoryProcessingStartedEvent
            - GitHubRepositoryProcessingCompletedEvent
            - GitHubTotalFilesToProcessEvent
            - GitHubFileProcessingStartedEvent
            - GitHubFileProcessedEvent
            - GitHubFileSkippedEvent
            - GitHubFileFailedEvent

        Raises:
            - `ValueError`: If the github_token is not provided and
                the GITHUB_TOKEN environment variable is not set.

        """
        super().__init__()

        self._owner = owner
        self._repo = repo
        self._use_parser = use_parser
        self._verbose = verbose
        self._concurrent_requests = concurrent_requests
        self._timeout = timeout
        self._retries = retries
        self._filter_directories = filter_directories
        self._filter_file_extensions = filter_file_extensions
        self._filter_file_paths = filter_file_paths
        self.custom_folder = custom_folder or os.getcwd()
        self.logger = logger or logging.getLogger(__name__)
        self._process_file_callback = process_file_callback
        self.fail_on_error = fail_on_error

        # Set up the event loop
        try:
            self._loop = asyncio.get_running_loop()
        except RuntimeError:
            # If there is no running loop, create a new one
            self._loop = asyncio.new_event_loop()
            asyncio.set_event_loop(self._loop)

        self._github_client = github_client

        self._file_readers: Dict[str, BaseReader] = custom_parsers or {}
        self._supported_suffix = list(DEFAULT_FILE_READER_CLS.keys())
        self.dispatcher = get_dispatcher()

    def _check_filter_directories(self, tree_obj_path: str) -> bool:
        """
        Check if a tree object should be allowed based on the directories.

        :param `tree_obj_path`: path of the tree object i.e. 'llama_index/readers'

        :return: True if the tree object should be allowed, False otherwise
        """
        if self._filter_directories is None:
            return True
        filter_directories, filter_type = self._filter_directories
        print_if_verbose(
            self._verbose,
            f"Checking {tree_obj_path} whether to {filter_type} it"
            + f" based on the filter directories: {filter_directories}",
        )

        if filter_type == self.FilterType.EXCLUDE:
            print_if_verbose(
                self._verbose,
                f"Checking if {tree_obj_path} is not a subdirectory of any of the"
                " filter directories",
            )
            return not any(
                tree_obj_path.startswith(directory) for directory in filter_directories
            )
        if filter_type == self.FilterType.INCLUDE:
            print_if_verbose(
                self._verbose,
                f"Checking if {tree_obj_path} is a subdirectory of any of the filter"
                " directories",
            )
            return any(
                tree_obj_path.startswith(directory)
                or directory.startswith(tree_obj_path)
                for directory in filter_directories
            )
        raise ValueError(
            f"Unknown filter type: {filter_type}. "
            "Please use either 'INCLUDE' or 'EXCLUDE'."
        )

    def _check_filter_file_paths(self, tree_obj_path: str) -> bool:
        """
        Check if a tree object should be allowed based on the file paths.

        :param `tree_obj_path`: path of the tree object i.e. 'llama_index/readers'

        :return: True if the tree object should be allowed, False otherwise
        """
        if self._filter_file_paths is None:
            return True
        filter_file_paths, filter_type = self._filter_file_paths
        print_if_verbose(
            self._verbose,
            f"Checking {tree_obj_path} whether to {filter_type} it"
            + f" based on the filter file paths: {filter_file_paths}",
        )

        if filter_type == self.FilterType.EXCLUDE:
            to_exclude = tree_obj_path not in filter_file_paths
            file_extension = get_file_extension(tree_obj_path)
            reason = "File in Exclude List"
            if to_exclude:
                self.logger.info(f"Skipping file {tree_obj_path}: {reason}")
                self.dispatcher.event(
                    GitHubFileSkippedEvent(
                        file_path=tree_obj_path,
                        file_type=file_extension,
                        reason=reason,
                    )
                )
            return to_exclude
        if filter_type == self.FilterType.INCLUDE:
            return tree_obj_path in filter_file_paths
        raise ValueError(
            f"Unknown filter type: {filter_type}. "
            "Please use either 'INCLUDE' or 'EXCLUDE'."
        )

    def _check_user_callback(self, full_path: str, file_size: int) -> bool:
        """
        Determine if a file should be processed based on the callback function.

        :param full_path: Full path to the file
        :param file_size: Size of the file in bytes
        :return: True if file should be processed, False otherwise
        """
        if not self._process_file_callback:
            return True

        file_extension = get_file_extension(full_path)

        try:
            should_process, reason = self._process_file_callback(full_path, file_size)
        except Exception as e:
            self.logger.error(f"Error in process_file_callback for {full_path}: {e}")
            if self.fail_on_error:
                raise
            # If fail_on_error is False, skip the file
            reason = f"Callback error: {e!s}"
            should_process = False

        if not should_process:
            self.logger.info(f"Skipping file {full_path}: {reason}")
            self.dispatcher.event(
                GitHubFileSkippedEvent(
                    file_path=full_path,
                    file_type=file_extension,
                    reason=reason,
                )
            )
        return should_process

    def _check_filter_file_extensions(self, tree_obj_path: str) -> bool:
        """
        Check if a tree object should be allowed based on the file extensions.

        :param `tree_obj_path`: path of the tree object i.e. 'llama_index/indices'

        :return: True if the tree object should be allowed, False otherwise
        """
        if self._filter_file_extensions is None:
            return True
        filter_file_extensions, filter_type = self._filter_file_extensions
        print_if_verbose(
            self._verbose,
            f"Checking {tree_obj_path} whether to {filter_type} it"
            + f" based on the filter file extensions: {filter_file_extensions}",
        )

        if filter_type == self.FilterType.EXCLUDE:
            return get_file_extension(tree_obj_path) not in filter_file_extensions
        if filter_type == self.FilterType.INCLUDE:
            return get_file_extension(tree_obj_path) in filter_file_extensions
        raise ValueError(
            f"Unknown filter type: {filter_type}. "
            "Please use either 'INCLUDE' or 'EXCLUDE'."
        )

    def _allow_tree_obj(
        self, tree_obj_path: str, tree_obj_type: str, file_size: int = None
    ) -> bool:
        """
        Check if a tree object should be allowed.

        :param `tree_obj_path`: path of the tree object

        :return: True if the tree object should be allowed, False otherwise

        """
        if self._filter_directories is not None and tree_obj_type == "tree":
            return self._check_filter_directories(tree_obj_path)

        if self._filter_file_extensions is not None and tree_obj_type == "blob":
            return self._check_filter_directories(
                tree_obj_path
            ) and self._check_filter_file_extensions(tree_obj_path)

        if self._filter_file_paths is not None and tree_obj_type == "blob":
            return self._check_filter_file_paths(
                tree_obj_path
            ) and self._check_filter_directories(tree_obj_path)

        if file_size:
            return self._check_user_callback(tree_obj_path, file_size)

        return True

    def _load_data_from_commit(self, commit_sha: str) -> List[Document]:
        """
        Load data from a commit.

        Loads github repository data from a specific commit sha.

        :param `commit`: commit sha

        :return: list of documents
        """
        repo_name = f"{self._owner}/{self._repo}"

        # Notify repository processing started
        self.dispatcher.event(
            GitHubRepositoryProcessingStartedEvent(
                repository_name=repo_name, branch_or_commit=commit_sha
            )
        )

        commit_response: GitCommitResponseModel = self._loop.run_until_complete(
            self._github_client.get_commit(
                self._owner,
                self._repo,
                commit_sha,
                timeout=self._timeout,
                retries=self._retries,
            )
        )

        tree_sha = commit_response.commit.tree.sha
        blobs_and_paths = self._loop.run_until_complete(self._recurse_tree(tree_sha))

        print_if_verbose(self._verbose, f"got {len(blobs_and_paths)} blobs")

        # Notify total files to process
        self.dispatcher.event(
            GitHubTotalFilesToProcessEvent(
                repository_name=repo_name,
                branch_or_commit=commit_sha,
                total_files=len(blobs_and_paths),
            )
        )

        documents = self._loop.run_until_complete(
            self._generate_documents(
                blobs_and_paths=blobs_and_paths,
                id=commit_sha,
            )
        )

        # Notify repository processing completed
        self.dispatcher.event(
            GitHubRepositoryProcessingCompletedEvent(
                repository_name=repo_name,
                branch_or_commit=commit_sha,
                total_documents=len(documents),
            )
        )

        return documents

    def _load_data_from_branch(
        self,
        branch: str,
        file_path: Optional[str] = None,
    ) -> List[Document]:
        """
        Load data from a branch.

        Loads github repository data from a specific branch.

        :param `branch`: branch name
        :param `file_path`: the full path to a specific file in the repo

        :return: list of documents
        """
        repo_name = f"{self._owner}/{self._repo}"

        # Notify repository processing started
        self.dispatcher.event(
            GitHubRepositoryProcessingStartedEvent(
                repository_name=repo_name, branch_or_commit=branch
            )
        )

        branch_data: GitBranchResponseModel = self._loop.run_until_complete(
            self._github_client.get_branch(
                self._owner,
                self._repo,
                branch,
                timeout=self._timeout,
                retries=self._retries,
            )
        )

        tree_sha = branch_data.commit.commit.tree.sha
        blobs_and_paths = self._loop.run_until_complete(self._recurse_tree(tree_sha))

        print_if_verbose(self._verbose, f"got {len(blobs_and_paths)} blobs")

        # Notify total files to process
        self.dispatcher.event(
            GitHubTotalFilesToProcessEvent(
                repository_name=repo_name,
                branch_or_commit=branch,
                total_files=len(blobs_and_paths),
            )
        )

        documents = self._loop.run_until_complete(
            self._generate_documents(
                blobs_and_paths=blobs_and_paths,
                id=branch,
            )
        )

        # Notify repository processing completed
        self.dispatcher.event(
            GitHubRepositoryProcessingCompletedEvent(
                repository_name=repo_name,
                branch_or_commit=branch,
                total_documents=len(documents),
            )
        )

        return documents

    def load_data(
        self,
        commit_sha: Optional[str] = None,
        branch: Optional[str] = None,
        file_path: Optional[str] = None,
    ) -> List[Document]:
        """
        Load data from a commit or a branch.

        Loads github repository data from a specific commit sha or a branch.

        :param `commit_sha`: commit sha
        :param `branch`: branch name
        :param `file_path`: the full path to a specific file in the repo

        :return: list of documents
        """
        if commit_sha is not None and branch is not None:
            raise ValueError("You can only specify one of commit or branch.")

        if commit_sha is None and branch is None:
            raise ValueError("You must specify one of commit or branch.")

        if commit_sha is not None:
            return self._load_data_from_commit(commit_sha)

        if branch is not None:
            return self._load_data_from_branch(branch, file_path=file_path)

        raise ValueError("You must specify one of commit or branch.")

    async def _recurse_tree(
        self,
        tree_sha: str,
        current_path: str = "",
        current_depth: int = 0,
        max_depth: int = -1,
    ) -> Any:
        """
        Recursively get all blob tree objects in a tree.

        And construct their full path relative to the root of the repository.
        (see GitTreeResponseModel.GitTreeObject in
            github_api_client.py for more information)

        :param `tree_sha`: sha of the tree to recurse
        :param `current_path`: current path of the tree
        :param `current_depth`: current depth of the tree
        :return: list of tuples of
            (tree object, file's full path relative to the root of the repo)
        """
        if max_depth != -1 and current_depth > max_depth:
            return []

        blobs_and_full_paths: List[Tuple[GitTreeResponseModel.GitTreeObject, str]] = []
        print_if_verbose(
            self._verbose,
            "\t" * current_depth + f"current path: {current_path}",
        )

        tree_data: GitTreeResponseModel = await self._github_client.get_tree(
            self._owner,
            self._repo,
            tree_sha,
            timeout=self._timeout,
            retries=self._retries,
        )
        print_if_verbose(
            self._verbose, "\t" * current_depth + f"tree data: {tree_data}"
        )
        print_if_verbose(
            self._verbose, "\t" * current_depth + f"processing tree {tree_sha}"
        )
        for tree_obj in tree_data.tree:
            file_path = os.path.join(current_path, tree_obj.path)
            file_size = None
            if tree_obj.type == "blob":
                file_size = tree_obj.size
            if not self._allow_tree_obj(file_path, tree_obj.type, file_size):
                print_if_verbose(
                    self._verbose,
                    "\t" * current_depth + f"ignoring {tree_obj.path} due to filter",
                )
                continue

            print_if_verbose(
                self._verbose,
                "\t" * current_depth + f"tree object: {tree_obj}",
            )

            if tree_obj.type == "tree":
                print_if_verbose(
                    self._verbose,
                    "\t" * current_depth + f"recursing into {tree_obj.path}",
                )

                blobs_and_full_paths.extend(
                    await self._recurse_tree(
                        tree_obj.sha, file_path, current_depth + 1, max_depth
                    )
                )
            elif tree_obj.type == "blob":
                print_if_verbose(
                    self._verbose,
                    "\t" * current_depth + f"found blob {tree_obj.path}",
                )

                blobs_and_full_paths.append((tree_obj, file_path))

            print_if_verbose(
                self._verbose,
                "\t" * current_depth + f"blob and full paths: {blobs_and_full_paths}",
            )
        return blobs_and_full_paths

    def _get_base_url(self, blob_url):
        match = re.match(r"(https://[^/]+\.com/)", blob_url)
        if match:
            return match.group(1)
        else:
            return "https://github.com/"

    async def _generate_documents(
        self,
        blobs_and_paths: List[Tuple[GitTreeResponseModel.GitTreeObject, str]],
        id: str = "",
    ) -> List[Document]:
        """
        Generate documents from a list of blobs and their full paths.

        :param `blobs_and_paths`: list of tuples of
            (tree object, file's full path in the repo relative to the root of the repo)
        :param `id`: the branch name or commit sha used when loading the repo
        :return: list of documents
        """
        buffered_iterator = BufferedGitBlobDataIterator(
            blobs_and_paths=blobs_and_paths,
            github_client=self._github_client,
            owner=self._owner,
            repo=self._repo,
            loop=self._loop,
            buffer_size=self._concurrent_requests,  # TODO: make this configurable
            verbose=self._verbose,
            timeout=self._timeout,
            retries=self._retries,
        )

        documents = []
        async for blob_data, full_path in buffered_iterator:
            print_if_verbose(self._verbose, f"generating document for {full_path}")
            assert blob_data.encoding == "base64", (
                f"blob encoding {blob_data.encoding} not supported"
            )

            # Notify file processing started
            file_extension = get_file_extension(full_path)
            self.dispatcher.event(
                GitHubFileProcessingStartedEvent(
                    file_path=full_path, file_type=file_extension
                )
            )

            decoded_bytes = None
            try:
                decoded_bytes = base64.b64decode(blob_data.content)
                del blob_data.content
            except binascii.Error:
                print_if_verbose(
                    self._verbose, f"could not decode {full_path} as base64"
                )
                self.dispatcher.event(
                    GitHubFileFailedEvent(
                        file_path=full_path,
                        file_type=file_extension,
                        error="Could not decode as base64",
                    )
                )
                continue

            try:
                if self._use_parser or file_extension in self._file_readers:
                    document = self._parse_supported_file(
                        file_path=full_path,
                        file_content=decoded_bytes,
                        tree_sha=blob_data.sha,
                        tree_path=full_path,
                    )
                    if document is not None:
                        documents.append(document)
                        self.dispatcher.event(
                            GitHubFileProcessedEvent(
                                file_path=full_path,
                                file_type=file_extension,
                                file_size=len(decoded_bytes) if decoded_bytes else 0,
                                document=document,
                            )
                        )
                        continue
                    print_if_verbose(
                        self._verbose,
                        f"could not parse {full_path} as a supported file type"
                        + " - falling back to decoding as utf-8 raw text",
                    )
            except Exception as e:
                self.logger.error(f"Error processing file {full_path}: {e}")
                self.dispatcher.event(
                    GitHubFileFailedEvent(
                        file_path=full_path,
                        file_type=get_file_extension(full_path),
                        error=str(e),
                    )
                )
                if self.fail_on_error:
                    raise
                else:
                    self.logger.warning(
                        f"Failed to process file {full_path}: {e}. Skipping this file."
                    )
                    continue

            try:
                if decoded_bytes is None:
                    raise ValueError("decoded_bytes is None")
                decoded_text = decoded_bytes.decode("utf-8")
            except UnicodeDecodeError:
                print_if_verbose(
                    self._verbose, f"could not decode {full_path} as utf-8"
                )
                self.dispatcher.event(
                    GitHubFileFailedEvent(
                        file_path=full_path,
                        file_type=file_extension,
                        error="Could not decode as UTF-8",
                    )
                )
                continue
            print_if_verbose(
                self._verbose,
                f"got {len(decoded_text)} characters"
                + f"- adding to documents - {full_path}",
            )
            url = os.path.join(
                self._get_base_url(blob_data.url),
                self._owner,
                self._repo,
                "blob/",
                id,
                full_path,
            )
            document = Document(
                text=decoded_text,
                doc_id=blob_data.sha,
                metadata={
                    "file_path": full_path,
                    "file_name": full_path.split("/")[-1],
                    "url": url,
                },
            )
            documents.append(document)
            self.dispatcher.event(
                GitHubFileProcessedEvent(
                    file_path=full_path,
                    file_type=file_extension,
                    file_size=len(decoded_text.encode("utf-8")),
                    document=document,
                )
            )

        return documents

    def _parse_supported_file(
        self,
        file_path: str,
        file_content: bytes,
        tree_sha: str,
        tree_path: str,
    ) -> Optional[Document]:
        """
        Parse a file if it is supported by a parser.

        :param `file_path`: path of the file in the repo
        :param `file_content`: content of the file
        :return: Document if the file is supported by a parser, None otherwise
        """
        file_extension = get_file_extension(file_path)
        if file_extension not in self._supported_suffix:
            # skip
            return None

        if file_extension not in self._file_readers:
            # initialize reader
            cls_ = DEFAULT_FILE_READER_CLS[file_extension]
            self._file_readers[file_extension] = cls_()

        reader = self._file_readers[file_extension]

        print_if_verbose(
            self._verbose,
            f"parsing {file_path}"
            + f"as {file_extension} with "
            + f"{reader.__class__.__name__}",
        )

        if self.custom_folder:
            with tempfile.NamedTemporaryFile(
                dir=self.custom_folder,
                suffix=f".{file_extension}",
                mode="w+b",
                delete=False,
            ) as tmpfile:
                parsed_file = self._start_parsing(
                    tmpfile, file_path, file_content, reader
                )
        else:
            with tempfile.TemporaryDirectory() as tmpdirname:
                with tempfile.NamedTemporaryFile(
                    dir=tmpdirname,
                    suffix=f".{file_extension}",
                    mode="w+b",
                    delete=False,
                ) as tmpfile:
                    parsed_file = self._start_parsing(
                        tmpfile, file_path, file_content, reader
                    )

        if parsed_file is None:
            return None
        return Document(
            text=parsed_file,
            doc_id=tree_sha,
            metadata={
                "file_path": file_path,
                "file_name": tree_path,
            },
        )

    def _start_parsing(
        self,
        tmpfile: tempfile.NamedTemporaryFile,
        file_path: str,
        file_content: bytes,
        reader: BaseReader,
    ):
        print_if_verbose(
            self._verbose,
            "created a temporary file" + f"{tmpfile.name} for parsing {file_path}",
        )
        tmpfile.write(file_content)
        tmpfile.flush()
        tmpfile.close()
        try:
            docs = reader.load_data(pathlib.Path(tmpfile.name))
            parsed_file = "\n\n".join([doc.get_text() for doc in docs])
        except Exception as e:
            print_if_verbose(self._verbose, f"error while parsing {file_path}")
            self.logger.error(
                "Error while parsing "
                + f"{file_path} with "
                + f"{reader.__class__.__name__}:\n{e}"
            )
            parsed_file = None
        finally:
            os.remove(tmpfile.name)
        return parsed_file

FilterType #

Bases: Enum

Filter type.

Used to determine whether the filter is inclusive or exclusive.

Attributes:

Name Type Description
- EXCLUDE

Exclude the files in the directories or with the extensions.
- INCLUDE

Include only the files in the directories or with the extensions.
Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/repository/base.py 
 90
 91
 92
 93
 94
 95
 96
 97
 98
 99
100
101
102
103
class FilterType(enum.Enum):
    """
    Filter type.

    Used to determine whether the filter is inclusive or exclusive.

    Attributes:
        - EXCLUDE: Exclude the files in the directories or with the extensions.
        - INCLUDE: Include only the files in the directories or with the extensions.

    """

    EXCLUDE = enum.auto()
    INCLUDE = enum.auto()

load_data #

load_data(commit_sha: Optional[str] = None, branch: Optional[str] = None, file_path: Optional[str] = None) -> List[Document]

Load data from a commit or a branch.

Loads github repository data from a specific commit sha or a branch.

:param commit_sha: commit sha :param branch: branch name :param file_path: the full path to a specific file in the repo

:return: list of documents

Source code in llama-index-integrations/readers/llama-index-readers-github/llama_index/readers/github/repository/base.py 
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
def load_data(
    self,
    commit_sha: Optional[str] = None,
    branch: Optional[str] = None,
    file_path: Optional[str] = None,
) -> List[Document]:
    """
    Load data from a commit or a branch.

    Loads github repository data from a specific commit sha or a branch.

    :param `commit_sha`: commit sha
    :param `branch`: branch name
    :param `file_path`: the full path to a specific file in the repo

    :return: list of documents
    """
    if commit_sha is not None and branch is not None:
        raise ValueError("You can only specify one of commit or branch.")

    if commit_sha is None and branch is None:
        raise ValueError("You must specify one of commit or branch.")

    if commit_sha is not None:
        return self._load_data_from_commit(commit_sha)

    if branch is not None:
        return self._load_data_from_branch(branch, file_path=file_path)

    raise ValueError("You must specify one of commit or branch.")