Skip to content

Support .txt files in LLMFileAnalysisOperator #70431

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
kaxil merged 1 commit into from
Jul 27, 2026
+27 −2
Merged

Support .txt files in LLMFileAnalysisOperator #70431

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions providers/common/ai/src/airflow/providers/common/ai/utils/file_analysis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,9 +52,10 @@
"parquet",
"pdf",
"png",
"txt",
)

_TEXT_LIKE_FORMATS = frozenset({"csv", "json", "log", "avro", "parquet"})
_TEXT_LIKE_FORMATS = frozenset({"csv", "json", "log", "avro", "parquet", "txt"})
_MULTI_MODAL_FORMATS = frozenset({"jpeg", "jpg", "pdf", "png"})
_COMPRESSION_SUFFIXES = {
"bz2": "bzip2",
Expand All @@ -63,7 +64,7 @@
"xz": "xz",
"zst": "zstd",
}
_GZIP_SUPPORTED_FORMATS = frozenset({"csv", "json", "log"})
_GZIP_SUPPORTED_FORMATS = frozenset({"csv", "json", "log", "txt"})
_TEXT_SAMPLE_HEAD_CHARS = 8_000
_TEXT_SAMPLE_TAIL_CHARS = 2_000
_MEDIA_TYPES = {
Expand Down
24 changes: 24 additions & 0 deletions providers/common/ai/tests/unit/common/ai/utils/test_file_analysis.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,28 @@ def test_text_file_analysis(self, tmp_path):
assert "first line" in request.user_content
assert "format=log" in request.user_content

def test_txt_file_analysis(self, tmp_path):
path = tmp_path / "notes.txt"
path.write_text("first line\nsecond line\n", encoding="utf-8")

request = build_file_analysis_request(
file_path=str(path),
file_conn_id=None,
prompt="Summarize the notes",
multi_modal=False,
max_files=20,
max_file_size_bytes=1024,
max_total_size_bytes=2048,
max_text_chars=500,
sample_rows=10,
)

assert isinstance(request, FileAnalysisRequest)
assert request.resolved_paths == [str(path)]
assert "Summarize the notes" in request.user_content
assert "first line" in request.user_content
assert "format=txt" in request.user_content

def test_file_conn_id_overrides_embedded_connection(self, tmp_path):
path = tmp_path / "data.json"
path.write_text('{"status": "ok"}', encoding="utf-8")
Expand Down Expand Up @@ -336,6 +358,8 @@ class TestFileAnalysisHelpers:
("dashboard.jpg", "jpg", None),
("report.pdf", "pdf", None),
("app", "log", None),
("notes.txt", "txt", None),
("notes.txt.gz", "txt", "gzip"),
],
)
def test_detect_file_format(self, tmp_path, filename, expected_format, expected_compression):
Expand Down