Delwin Mathew
commited on
Commit
·
736fded
1
Parent(s):
923a315
add ner sample
Browse files- .gitignore +1 -0
- Dockerfile +17 -0
- app.py +44 -0
- requirements.txt +0 -0
.gitignore
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
/venv/
|
Dockerfile
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Read the doc: https://huggingface.co/docs/hub/spaces-sdks-docker
|
| 2 |
+
# you will also find guides on how best to write your Dockerfile
|
| 3 |
+
|
| 4 |
+
FROM python:3.11
|
| 5 |
+
|
| 6 |
+
RUN useradd -m -u 1000 user
|
| 7 |
+
USER user
|
| 8 |
+
ENV PATH="/home/user/.local/bin:$PATH"
|
| 9 |
+
|
| 10 |
+
WORKDIR /app
|
| 11 |
+
|
| 12 |
+
COPY --chown=user ./requirements.txt requirements.txt
|
| 13 |
+
RUN pip install --no-cache-dir --upgrade -r requirements.txt
|
| 14 |
+
|
| 15 |
+
COPY --chown=user . /app
|
| 16 |
+
EXPOSE 7860
|
| 17 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|
app.py
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
from fastapi import FastAPI
|
| 2 |
+
from pydantic import BaseModel
|
| 3 |
+
import spacy
|
| 4 |
+
|
| 5 |
+
app = FastAPI()
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
class NERRequest(BaseModel):
|
| 9 |
+
chunks: list[str]
|
| 10 |
+
|
| 11 |
+
|
| 12 |
+
@app.post("/process")
|
| 13 |
+
async def process_text(request: NERRequest):
|
| 14 |
+
nlp = spacy.load("en_legal_ner_trf")
|
| 15 |
+
redacted_chunks = []
|
| 16 |
+
supa_clien = []
|
| 17 |
+
redacted_count = 0
|
| 18 |
+
for text in request.chunks:
|
| 19 |
+
doc = nlp(text)
|
| 20 |
+
|
| 21 |
+
for ent in doc.ents:
|
| 22 |
+
print(f"{ent.text} - {ent.label_}")
|
| 23 |
+
metadata_record = {
|
| 24 |
+
"personal_info": ent.text,
|
| 25 |
+
"redaction_type": ent.label_,
|
| 26 |
+
}
|
| 27 |
+
|
| 28 |
+
# insert into the table to get the primary key
|
| 29 |
+
query = supa_clien.append(metadata_record)
|
| 30 |
+
|
| 31 |
+
# Form the redacted word with label and primary key (REDACTED_PERSON_1)
|
| 32 |
+
redacted_count += 1
|
| 33 |
+
redacted_word = f"REDACTED_{ent.label_}_{redacted_count}"
|
| 34 |
+
|
| 35 |
+
metadata_record["redacted_word"] = redacted_word
|
| 36 |
+
|
| 37 |
+
text = text.replace(ent.text, redacted_word)
|
| 38 |
+
|
| 39 |
+
redacted_chunks.append(text)
|
| 40 |
+
|
| 41 |
+
return {
|
| 42 |
+
"redacted_chunks": redacted_chunks,
|
| 43 |
+
"metadata": supa_clien,
|
| 44 |
+
}
|
requirements.txt
ADDED
|
Binary file (7.82 kB). View file
|
|
|