montazerh82/hazm_docker
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

some changes in source

Browse Source
This commit is contained in:
HamidReza Montazer 2025-02-04 06:03:37 +00:00
parent 96bf9b7290
commit fb74c37954
3 changed files with 10 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.dockerignore
View File

@ -1 +1,4 @@
Dockerfile
.dockerignore
docker-compose.yml
.env .env

11
Dockerfile
View File

@ -1,9 +1,10 @@
FROM python:3.10-slim FROM 192.168.23.75/tavasi/hazm:base
WORKDIR /app
COPY . .
RUN pip install -r requirements.txt COPY . /src/
WORKDIR /src/app
EXPOSE 5110 EXPOSE 5110
CMD ["python", "app/main.py"]
CMD python main.py

4
app/hazm_api.py
View File

@ -32,6 +32,7 @@ word_tokenizer = WordTokenizer()
postagger = POSTagger(model=os.path.join(path_base_model, 'hazm/pos_tagger.model')) postagger = POSTagger(model=os.path.join(path_base_model, 'hazm/pos_tagger.model'))
lemmatizer = Lemmatizer() lemmatizer = Lemmatizer()
parser = DependencyParser(tagger=postagger, lemmatizer=lemmatizer, working_dir=os.path.join(path_base_model, 'hazm/universal_dependency_parser')) parser = DependencyParser(tagger=postagger, lemmatizer=lemmatizer, working_dir=os.path.join(path_base_model, 'hazm/universal_dependency_parser'))
chunker = Chunker(model=os.path.join(path_base_model, 'hazm/chunker.model'))
def dependency_parse(data): def dependency_parse(data):
tokens = word_tokenizer.tokenize(data.text) tokens = word_tokenizer.tokenize(data.text)
@ -72,9 +73,6 @@ async def plot_dependency_tree(data: TextData):
@router.post("/chunks", tags=['Hazm']) @router.post("/chunks", tags=['Hazm'])
async def chunks(data: TextData): async def chunks(data: TextData):
word_tokenizer = WordTokenizer()
postagger = POSTagger(model=path_base_model + 'hazm/pos_tagger.model')
chunker = Chunker(model=path_base_model + 'hazm/chunker.model')
tokens = word_tokenizer.tokenize(data.text) tokens = word_tokenizer.tokenize(data.text)
pos_tags = postagger.tag(tokens) pos_tags = postagger.tag(tokens)
result = chunker.parse(pos_tags) result = chunker.parse(pos_tags)