lukaszett/Knack-Scraper
1
1
Fork 1
Code Issues Pull requests Projects Releases Packages Wiki Activity

Implement Nodes to compute text embeddings

Browse source
This commit is contained in:
quorploop 2025-12-24 17:58:23 +01:00
parent 72765532d3
commit 49239e7e25
9 changed files with 505 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

7
transform/Dockerfile
View file

@ -17,6 +17,9 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
ENV GLINER_MODEL_ID=urchade/gliner_multi-v2.1
ENV GLINER_MODEL_PATH=/models/gliner_multi-v2.1
ENV MINILM_MODEL_ID=sentence-transformers/all-MiniLM-L6-v2
ENV MINILM_MODEL_PATH=/models/all-MiniLM-L6-v2
WORKDIR /app
COPY requirements.txt .
RUN pip install --no-cache-dir -r requirements.txt
@ -28,8 +31,10 @@ RUN apt install -y cron locales
# Ensure GLiNER helper scripts are available
COPY ensure_gliner_model.sh /usr/local/bin/ensure_gliner_model.sh
# Ensure MiniLM helper scripts are available
COPY ensure_minilm_model.sh /usr/local/bin/ensure_minilm_model.sh
COPY entrypoint.sh /usr/local/bin/entrypoint.sh
RUN chmod +x /usr/local/bin/ensure_gliner_model.sh /usr/local/bin/entrypoint.sh
RUN chmod +x /usr/local/bin/ensure_gliner_model.sh /usr/local/bin/ensure_minilm_model.sh /usr/local/bin/entrypoint.sh
COPY *.py .