apunkt/dograh
1
0
Fork 0
mirror of https://github.com/dograh-hq/dograh.git synced 2026-06-07 07:55:16 +02:00
Code Issues Projects Releases Packages Wiki Activity

fix: bake punkt_tab file into docker images

Browse source
This commit is contained in:
Sabiha Khan 2026-04-11 18:20:25 +05:30
parent 0bdb65f197
commit 0a972ef66d
1 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
api/Dockerfile
View file

@ -26,6 +26,8 @@ RUN pip install --user --no-cache-dir -r requirements.txt && \
# Copy and install pipecat from local submodule
COPY pipecat /tmp/pipecat
RUN pip install --user --no-cache-dir '/tmp/pipecat[cartesia,deepgram,openai,elevenlabs,groq,google,azure,sarvam,soundfile,silero,webrtc,local-smart-turn-v3,speechmatics,openrouter,camb]' && \
# Pre-download NLTK punkt_tab tokenizer data (required by pipecat at runtime)
python -c "import nltk; nltk.download('punkt_tab', quiet=True)" && \
# Clean up pip cache and temporary pipecat directory
rm -rf /root/.cache/pip /tmp/pipecat
@ -48,6 +50,9 @@ RUN apt-get update && apt-get install -y --no-install-recommends \
# Copy Python packages from builder stage
COPY --from=builder /root/.local /root/.local
# Copy NLTK data (punkt_tab tokenizer) from builder stage
COPY --from=builder /root/nltk_data /root/nltk_data
# Make sure scripts in .local are available
ENV PATH=/root/.local/bin:$PATH