Skip to content

full rebuild of knowledge base code with hybrid search and ampere docs #67

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
JoeStech merged 3 commits into from
Mar 20, 2026
Merged

full rebuild of knowledge base code with hybrid search and ampere docs #67

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
b4f2a5c
full rebuild of knowledge base code with hybrid search and ampere docs
JoeStech Mar 20, 2026
8fbcd9d
Apply suggestion from @Copilot
JoeStech Mar 20, 2026
be402db
Apply suggestion from @Copilot
JoeStech Mar 20, 2026
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
14 changes: 12 additions & 2 deletions embedding-generation/Dockerfile
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,9 +19,15 @@ FROM ${EMBEDDING_BASE_IMAGE} AS intrinsic-chunks

FROM ubuntu:24.04 AS builder

ARG SOURCES_FILE=vector-db-sources.csv
ARG EMBEDDING_MODEL=all-MiniLM-L6-v2

ENV DEBIAN_FRONTEND=noninteractive \
PIP_INDEX_URL=https://download.pytorch.org/whl/cpu \
PIP_EXTRA_INDEX_URL=https://pypi.org/simple
PIP_EXTRA_INDEX_URL=https://pypi.org/simple \
SENTENCE_TRANSFORMER_MODEL=${EMBEDDING_MODEL} \
HF_HOME=/embedding-data/.cache/huggingface \
SENTENCE_TRANSFORMERS_HOME=/embedding-data/.cache/sentence_transformers

# Install Python
RUN apt-get update && apt-get install -y --no-install-recommends \
Expand All @@ -32,6 +38,7 @@ WORKDIR /embedding-data

# Copy Python scripts and dependencies
COPY generate-chunks.py .
COPY document_chunking.py .
COPY local_vectorstore_creation.py .
COPY vector-db-sources.csv .
COPY requirements.txt .
Expand All @@ -42,8 +49,11 @@ COPY --from=intrinsic-chunks /embedding-data/intrinsic_chunks ./intrinsic_chunks
# Install Python dependencies (force CPU-only torch)
RUN pip3 install --no-cache-dir --break-system-packages -r requirements.txt

# Pre-download the embedding model so local/offline loads succeed later in the build.
RUN python3 -c "from sentence_transformers import SentenceTransformer; import os; SentenceTransformer(os.environ['SENTENCE_TRANSFORMER_MODEL'], cache_folder=os.environ['SENTENCE_TRANSFORMERS_HOME'])"

# Generate vector database
RUN python3 generate-chunks.py vector-db-sources.csv && \
RUN python3 generate-chunks.py ${SOURCES_FILE} && \
python3 local_vectorstore_creation.py && \
rm -f embeddings_*.txt

Expand Down
Loading
Loading