Skip to content

Commit

Permalink
change embedding model. ROOT move to HF embeddings
Browse files Browse the repository at this point in the history
  • Loading branch information
Ludovico Mori committed Nov 3, 2023
1 parent 4be0b0b commit 137ce7c
Show file tree
Hide file tree
Showing 6 changed files with 2,549 additions and 9 deletions.
7 changes: 3 additions & 4 deletions .github/workflows/dev-ci-cd.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,6 @@ on:
push:
branches:
- main
- dev-root
jobs:
deploy-dev-system:
runs-on: ubuntu-latest
Expand Down Expand Up @@ -88,20 +87,20 @@ jobs:
# stop any existing docker compose that's running
- name: Stop Docker Compose
run: |
ssh submit-t3desk 'bash -s' < ${{ github.workspace }}/deploy/dev/dev-stop.sh
ssh submit06 'bash -s' < ${{ github.workspace }}/deploy/dev/dev-stop.sh
# copy repository to machine
- name: Copy Repository
run: |
rsync -e ssh -r ${{ github.workspace}}/* --exclude .git/ --delete submit-t3desk:~/A2rchi-dev/
rsync -e ssh -r ${{ github.workspace}}/* --exclude .git/ --delete submit06:~/A2rchi-dev/
# run deploy script
- name: Run Deploy Script
run: |
export tag="${GITHUB_REF#refs/heads/}"
export tag="${tag//\//-}.${GITHUB_SHA}"
sed -i "s/BASE_TAG/${tag}/" ${{ github.workspace }}/deploy/dev/dev-install.sh
ssh submit-t3desk 'bash -s' < ${{ github.workspace }}/deploy/dev/dev-install.sh
ssh submit06 'bash -s' < ${{ github.workspace }}/deploy/dev/dev-install.sh
# clean up secret files
- name: Remove Secrets from Runner
Expand Down
2 changes: 1 addition & 1 deletion config/prod-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -104,7 +104,7 @@ utils:
HuggingFaceEmbeddings:
class: HuggingFaceEmbeddings
kwargs:
model_name: "sentence-transformers/all-mpnet-base-v2"
model_name: sentence-transformers/all-MiniLM-L6-v2 #"sentence-transformers/all-mpnet-base-v2"
model_kwargs:
device: 'cpu'
encode_kwargs:
Expand Down
4 changes: 2 additions & 2 deletions config/prod-meta-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,7 @@ chains:
ROLES:
- User
- A2rchi
- Expert
- Expert
#logging within base chain
logging:
#name of .log logfile to be saved in data folder.
Expand Down Expand Up @@ -103,7 +103,7 @@ utils:
HuggingFaceEmbeddings:
class: HuggingFaceEmbeddings
kwargs:
model_name: "sentence-transformers/all-mpnet-base-v2"
model_name: sentence-transformers/all-MiniLM-L6-v2 #"sentence-transformers/all-mpnet-base-v2"
model_kwargs:
device: 'cpu'
encode_kwargs:
Expand Down
5 changes: 3 additions & 2 deletions config/prod-root-config.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -28,6 +28,7 @@ chains:
- empty.list
- miscellanea.list
- root-docs.list
- root-tutorial.list
# - root-forum.list
base:
# roles that A2rchi knows about
Expand Down Expand Up @@ -94,7 +95,7 @@ utils:
reset_collection: True # reset the entire collection each time it is accessed by a new data manager instance
embeddings:
# choose one embedding from list below
EMBEDDING_NAME: OpenAIEmbeddings
EMBEDDING_NAME: HuggingFaceEmbeddings
# list of possible embeddings to use in vectorstore
EMBEDDING_CLASS_MAP:
OpenAIEmbeddings:
Expand All @@ -105,7 +106,7 @@ utils:
HuggingFaceEmbeddings:
class: HuggingFaceEmbeddings
kwargs:
model_name: "sentence-transformers/all-mpnet-base-v2"
model_name: sentence-transformers/all-MiniLM-L6-v2 #"sentence-transformers/all-mpnet-base-v2" is best but currently not working
model_kwargs:
device: 'cpu'
encode_kwargs:
Expand Down
45 changes: 45 additions & 0 deletions config/root-docs.list
Original file line number Diff line number Diff line change
@@ -1 +1,46 @@
https://root.cern/install
https://root.cern/manual/object_ownership
https://root.cern/
https://root.cern/manual/io_custom_classes
https://root.cern/manual/integrate_root_into_my_cmake_project
https://root.cern/manual/cling
https://root.cern/manual
https://root.cern/manual/io
https://root.cern/primer
https://root.cern/reference/
https://root.cern/manual/data_frame
https://root.cern/manual/histograms
https://root.cern/reference
https://root.cern/tutorials/
https://root.cern/manual/math
https://root.cern/manual/root_files
https://root.cern/manual/functional_parts
https://root.cern/topical
https://root.cern/for_developers
https://root.cern/manual/basics
https://root.cern/manual/python
https://root.cern/primer/
https://root.cern/blog
https://root.cern/manual/roofit
https://root.cern/about
https://root.cern/manual/signal_slot
https://root.cern/manual/jsroot
https://root.cern/manual/embed_root_in_gui
https://root.cern/cling/
https://root.cern/manual/fitting
https://root.cern/get_started
https://root.cern/cling
https://root.cern/manual/root_architecture_and_components
https://root.cern/manual/first_steps_with_root
https://root.cern/manual/graphs
https://root.cern/manual/multi_threading
https://root.cern/manual/trees
https://root.cern/contribute
https://root.cern/manual/creating_a_user_application
https://root.cern/manual/root_collections
https://root.cern/manual/physics_vectors
https://root.cern/manual/geometry
https://root.cern/topical/
https://root.cern/manual/root_macros_and_shared_libraries
https://root.cern/manual/graphics
https://root.cern/manual/tmva
Loading

0 comments on commit 137ce7c

Please sign in to comment.