From 4722dfbd767ad34ef2e5de3de4d8810c7de941b6 Mon Sep 17 00:00:00 2001 From: flavienbwk Date: Sun, 8 Sep 2024 13:51:26 -0400 Subject: [PATCH] 0.13.0: Increased chunk size for code and added auto-URL upgrade --- .github/workflows/deploy.yml | 8 ++++++++ api/api_loader.py | 2 +- api/dir_loader.py | 2 +- package.json | 2 +- 4 files changed, 11 insertions(+), 3 deletions(-) diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml index 22cd588..d54c320 100644 --- a/.github/workflows/deploy.yml +++ b/.github/workflows/deploy.yml @@ -26,6 +26,14 @@ jobs: provider_project_id: ${{ secrets.PROVIDER_PROJECT_ID }} provider_default_region: 'fr-par' provider_default_zone: 'fr-par-2' + - name: Get repochat domain run: echo "DOMAIN=${{ steps.deploy_repochat.outputs.domain }}" >> $GITHUB_OUTPUT id: repochat_domain + + - name: Set repo URL + run: | + REPO_URL="https://github.com/${{ github.repository }}" + curl -X POST "$DOMAIN/api/set-repo-url" \ + -H "Content-Type: application/json" \ + -d "{\"repoUrl\": \"$REPO_URL\"}" diff --git a/api/api_loader.py b/api/api_loader.py index 699ab09..37eb388 100644 --- a/api/api_loader.py +++ b/api/api_loader.py @@ -103,7 +103,7 @@ def split_docs(self, docs): processed_docs.append(doc) splitter = RecursiveCharacterTextSplitter( - chunk_size=512, + chunk_size=2048, chunk_overlap=20, separators=["\n\n", "\n", "(?<=\. )", " ", ""], ) diff --git a/api/dir_loader.py b/api/dir_loader.py index 94e49f0..73906e4 100644 --- a/api/dir_loader.py +++ b/api/dir_loader.py @@ -71,7 +71,7 @@ def split_docs(self, docs): # RecursiveTextSplitter # Chunk size big enough splitter = RecursiveCharacterTextSplitter( - chunk_size=512, + chunk_size=2048, chunk_overlap=20, separators=["\n\n", "\n", "(?<=\. )", " ", ""], ) diff --git a/package.json b/package.json index 7d7d5c7..0cfc5fa 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "gh-action-repochat", - "version": "0.12.0", + "version": "0.13.0", "type": "module", "description": "GitHub Action to run repochat", "main": "index.js",