(new docs): update branch and resolve conflicts around build

.devcontainer/devcontainer.json

@@ -12,7 +12,7 @@
 
  // The optional 'workspaceFolder' property is the path VS Code should open by default when
  // connected. This is typically a file mount in .devcontainer/docker-compose.yml
- "workspaceFolder": "/workspaces/${localWorkspaceFolderBasename}",
+ "workspaceFolder": "/workspaces/langchain",
 
  // Prevent the container from shutting down
  "overrideCommand": true

.devcontainer/docker-compose.yaml

@@ -6,7 +6,7 @@ services:
  context: ..
  volumes:
  # Update this to wherever you want VS Code to mount the folder of your project
- - ..:/workspaces:cached
+ - ..:/workspaces/langchain:cached
  networks:
  - langchain-network 
  # environment:

.github/workflows/_release.yml

@@ -177,7 +177,7 @@ jobs:
  env:
  MIN_VERSIONS: ${{ steps.min-version.outputs.min-versions }}
  run: |
- poetry run pip install $MIN_VERSIONS
+ poetry run pip install --force-reinstall $MIN_VERSIONS
  make tests
  working-directory: ${{ inputs.working-directory }}
 
@@ -297,14 +297,13 @@ jobs:
  with:
  name: dist
  path: ${{ inputs.working-directory }}/dist/
-
- - name: Create Release
+ 
+ - name: Create Tag
  uses: ncipollo/release-action@v1
- if: ${{ inputs.working-directory == 'libs/langchain' }}
  with:
  artifacts: "dist/*"
  token: ${{ secrets.GITHUB_TOKEN }}
- draft: false
- generateReleaseNotes: true
- tag: v${{ needs.build.outputs.version }}
+ generateReleaseNotes: false
+ tag: ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}
+ body: "# Release ${{needs.build.outputs.pkg-name}}==${{ needs.build.outputs.version }}\n\nPackage-specific release note generation coming soon."
  commit: ${{ github.sha }}

Makefile

@@ -17,16 +17,11 @@ clean: docs_clean api_docs_clean
 
 ## docs_build: Build the documentation.
 docs_build:
- docs/.local_build.sh
+ cd docs && make build-local
 
 ## docs_clean: Clean the documentation build artifacts.
 docs_clean:
- @if [ -d _dist ]; then \
- rm -r _dist; \
- echo "Directory _dist has been cleaned."; \
- else \
- echo "Nothing to clean."; \
- fi
+ cd docs && make clean
 
 ## docs_linkcheck: Run linkchecker on the documentation.
 docs_linkcheck:
@@ -60,12 +55,12 @@ spell_fix:
 
 ## lint: Run linting on the project.
 lint lint_package lint_tests:
- poetry run ruff docs templates cookbook
+ poetry run ruff check docs templates cookbook
  poetry run ruff format docs templates cookbook --diff
- poetry run ruff --select I docs templates cookbook
+ poetry run ruff check --select I docs templates cookbook
  git grep 'from langchain import' docs/docs templates cookbook | grep -vE 'from langchain import (hub)' && exit 1 || exit 0
 
 ## format: Format the project files.
 format format_diff:
  poetry run ruff format docs templates cookbook
- poetry run ruff --select I --fix docs templates cookbook
+ poetry run ruff check --select I --fix docs templates cookbook

cookbook/Multi_modal_RAG.ipynb

@@ -464,8 +464,8 @@
  " Check if the base64 data is an image by looking at the start of the data\n",
  " \"\"\"\n",
  " image_signatures = {\n",
- " b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
- " b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
+ " b\"\\xff\\xd8\\xff\": \"jpg\",\n",
+ " b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
  " b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
  " b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
  " }\n",

cookbook/Multi_modal_RAG_google.ipynb

@@ -185,7 +185,7 @@
  " )\n",
  " # Text summary chain\n",
  " model = VertexAI(\n",
- " temperature=0, model_name=\"gemini-pro\", max_output_tokens=1024\n",
+ " temperature=0, model_name=\"gemini-pro\", max_tokens=1024\n",
  " ).with_fallbacks([empty_response])\n",
  " summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n",
  "\n",
@@ -254,7 +254,7 @@
  "\n",
  "def image_summarize(img_base64, prompt):\n",
  " \"\"\"Make image summary\"\"\"\n",
- " model = ChatVertexAI(model_name=\"gemini-pro-vision\", max_output_tokens=1024)\n",
+ " model = ChatVertexAI(model=\"gemini-pro-vision\", max_tokens=1024)\n",
  "\n",
  " msg = model.invoke(\n",
  " [\n",
@@ -462,8 +462,8 @@
  " Check if the base64 data is an image by looking at the start of the data\n",
  " \"\"\"\n",
  " image_signatures = {\n",
- " b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
- " b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
+ " b\"\\xff\\xd8\\xff\": \"jpg\",\n",
+ " b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
  " b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
  " b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
  " }\n",
@@ -553,9 +553,7 @@
  " \"\"\"\n",
  "\n",
  " # Multi-modal LLM\n",
- " model = ChatVertexAI(\n",
- " temperature=0, model_name=\"gemini-pro-vision\", max_output_tokens=1024\n",
- " )\n",
+ " model = ChatVertexAI(temperature=0, model_name=\"gemini-pro-vision\", max_tokens=1024)\n",
  "\n",
  " # RAG pipeline\n",
  " chain = (\n",

cookbook/advanced_rag_eval.ipynb

@@ -532,8 +532,8 @@
  "def is_image_data(b64data):\n",
  " \"\"\"Check if the base64 data is an image by looking at the start of the data.\"\"\"\n",
  " image_signatures = {\n",
- " b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
- " b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
+ " b\"\\xff\\xd8\\xff\": \"jpg\",\n",
+ " b\"\\x89\\x50\\x4e\\x47\\x0d\\x0a\\x1a\\x0a\": \"png\",\n",
  " b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
  " b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
  " }\n",

cookbook/self_query_hotel_search.ipynb

@@ -355,15 +355,15 @@
  "metadata": {},
  "outputs": [],
  "source": [
- "attribute_info[-2][\n",
- " \"description\"\n",
- "] += f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
- "attribute_info[3][\n",
- " \"description\"\n",
- "] += f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
- "attribute_info[-3][\n",
- " \"description\"\n",
- "] += f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\""
+ "attribute_info[-2][\"description\"] += (\n",
+ " f\". Valid values are {sorted(latest_price['starrating'].value_counts().index.tolist())}\"\n",
+ ")\n",
+ "attribute_info[3][\"description\"] += (\n",
+ " f\". Valid values are {sorted(latest_price['maxoccupancy'].value_counts().index.tolist())}\"\n",
+ ")\n",
+ "attribute_info[-3][\"description\"] += (\n",
+ " f\". Valid values are {sorted(latest_price['country'].value_counts().index.tolist())}\"\n",
+ ")"
  ]
  },
  {
@@ -688,9 +688,9 @@
  "metadata": {},
  "outputs": [],
  "source": [
- "attribute_info[-3][\n",
- " \"description\"\n",
- "] += \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
+ "attribute_info[-3][\"description\"] += (\n",
+ " \". NOTE: Only use the 'eq' operator if a specific country is mentioned. If a region is mentioned, include all relevant countries in filter.\"\n",
+ ")\n",
  "chain = load_query_constructor_runnable(\n",
  " ChatOpenAI(model=\"gpt-3.5-turbo\", temperature=0),\n",
  " doc_contents,\n",

docs/.gitignore

@@ -1,2 +1,3 @@
 /.quarto/
 src/supabase.d.ts
+build

docs/Makefile

@@ -0,0 +1,105 @@
+# we build the docs in these stages:
+# 1. install quarto and python dependencies
+# 2. copy files from "source dir" to "intermediate dir"
+# 2. generate files like model feat table, etc in "intermediate dir"
+# 3. copy files to their right spots (e.g. langserve readme) in "intermediate dir"
+# 4. build the docs from "intermediate dir" to "output dir"
+
+SOURCE_DIR = docs/
+INTERMEDIATE_DIR = build/intermediate/docs
+VERIONED_INTERMEDIATE_DIR = build/versioned_intermediate/version-0.2.x/docs
+OUTPUT_DIR = build/output
+OUTPUT_DOCS_DIR = $(OUTPUT_DIR)/docs
+VERSIONED_DOCS_DIR = $(OUTPUT_DIR)/versioned_docs/version-0.2.x
+
+PYTHON = .venv/bin/python
+
+QUARTO_CMD ?= quarto
+
+PARTNER_DEPS_LIST := $(shell ls -1 ../libs/partners | grep -vE "airbyte|ibm" | xargs -I {} echo "../libs/partners/{}" | tr '\n' ' ')
+
+PORT ?= 3001
+
+clean:
+ rm -rf build
+
+install-vercel-deps:
+ yum -y update
+ yum install gcc bzip2-devel libffi-devel zlib-devel wget tar gzip rsync -y
+
+ wget -q https://github.com/quarto-dev/quarto-cli/releases/download/v1.3.450/quarto-1.3.450-linux-amd64.tar.gz
+ tar -xzf quarto-1.3.450-linux-amd64.tar.gz
+
+install-py-deps:
+ python3 -m venv .venv
+ $(PYTHON) -m pip install --upgrade pip
+ $(PYTHON) -m pip install --upgrade uv
+ $(PYTHON) -m uv pip install -r vercel_requirements.txt
+ $(PYTHON) -m uv pip install --editable $(PARTNER_DEPS_LIST)
+
+generate-files:
+ mkdir -p $(INTERMEDIATE_DIR)
+ cp -r $(SOURCE_DIR)/* $(INTERMEDIATE_DIR)
+ mkdir -p $(INTERMEDIATE_DIR)/templates
+ cp ../templates/docs/INDEX.md $(INTERMEDIATE_DIR)/templates/index.md
+ cp ../cookbook/README.md $(INTERMEDIATE_DIR)/cookbook.mdx
+
+ $(PYTHON) scripts/model_feat_table.py $(INTERMEDIATE_DIR)
+
+ $(PYTHON) scripts/copy_templates.py $(INTERMEDIATE_DIR)
+
+ wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O $(INTERMEDIATE_DIR)/langserve.md
+ $(PYTHON) scripts/resolve_local_links.py $(INTERMEDIATE_DIR)/langserve.md https://github.com/langchain-ai/langserve/tree/main/
+
+ wget -q https://raw.githubusercontent.com/langchain-ai/langgraph/main/README.md -O $(INTERMEDIATE_DIR)/langgraph.md
+ $(PYTHON) scripts/resolve_local_links.py $(INTERMEDIATE_DIR)/langgraph.md https://github.com/langchain-ai/langgraph/tree/main/
+
+ $(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(INTERMEDIATE_DIR)
+
+
+ mkdir -p $(VERIONED_INTERMEDIATE_DIR)
+ mkdir -p $(VERIONED_INTERMEDIATE_DIR)/templates
+ mkdir -p $(VERIONED_INTERMEDIATE_DIR)/integrations
+ mkdir -p $(VERIONED_INTERMEDIATE_DIR)/integrations/llms
+ cp $(INTERMEDIATE_DIR)/integrations/llms/index.mdx $(VERIONED_INTERMEDIATE_DIR)/integrations/llms/
+ cp $(INTERMEDIATE_DIR)/integrations/chat/index.mdx $(VERIONED_INTERMEDIATE_DIR)/integrations/chat/
+ cp -r $(INTERMEDIATE_DIR)/templates/* $(VERIONED_INTERMEDIATE_DIR)/templates/
+
+ wget -q https://raw.githubusercontent.com/langchain-ai/langserve/main/README.md -O $(VERIONED_INTERMEDIATE_DIR)/langserve.md
+ $(PYTHON) scripts/resolve_local_links.py $(VERIONED_INTERMEDIATE_DIR)/langserve.md https://github.com/langchain-ai/langserve/tree/main/
+
+ wget -q https://raw.githubusercontent.com/langchain-ai/langgraph/main/README.md -O $(VERIONED_INTERMEDIATE_DIR)/langgraph.md
+ $(PYTHON) scripts/resolve_local_links.py $(VERIONED_INTERMEDIATE_DIR)/langgraph.md https://github.com/langchain-ai/langgraph/tree/main/
+
+ $(PYTHON) scripts/resolve_versioned_links_in_markdown.py $(VERIONED_INTERMEDIATE_DIR) /docs/0.2.x/
+ $(PYTHON) scripts/generate_api_reference_links.py --docs_dir $(VERIONED_INTERMEDIATE_DIR)
+
+
+copy-infra:
+ mkdir -p $(OUTPUT_DIR)
+ cp -r src $(OUTPUT_DIR)
+ cp vercel.json $(OUTPUT_DIR)
+ cp babel.config.js $(OUTPUT_DIR)
+ cp -r data $(OUTPUT_DIR)
+ cp docusaurus.config.js $(OUTPUT_DIR)
+ cp package.json $(OUTPUT_DIR)
+ cp sidebars.js $(OUTPUT_DIR)
+ cp -r static $(OUTPUT_DIR)
+ cp yarn.lock $(OUTPUT_DIR)
+
+quarto-render:
+ $(QUARTO_CMD) render $(INTERMEDIATE_DIR) --output-dir $(OUTPUT_DOCS_DIR) --no-execute
+ mv $(OUTPUT_DOCS_DIR)/$(INTERMEDIATE_DIR)/* $(OUTPUT_DOCS_DIR)
+ rm -rf $(OUTPUT_DOCS_DIR)/build
+
+ $(QUARTO_CMD) render $(VERIONED_INTERMEDIATE_DIR) --output-dir $(VERSIONED_DOCS_DIR) --no-execute
+ mv $(VERSIONED_DOCS_DIR)/$(VERIONED_INTERMEDIATE_DIR)/* $(VERSIONED_DOCS_DIR)
+ rm -rf $(VERSIONED_DOCS_DIR)/build
+
+md-sync:
+ rsync -avm --include="*/" --include="*.mdx" --include="*.md" --exclude="*" $(INTERMEDIATE_DIR)/ $(OUTPUT_DOCS_DIR)
+
+build: install-py-deps generate-files copy-infra quarto-render md-sync
+
+start:
+ cd $(OUTPUT_DIR) && yarn && yarn start --port=$(PORT)