Merge pull request langchain-ai#9 from benjaminliugang/MAX-33800-1

MAX-33800 Upgrade langchain to 0.2.7

.github/ISSUE_TEMPLATE/config.yml

@@ -4,9 +4,6 @@ contact_links:
   - name: 🤔 Question or Problem
     about: Ask a question or ask about a problem in GitHub Discussions.
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/q-a
-  - name: Discord
-    url: https://discord.gg/6adMQxSpJS
-    about: General community discussions
   - name: Feature Request
     url: https://www.github.com/langchain-ai/langchain/discussions/categories/ideas
     about: Suggest a feature or an idea

.github/actions/people/app/main.py

@@ -350,11 +350,7 @@ def get_graphql_pr_edges(*, settings: Settings, after: Union[str, None] = None):
         print("Querying PRs...")
     else:
         print(f"Querying PRs with cursor {after}...")
-    data = get_graphql_response(
-        settings=settings,
-        query=prs_query,
-        after=after
-    )
+    data = get_graphql_response(settings=settings, query=prs_query, after=after)
     graphql_response = PRsResponse.model_validate(data)
     return graphql_response.data.repository.pullRequests.edges
 
@@ -484,10 +480,16 @@ def get_contributors(settings: Settings):
             lines_changed = pr.additions + pr.deletions
             score = _logistic(files_changed, 20) + _logistic(lines_changed, 100)
             contributor_scores[pr.author.login] += score
-            three_months_ago = (datetime.now(timezone.utc) - timedelta(days=3*30))
+            three_months_ago = datetime.now(timezone.utc) - timedelta(days=3 * 30)
             if pr.createdAt > three_months_ago:
                 recent_contributor_scores[pr.author.login] += score
-    return contributors, contributor_scores, recent_contributor_scores, reviewers, authors
+    return (
+        contributors,
+        contributor_scores,
+        recent_contributor_scores,
+        reviewers,
+        authors,
+    )
 
 
 def get_top_users(
@@ -524,9 +526,13 @@ def get_top_users(
     # question_commentors, question_last_month_commentors, question_authors = get_experts(
     #     settings=settings
     # )
-    contributors, contributor_scores, recent_contributor_scores, reviewers, pr_authors = get_contributors(
-        settings=settings
-    )
+    (
+        contributors,
+        contributor_scores,
+        recent_contributor_scores,
+        reviewers,
+        pr_authors,
+    ) = get_contributors(settings=settings)
     # authors = {**question_authors, **pr_authors}
     authors = {**pr_authors}
     maintainers_logins = {
@@ -547,6 +553,7 @@ def get_top_users(
         "obi1kenobi",
         "langchain-infra",
         "jacoblee93",
+        "isahers1",
         "dqbd",
         "bracesproul",
         "akira",
@@ -558,7 +565,7 @@ def get_top_users(
         maintainers.append(
             {
                 "login": login,
-                "count": contributors[login], #+ question_commentors[login],
+                "count": contributors[login],  # + question_commentors[login],
                 "avatarUrl": user.avatarUrl,
                 "twitterUsername": user.twitterUsername,
                 "url": user.url,
@@ -614,9 +621,7 @@ def get_top_users(
     new_people_content = yaml.dump(
         people, sort_keys=False, width=200, allow_unicode=True
     )
-    if (
-        people_old_content == new_people_content
-    ):
+    if people_old_content == new_people_content:
         logging.info("The LangChain People data hasn't changed, finishing.")
         sys.exit(0)
     people_path.write_text(new_people_content, encoding="utf-8")
@@ -629,9 +634,7 @@ def get_top_users(
     logging.info(f"Creating a new branch {branch_name}")
     subprocess.run(["git", "checkout", "-B", branch_name], check=True)
     logging.info("Adding updated file")
-    subprocess.run(
-        ["git", "add", str(people_path)], check=True
-    )
+    subprocess.run(["git", "add", str(people_path)], check=True)
     logging.info("Committing updated file")
     message = "👥 Update LangChain people data"
     result = subprocess.run(["git", "commit", "-m", message], check=True)
@@ -640,4 +643,4 @@ def get_top_users(
     logging.info("Creating PR")
     pr = repo.create_pull(title=message, body=message, base="master", head=branch_name)
     logging.info(f"Created PR: {pr.number}")
-    logging.info("Finished")
+    logging.info("Finished")

.github/scripts/check_diff.py

@@ -1,7 +1,12 @@
+import glob
 import json
-import sys
 import os
-from typing import Dict
+import re
+import sys
+import tomllib
+from collections import defaultdict
+from typing import Dict, List, Set
+
 
 LANGCHAIN_DIRS = [
     "libs/core",
@@ -11,6 +16,43 @@
     "libs/experimental",
 ]
 
+
+def all_package_dirs() -> Set[str]:
+    return {
+        "/".join(path.split("/")[:-1]).lstrip("./")
+        for path in glob.glob("./libs/**/pyproject.toml", recursive=True)
+        if "libs/cli" not in path and "libs/standard-tests" not in path
+    }
+
+
+def dependents_graph() -> dict:
+    dependents = defaultdict(set)
+
+    for path in glob.glob("./libs/**/pyproject.toml", recursive=True):
+        if "template" in path:
+            continue
+        with open(path, "rb") as f:
+            pyproject = tomllib.load(f)["tool"]["poetry"]
+        pkg_dir = "libs" + "/".join(path.split("libs")[1].split("/")[:-1])
+        for dep in pyproject["dependencies"]:
+            if "langchain" in dep:
+                dependents[dep].add(pkg_dir)
+    return dependents
+
+
+def add_dependents(dirs_to_eval: Set[str], dependents: dict) -> List[str]:
+    updated = set()
+    for dir_ in dirs_to_eval:
+        # handle core manually because it has so many dependents
+        if "core" in dir_:
+            updated.add(dir_)
+            continue
+        pkg = "langchain-" + dir_.split("/")[-1]
+        updated.update(dependents[pkg])
+        updated.add(dir_)
+    return list(updated)
+
+
 if __name__ == "__main__":
     files = sys.argv[1:]
 
@@ -21,10 +63,11 @@
     }
     docs_edited = False
 
-    if len(files) == 300:
+    if len(files) >= 300:
         # max diff length is 300 files - there are likely files missing
-        raise ValueError("Max diff reached. Please manually run CI on changed libs.")
-
+        dirs_to_run["lint"] = all_package_dirs()
+        dirs_to_run["test"] = all_package_dirs()
+        dirs_to_run["extended-test"] = set(LANGCHAIN_DIRS)
     for file in files:
         if any(
             file.startswith(dir_)
@@ -81,11 +124,16 @@
                 docs_edited = True
             dirs_to_run["lint"].add(".")
 
+    dependents = dependents_graph()
+
     outputs = {
-        "dirs-to-lint": list(
-            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"]
+        "dirs-to-lint": add_dependents(
+            dirs_to_run["lint"] | dirs_to_run["test"] | dirs_to_run["extended-test"],
+            dependents,
+        ),
+        "dirs-to-test": add_dependents(
+            dirs_to_run["test"] | dirs_to_run["extended-test"], dependents
         ),
-        "dirs-to-test": list(dirs_to_run["test"] | dirs_to_run["extended-test"]),
         "dirs-to-extended-test": list(dirs_to_run["extended-test"]),
         "docs-edited": "true" if docs_edited else "",
     }

.github/scripts/get_min_versions.py

@@ -74,6 +74,4 @@ def get_min_version_from_toml(toml_path: str):
     # Call the function to get the minimum versions
     min_versions = get_min_version_from_toml(toml_file)
 
-    print(
-        " ".join([f"{lib}=={version}" for lib, version in min_versions.items()])
-    )
+    print(" ".join([f"{lib}=={version}" for lib, version in min_versions.items()]))

.github/workflows/_compile_integration_test.yml

@@ -24,6 +24,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: "poetry run pytest -m compile tests/integration_tests #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_dependencies.yml

@@ -28,6 +28,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: dependency checks ${{ matrix.python-version }}
     steps:
       - uses: actions/checkout@v4

.github/workflows/_integration_test.yml

@@ -12,7 +12,6 @@ env:
 
 jobs:
   build:
-    environment: Scheduled testing
     defaults:
       run:
         working-directory: ${{ inputs.working-directory }}
@@ -53,8 +52,15 @@ jobs:
         shell: bash
         env:
           AI21_API_KEY: ${{ secrets.AI21_API_KEY }}
+          FIREWORKS_API_KEY: ${{ secrets.FIREWORKS_API_KEY }}
           GOOGLE_API_KEY: ${{ secrets.GOOGLE_API_KEY }}
           ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+          AZURE_OPENAI_API_VERSION: ${{ secrets.AZURE_OPENAI_API_VERSION }}
+          AZURE_OPENAI_API_BASE: ${{ secrets.AZURE_OPENAI_API_BASE }}
+          AZURE_OPENAI_API_KEY: ${{ secrets.AZURE_OPENAI_API_KEY }}
+          AZURE_OPENAI_CHAT_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_CHAT_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_LLM_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_LLM_DEPLOYMENT_NAME }}
+          AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME: ${{ secrets.AZURE_OPENAI_EMBEDDINGS_DEPLOYMENT_NAME }}
           MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
           TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
           OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}

.github/workflows/_lint.yml

@@ -34,7 +34,7 @@ jobs:
         # so linting on fewer versions makes CI faster.
         python-version:
           - "3.8"
-          - "3.11"
+          - "3.12"
     steps:
       - uses: actions/checkout@v4
 

.github/workflows/_release.yml

@@ -135,6 +135,7 @@ jobs:
       - release-notes
     uses:
       ./.github/workflows/_test_release.yml
+    permissions: write-all
     with:
       working-directory: ${{ inputs.working-directory }}
       dangerous-nonmaster-release: ${{ inputs.dangerous-nonmaster-release }}
@@ -202,7 +203,7 @@ jobs:
           poetry run python -c "import $IMPORT_NAME; print(dir($IMPORT_NAME))"
 
       - name: Import test dependencies
-        run: poetry install --with test,test_integration
+        run: poetry install --with test
         working-directory: ${{ inputs.working-directory }}
 
       # Overwrite the local version of the package with the test PyPI version.
@@ -245,6 +246,10 @@ jobs:
         with:
           credentials_json: '${{ secrets.GOOGLE_CREDENTIALS }}'
 
+      - name: Import integration test dependencies
+        run: poetry install --with test,test_integration
+        working-directory: ${{ inputs.working-directory }}
+
       - name: Run integration tests
         if: ${{ startsWith(inputs.working-directory, 'libs/partners/') }}
         env:

.github/workflows/_test.yml

@@ -28,6 +28,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     name: "make test #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/_test_doc_imports.yml

@@ -12,7 +12,7 @@ jobs:
     strategy:
       matrix:
         python-version:
-          - "3.11"
+          - "3.12"
     name: "check doc imports #${{ matrix.python-version }}"
     steps:
       - uses: actions/checkout@v4

.github/workflows/check-broken-links.yml

@@ -7,6 +7,7 @@ on:
 
 jobs:
   check-links:
+    if: github.repository_owner == 'langchain-ai'
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4

.github/workflows/check_diffs.yml

@@ -26,7 +26,7 @@ jobs:
       - uses: actions/checkout@v4
       - uses: actions/setup-python@v5
         with:
-          python-version: '3.10'
+          python-version: '3.11'
       - id: files
         uses: Ana06/get-changed-files@v2.2.0
       - id: set-matrix
@@ -104,6 +104,7 @@ jobs:
           - "3.9"
           - "3.10"
           - "3.11"
+          - "3.12"
     runs-on: ubuntu-latest
     defaults:
       run:

.github/workflows/check_new_docs.yml

@@ -0,0 +1,36 @@
+---
+name: Integration docs lint
+
+on:
+  push:
+    branches: [master]
+  pull_request:
+
+# If another push to the same PR or branch happens while this workflow is still running,
+# cancel the earlier run in favor of the next run.
+#
+# There's no point in testing an outdated version of the code. GitHub only allows
+# a limited number of job runners to be active at the same time, so it's better to cancel
+# pointless jobs early so that more useful jobs can run sooner.
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+      - id: files
+        uses: Ana06/get-changed-files@v2.2.0
+        with:
+          filter: |
+            *.ipynb
+            *.md
+            *.mdx
+      - name: Check new docs
+        run: |
+          python docs/scripts/check_templates.py ${{ steps.files.outputs.added }}

.github/workflows/people.yml

@@ -16,6 +16,7 @@ jobs:
   langchain-people:
     if: github.repository_owner == 'langchain-ai'
     runs-on: ubuntu-latest
+    permissions: write-all
     steps:
       - name: Dump GitHub context
         env: