INTPYTHON-816 - Bump minimum Python version to 3.10 (#241)

[INTPYTHON-816](https://jira.mongodb.org/browse/INTPYTHON-816)

## Summary

LangChain 1.0 requires Python 3.10+. Updating our own minimum version
now before the package split will reduce the complexity of doing so.

## Changes in this PR

Bump minimum Python version across the board to 3.10. Update ruff to the
latest release for fixes such as the removal of
[UP038](https://docs.astral.sh/ruff/rules/non-pep604-isinstance/).

Author: NoahStapp

.github/workflows/_lint.yml

@@ -29,7 +29,7 @@ jobs:
         # Starting new jobs is also relatively slow,
         # so linting on fewer versions makes CI faster.
         python-version:
-          - "3.9"
+          - "3.10"
           - "3.13"
     steps:
       - uses: actions/checkout@v5

.github/workflows/_test.yml

@@ -18,7 +18,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version:
-          - "3.9"
+          - "3.10"
           - "3.13"
     name: "run test #${{ matrix.python-version }}"
     steps:

.github/workflows/ci.yml

@@ -86,7 +86,7 @@ jobs:
         uses: astral-sh/setup-uv@2ddd2b9cb38ad8efd50337e8ab201519a34c9f24 # v7
         with:
           enable-cache: true
-          python-version: 3.9
+          python-version: "3.10"
       - run: just docs
 
   ci_success:

.pre-commit-config.yaml

@@ -40,7 +40,7 @@ repos:
 
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: v0.8.5
+  rev: v0.14.2
   hooks:
     # Run the linter.
     - id: ruff

CONTRIBUTING.md

@@ -135,3 +135,8 @@ just codespell
 ```
 
 If codespell is incorrectly flagging a word, you can skip spellcheck for that word by adding it to the codespell config in the `.pre-commit-config.yaml` file.
+
+### CI Configuration
+The CI configuration for this project is located in the `.github/workflows` directory.
+The `.github/scripts/check_diff.py` script is run automatically at the start of CI to determine which parts of the codebase have changed and need to be tested. I
+f you add new packages or change the directory structure, update this script accordingly.

docs/_extensions/gallery_directive.py

@@ -108,7 +108,7 @@ def run(self) -> List[nodes.Node]:
 
         # Parse the template with Sphinx Design to create an output container
         # Prep the options for the template grid
-        class_ = "gallery-directive" + f' {self.options.get("class-container", "")}'
+        class_ = "gallery-directive" + f" {self.options.get('class-container', '')}"
         options = {"gutter": 2, "class-container": class_}
         options_str = "\n".join(f":{k}: {v}" for k, v in options.items())
 

docs/create_api_rst.py

@@ -269,7 +269,7 @@ def _construct_doc(
 .. _{package_namespace}:
 
 ======================================
-{package_namespace.replace('_', '-').replace('.', '-')}: {package_version}
+{package_namespace.replace("_", "-").replace(".", "-")}: {package_version}
 ======================================
 
 .. automodule:: {package_namespace}
@@ -327,7 +327,7 @@ def _construct_doc(
 
         index_autosummary += f"""
 :ref:`{package_namespace}_{module}`
-{'^' * (len(package_namespace) + len(module) + 8)}
+{"^" * (len(package_namespace) + len(module) + 8)}
 """
 
         if classes:
@@ -366,7 +366,7 @@ def _construct_doc(
 
 """
                 index_autosummary += f"""
-    {class_['qualified_name']}
+    {class_["qualified_name"]}
 """
 
         if functions:
@@ -429,7 +429,7 @@ def _construct_doc(
 
 """
                 index_autosummary += f"""
-    {class_['qualified_name']}
+    {class_["qualified_name"]}
 """
 
         if deprecated_functions:

libs/langchain-mongodb/langchain_mongodb/docstores.py

@@ -99,12 +99,13 @@ def mset(
             batch_size: Number of documents to insert at a time.
                 Tuning this may help with performance and sidestep MongoDB limits.
         """
-        keys, docs = zip(*key_value_pairs)
+        keys, docs = zip(*key_value_pairs, strict=True)
         n_docs = len(docs)
         start = 0
         for end in range(batch_size, n_docs + batch_size, batch_size):
             texts, metadatas = zip(
-                *[(doc.page_content, doc.metadata) for doc in docs[start:end]]
+                *[(doc.page_content, doc.metadata) for doc in docs[start:end]],
+                strict=True,
             )
             self.insert_many(texts=texts, metadatas=metadatas, ids=keys[start:end])  # type: ignore
             start = end
@@ -149,6 +150,7 @@ def insert_many(
         in the batch that do not have conflicting _ids will still be inserted.
         """
         to_insert = [
-            {"_id": i, self._text_key: t, **m} for i, t, m in zip(ids, texts, metadatas)
+            {"_id": i, self._text_key: t, **m}
+            for i, t, m in zip(ids, texts, metadatas, strict=True)
         ]
         self.collection.insert_many(to_insert)  # type: ignore

libs/langchain-mongodb/langchain_mongodb/indexes.py

@@ -85,7 +85,7 @@ def update(
         if len(keys) != len(group_ids):
             raise ValueError("Number of keys does not match number of group_ids")
 
-        for key, group_id in zip(keys, group_ids):
+        for key, group_id in zip(keys, group_ids, strict=True):
             self._collection.find_one_and_update(
                 {"namespace": self.namespace, "key": key},
                 {"$set": {"group_id": group_id, "updated_at": self.get_time()}},

libs/langchain-mongodb/langchain_mongodb/vectorstores.py

@@ -356,7 +356,7 @@ def add_texts(
             metadatas_batch = []
             size = 0
             i = 0
-            for j, (text, metadata) in enumerate(zip(texts, _metadatas)):
+            for j, (text, metadata) in enumerate(zip(texts, _metadatas, strict=True)):
                 size += len(text) + len(metadata)
                 texts_batch.append(text)
                 metadatas_batch.append(metadata)
@@ -442,7 +442,9 @@ def bulk_embed_and_insert_texts(
                 self._embedding_key: embedding,
                 **m,
             }
-            for i, t, m, embedding in zip(ids, texts, metadatas, embeddings)
+            for i, t, m, embedding in zip(
+                ids, texts, metadatas, embeddings, strict=True
+            )
         ]
         operations = [ReplaceOne({"_id": doc["_id"]}, doc, upsert=True) for doc in docs]
         # insert the documents in MongoDB Atlas
@@ -478,7 +480,8 @@ def add_documents(
         start = 0
         for end in range(batch_size, n_docs + batch_size, batch_size):
             texts, metadatas = zip(
-                *[(doc.page_content, doc.metadata) for doc in documents[start:end]]
+                *[(doc.page_content, doc.metadata) for doc in documents[start:end]],
+                strict=True,
             )
             result_ids.extend(
                 self.bulk_embed_and_insert_texts(