[ENH] Add support for collection.fork, update tool prompts with regex (#46)

Author: jairad26

.github/workflows/test.yml

@@ -19,14 +19,16 @@ jobs:
       uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
+    - name: Install uv
+      run: |
+        curl -LsSf https://astral.sh/uv/install.sh | sh
+        echo "$HOME/.cargo/bin" >> $GITHUB_PATH
     - name: Install dependencies
       run: |
-        python -m pip install --upgrade pip
-        pip install -e ".[test]"
-        pip install pytest pytest-asyncio pytest-cov
+        uv sync --extra test
     - name: Run tests
       run: |
-        pytest tests/ --cov=chroma_mcp --cov-report=xml
+        uv run pytest tests/ --cov=chroma_mcp --cov-report=xml
     - name: Upload coverage
       uses: codecov/codecov-action@v3
       with:

CHANGELOG.md

@@ -5,6 +5,12 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.6] - 08/14/2025
+
+- Update chromadb to 1.0.16
+- Add tool prompts for regex support
+- Add new `chroma_fork_collection` tool support
+
 ## [0.2.5] - 06/18/2025
 
 - Update chromadb to 1.0.13

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "chroma-mcp"
-version = "0.2.5"
+version = "0.2.6"
 description = "Chroma MCP Server - Vector Database Integration for LLM Applications"
 readme = "README.md"
 requires-python = ">=3.10"
@@ -16,14 +16,12 @@ classifiers = [
     "Topic :: Software Development :: Libraries :: Python Modules"
 ]
 dependencies = [
-    "chromadb>=1.0.13",
+    "chromadb>=1.0.16",
     "cohere>=5.14.2",
     "httpx>=0.28.1",
-    "mcp[cli]>=1.2.1",
+    "mcp[cli]==1.6.0",
     "openai>=1.70.0",
     "pillow>=11.1.0",
-    "pytest>=8.3.5",
-    "pytest-asyncio>=0.26.0",
     "python-dotenv>=0.19.0",
     "typing-extensions>=4.13.1",
     "voyageai>=0.3.2",
@@ -43,10 +41,16 @@ chroma-mcp = "chroma_mcp:main"
 
 [project.optional-dependencies]
 sentence-transformers = ["sentence-transformers>=4.1.0"]
+test = [
+    "pytest>=8.3.5",
+    "pytest-asyncio>=0.26.0",
+    "pytest-cov>=4.1.0",
+]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]
 python_files = ["test_*.py"]
+asyncio_default_fixture_loop_scope = "function"
 
 [tool.ruff]
 select = ["E", "F", "B", "I"]

src/chroma_mcp/server.py

@@ -293,7 +293,27 @@ async def chroma_modify_collection(
         return f"Successfully modified collection {collection_name}: updated {' and '.join(modified_aspects)}"
     except Exception as e:
         raise Exception(f"Failed to modify collection '{collection_name}': {str(e)}") from e
-
+    
+@mcp.tool()
+async def chroma_fork_collection(
+    collection_name: str,
+    new_collection_name: str,
+) -> str:
+    """Fork a Chroma collection.
+    
+    Args:
+        collection_name: Name of the collection to fork
+        new_collection_name: Name of the new collection to create
+        metadata: Optional metadata dict to add to the new collection
+    """
+    client = get_chroma_client()
+    try:
+        collection = client.get_collection(collection_name)
+        collection.fork(new_collection_name)
+        return f"Successfully forked collection {collection_name} to {new_collection_name}"
+    except Exception as e:
+        raise Exception(f"Failed to fork collection '{collection_name}': {str(e)}") from e
+    
 @mcp.tool()
 async def chroma_delete_collection(collection_name: str) -> str:
     """Delete a Chroma collection.
@@ -394,6 +414,13 @@ async def chroma_query_documents(
                - Logical AND: {"$and": [{"field1": {"$eq": "value1"}}, {"field2": {"$gt": 5}}]}
                - Logical OR: {"$or": [{"field1": {"$eq": "value1"}}, {"field1": {"$eq": "value2"}}]}
         where_document: Optional document content filters
+               Examples:
+               - Contains: {"$contains": "value"}
+               - Not contains: {"$not_contains": "value"}
+               - Regex: {"$regex": "[a-z]+"}
+               - Not regex: {"$not_regex": "[a-z]+"}
+               - Logical AND: {"$and": [{"$contains": "value1"}, {"$not_regex": "[a-z]+"}]}
+               - Logical OR: {"$or": [{"$regex": "[a-z]+"}, {"$not_contains": "value2"}]}
         include: List of what to include in response. By default, this will include documents, metadatas, and distances.
     """
     if not query_texts:
@@ -434,6 +461,13 @@ async def chroma_get_documents(
                - Logical AND: {"$and": [{"field1": {"$eq": "value1"}}, {"field2": {"$gt": 5}}]}
                - Logical OR: {"$or": [{"field1": {"$eq": "value1"}}, {"field1": {"$eq": "value2"}}]}
         where_document: Optional document content filters
+               Examples:
+               - Contains: {"$contains": "value"}
+               - Not contains: {"$not_contains": "value"}
+               - Regex: {"$regex": "[a-z]+"}
+               - Not regex: {"$not_regex": "[a-z]+"}
+               - Logical AND: {"$and": [{"$contains": "value1"}, {"$not_regex": "[a-z]+"}]}
+               - Logical OR: {"$or": [{"$regex": "[a-z]+"}, {"$not_contains": "value2"}]}
         include: List of what to include in response. By default, this will include documents, and metadatas.
         limit: Optional maximum number of documents to return
         offset: Optional number of documents to skip before returning results