Handle chromadb dep and version bump (#1638)

This commit is contained in:
Dev Khant
2024-08-04 00:07:15 +05:30
committed by GitHub
parent 04b4807145
commit 5aa7bedabe
7 changed files with 93 additions and 99 deletions

View File

@@ -51,7 +51,7 @@ from mem0 import Memory
config = { config = {
"vectordb": { "vectordb": {
"provider": "chromadb", "provider": "chroma",
"config": { "config": {
"collection_name": "test", "collection_name": "test",
"path": "db", "path": "db",

View File

View File

@@ -0,0 +1,26 @@
from typing import Optional,ClassVar
from pydantic import BaseModel, Field, field_validator, model_validator
class ChromaDbConfig(BaseModel):
try:
from chromadb.api.client import Client
except ImportError:
raise ImportError("Chromadb requires extra dependencies. Install with `pip install chromadb`") from None
Client: ClassVar[type] = Client
collection_name: str = Field("mem0", description="Default name for the collection")
client: Optional[Client] = Field(None, description="Existing ChromaDB client instance")
path: Optional[str] = Field(None, description="Path to the database directory")
host: Optional[str] = Field(None, description="Database connection remote host")
port: Optional[str] = Field(None, description="Database connection remote port")
@model_validator(mode="before")
def check_host_port_or_path(cls, values):
host, port, path = values.get("host"), values.get("port"), values.get("path")
if not path and not (host and port):
raise ValueError("Either 'host' and 'port' or 'path' must be provided.")
return values
class Config:
arbitrary_types_allowed = True

View File

@@ -0,0 +1,34 @@
from typing import Optional,ClassVar
from pydantic import BaseModel, Field, field_validator, model_validator
class QdrantConfig(BaseModel):
from qdrant_client import QdrantClient
QdrantClient: ClassVar[type] = QdrantClient
collection_name: str = Field("mem0", description="Name of the collection")
embedding_model_dims: Optional[int] = Field(1536, description="Dimensions of the embedding model")
client: Optional[QdrantClient] = Field(None, description="Existing Qdrant client instance")
host: Optional[str] = Field(None, description="Host address for Qdrant server")
port: Optional[int] = Field(None, description="Port for Qdrant server")
path: Optional[str] = Field("/tmp/qdrant", description="Path for local Qdrant database")
url: Optional[str] = Field(None, description="Full URL for Qdrant server")
api_key: Optional[str] = Field(None, description="API key for Qdrant server")
@model_validator(mode="before")
def check_host_port_or_path(cls, values):
host, port, path, url, api_key = (
values.get("host"),
values.get("port"),
values.get("path"),
values.get("url"),
values.get("api_key"),
)
if not path and not (host and port) and not (url and api_key):
raise ValueError(
"Either 'host' and 'port' or 'url' and 'api_key' or 'path' must be provided."
)
return values
class Config:
arbitrary_types_allowed = True

View File

@@ -49,7 +49,7 @@ class EmbedderFactory:
class VectorStoreFactory: class VectorStoreFactory:
provider_to_class = { provider_to_class = {
"qdrant": "mem0.vector_stores.qdrant.Qdrant", "qdrant": "mem0.vector_stores.qdrant.Qdrant",
"chromadb": "mem0.vector_stores.chroma.ChromaDB", "chroma": "mem0.vector_stores.chroma.ChromaDB",
} }
@classmethod @classmethod

View File

@@ -1,108 +1,42 @@
from typing import Optional from typing import Optional, Dict, Type
from pydantic import BaseModel, Field, model_validator
from pydantic import BaseModel, Field, field_validator, model_validator
from qdrant_client import QdrantClient
from chromadb.api.client import Client as ChromaDbClient
def create_default_config(provider: str):
"""Create a default configuration based on the provider."""
if provider == "qdrant":
return QdrantConfig(path="/tmp/qdrant")
elif provider == "chromadb":
return ChromaDbConfig(path="/tmp/chromadb")
else:
raise ValueError(f"Unsupported vector store provider: {provider}")
class QdrantConfig(BaseModel):
collection_name: str = Field("mem0", description="Name of the collection")
embedding_model_dims: Optional[int] = Field(1536, description="Dimensions of the embedding model")
client: Optional[QdrantClient] = Field(None, description="Existing Qdrant client instance")
host: Optional[str] = Field(None, description="Host address for Qdrant server")
port: Optional[int] = Field(None, description="Port for Qdrant server")
path: Optional[str] = Field("/tmp/qdrant", description="Path for local Qdrant database")
url: Optional[str] = Field(None, description="Full URL for Qdrant server")
api_key: Optional[str] = Field(None, description="API key for Qdrant server")
@model_validator(mode="before")
def check_host_port_or_path(cls, values):
host, port, path, url, api_key = (
values.get("host"),
values.get("port"),
values.get("path"),
values.get("url"),
values.get("api_key"),
)
if not path and not (host and port) and not (url and api_key):
raise ValueError(
"Either 'host' and 'port' or 'url' and 'api_key' or 'path' must be provided."
)
return values
class Config:
arbitrary_types_allowed = True
class ChromaDbConfig(BaseModel):
collection_name: str = Field("mem0", description="Default name for the collection")
client: Optional[ChromaDbClient] = Field(None, description="Existing ChromaDB client instance")
path: Optional[str] = Field(None, description="Path to the database directory")
host: Optional[str] = Field(None, description="Database connection remote host")
port: Optional[str] = Field(None, description="Database connection remote port")
@model_validator(mode="before")
def check_host_port_or_path(cls, values):
host, port, path = values.get("host"), values.get("port"), values.get("path")
if not path and not (host and port):
raise ValueError("Either 'host' and 'port' or 'path' must be provided.")
return values
class Config:
arbitrary_types_allowed = True
class VectorStoreConfig(BaseModel): class VectorStoreConfig(BaseModel):
provider: str = Field( provider: str = Field(
description="Provider of the vector store (e.g., 'qdrant', 'chromadb', 'elasticsearch')", description="Provider of the vector store (e.g., 'qdrant', 'chromadb')",
default="qdrant", default="qdrant",
) )
config: Optional[dict] = Field( config: Optional[Dict] = Field(
description="Configuration for the specific vector store", description="Configuration for the specific vector store",
default=None default=None
) )
@field_validator("config") _provider_configs: Dict[str, str] = {
def validate_config(cls, v, values): "qdrant": "QdrantConfig",
provider = values.data.get("provider") "chroma": "ChromaDbConfig"
}
if v is None:
return create_default_config(provider)
if isinstance(v, dict):
if provider == "qdrant":
if "path" not in v:
v["path"] = "/tmp/qdrant"
return QdrantConfig(**v)
elif provider == "chromadb":
if "path" not in v:
v["path"] = "/tmp/chromadb"
return ChromaDbConfig(**v)
return v
@model_validator(mode="after") @model_validator(mode="after")
def ensure_config_type(cls, values): def validate_and_create_config(self) -> 'VectorStoreConfig':
provider = values.provider provider = self.provider
config = values.config config = self.config
if provider not in self._provider_configs:
raise ValueError(f"Unsupported vector store provider: {provider}")
module = __import__(f"mem0.configs.vector_stores.{provider}", fromlist=[self._provider_configs[provider]])
config_class = getattr(module, self._provider_configs[provider])
if config is None: if config is None:
values.config = create_default_config(provider) config = {}
elif isinstance(config, dict):
if provider == "qdrant": if not isinstance(config, dict):
values.config = QdrantConfig(**config) if not isinstance(config, config_class):
elif provider == "chromadb": raise ValueError(f"Invalid config type for provider {provider}")
values.config = ChromaDbConfig(**config) return self
elif not isinstance(config, (QdrantConfig, ChromaDbConfig)):
raise ValueError(f"Invalid config type for provider {provider}") if "path" not in config:
config["path"] = f"/tmp/{provider}"
return values
self.config = config_class(**config)
return self

View File

@@ -1,6 +1,6 @@
[tool.poetry] [tool.poetry]
name = "mem0ai" name = "mem0ai"
version = "0.0.12" version = "0.0.13"
description = "Long-term memory for AI Agents" description = "Long-term memory for AI Agents"
authors = ["Mem0 <founders@mem0.ai>"] authors = ["Mem0 <founders@mem0.ai>"]
exclude = [ exclude = [