fix pinecone (#2414)
This commit is contained in:
@@ -2,6 +2,8 @@
|
||||
|
||||
[Pinecone](https://www.pinecone.io/) is a fully managed vector database designed for machine learning applications, offering high performance vector search with low latency at scale. It's particularly well-suited for semantic search, recommendation systems, and other AI-powered applications.
|
||||
|
||||
> **Note**: Before configuring Pinecone, you need to select an embedding model (e.g., OpenAI, Cohere, or custom models) and ensure the `embedding_model_dims` in your config matches your chosen model's dimensions. For example, OpenAI's text-embedding-ada-002 uses 1536 dimensions.
|
||||
|
||||
### Usage
|
||||
|
||||
```python
|
||||
@@ -11,13 +13,17 @@ from mem0 import Memory
|
||||
os.environ["OPENAI_API_KEY"] = "sk-xx"
|
||||
os.environ["PINECONE_API_KEY"] = "your-api-key"
|
||||
|
||||
# Example using serverless configuration
|
||||
config = {
|
||||
"vector_store": {
|
||||
"provider": "pinecone",
|
||||
"config": {
|
||||
"collection_name": "memory_index",
|
||||
"embedding_model_dims": 1536,
|
||||
"environment": "us-west1-gcp",
|
||||
"collection_name": "testing",
|
||||
"embedding_model_dims": 1536, # Matches OpenAI's text-embedding-3-small
|
||||
"serverless_config": {
|
||||
"cloud": "aws", # Choose between 'aws' or 'gcp' or 'azure'
|
||||
"region": "us-east-1"
|
||||
},
|
||||
"metric": "cosine"
|
||||
}
|
||||
}
|
||||
@@ -40,28 +46,29 @@ Here are the parameters available for configuring Pinecone:
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
| `collection_name` | Name of the index/collection | Required |
|
||||
| `embedding_model_dims` | Dimensions of the embedding model | Required |
|
||||
| `embedding_model_dims` | Dimensions of the embedding model (must match your chosen embedding model) | Required |
|
||||
| `client` | Existing Pinecone client instance | `None` |
|
||||
| `api_key` | API key for Pinecone | Environment variable: `PINECONE_API_KEY` |
|
||||
| `environment` | Pinecone environment | `None` |
|
||||
| `serverless_config` | Configuration for serverless deployment | `None` |
|
||||
| `serverless_config` | Configuration for serverless deployment (AWS or GCP or Azure) | `None` |
|
||||
| `pod_config` | Configuration for pod-based deployment | `None` |
|
||||
| `hybrid_search` | Whether to enable hybrid search | `False` |
|
||||
| `metric` | Distance metric for vector similarity | `"cosine"` |
|
||||
| `batch_size` | Batch size for operations | `100` |
|
||||
|
||||
#### Serverless Config Example
|
||||
> **Important**: You must choose either `serverless_config` or `pod_config` for your deployment, but not both.
|
||||
|
||||
#### Serverless Config Example
|
||||
```python
|
||||
config = {
|
||||
"vector_store": {
|
||||
"provider": "pinecone",
|
||||
"config": {
|
||||
"collection_name": "memory_index",
|
||||
"embedding_model_dims": 1536,
|
||||
"embedding_model_dims": 1536, # For OpenAI's text-embedding-3-small
|
||||
"serverless_config": {
|
||||
"cloud": "aws",
|
||||
"region": "us-west-2"
|
||||
"cloud": "aws", # or "gcp" or "azure"
|
||||
"region": "us-east-1" # Choose appropriate region
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -69,14 +76,13 @@ config = {
|
||||
```
|
||||
|
||||
#### Pod Config Example
|
||||
|
||||
```python
|
||||
config = {
|
||||
"vector_store": {
|
||||
"provider": "pinecone",
|
||||
"config": {
|
||||
"collection_name": "memory_index",
|
||||
"embedding_model_dims": 1536,
|
||||
"embedding_model_dims": 1536, # For OpenAI's text-embedding-ada-002
|
||||
"pod_config": {
|
||||
"environment": "gcp-starter",
|
||||
"replicas": 1,
|
||||
|
||||
@@ -199,12 +199,13 @@ class PineconeDB(VectorStoreBase):
|
||||
|
||||
return pinecone_filter
|
||||
|
||||
def search(self, query: List[float], limit: int = 5, filters: Optional[Dict] = None) -> List[OutputData]:
|
||||
def search(self, query: str, vectors: List[float], limit: int = 5, filters: Optional[Dict] = None) -> List[OutputData]:
|
||||
"""
|
||||
Search for similar vectors.
|
||||
|
||||
Args:
|
||||
query (list): Query vector.
|
||||
query (str): Query.
|
||||
vectors (list): List of vectors to search.
|
||||
limit (int, optional): Number of results to return. Defaults to 5.
|
||||
filters (dict, optional): Filters to apply to the search. Defaults to None.
|
||||
|
||||
@@ -214,7 +215,7 @@ class PineconeDB(VectorStoreBase):
|
||||
filter_dict = self._create_filter(filters) if filters else None
|
||||
|
||||
query_params = {
|
||||
"vector": query,
|
||||
"vector": vectors,
|
||||
"top_k": limit,
|
||||
"include_metadata": True,
|
||||
"include_values": False,
|
||||
|
||||
Reference in New Issue
Block a user