my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	[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.
#2
#3	> New: Pinecone integration now supports custom namespaces! Use the `namespace` parameter to logically separate data within the same index. This is especially useful for multi-tenant or multi-user applications.
#4
#5	> 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-3-small uses 1536 dimensions.
#6
#7	### Usage
#8
#9	```python
#10	import os
#11	from mem0 import Memory
#12
#13	os.environ["OPENAI_API_KEY"] = "sk-xx"
#14	os.environ["PINECONE_API_KEY"] = "your-api-key"
#15
#16	# Example using serverless configuration
#17	config = {
#18	"vector_store": {
#19	"provider": "pinecone",
#20	"config": {
#21	"collection_name": "testing",
#22	"embedding_model_dims": 1536, # Matches OpenAI's text-embedding-3-small
#23	"namespace": "my-namespace", # Optional: specify a namespace for multi-tenancy
#24	"serverless_config": {
#25	"cloud": "aws", # Choose between 'aws' or 'gcp' or 'azure'
#26	"region": "us-east-1"
#27	},
#28	"metric": "cosine"
#29	}
#30	}
#31	}
#32
#33	m = Memory.from_config(config)
#34	messages = [
#35	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#36	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#37	{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
#38	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#39	]
#40	m.add(messages, user_id="alice", metadata={"category": "movies"})
#41	```
#42
#43	### Config
#44
#45	Here are the parameters available for configuring Pinecone:
#46
#47	\| Parameter \| Description \| Default Value \|
#48	\| --- \| --- \| --- \|
#49	\| `collection_name` \| Name of the index/collection \| Required \|
#50	\| `embedding_model_dims` \| Dimensions of the embedding model (must match your chosen embedding model) \| Required \|
#51	\| `client` \| Existing Pinecone client instance \| `None` \|
#52	\| `api_key` \| API key for Pinecone \| Environment variable: `PINECONE_API_KEY` \|
#53	\| `environment` \| Pinecone environment \| `None` \|
#54	\| `serverless_config` \| Configuration for serverless deployment (AWS or GCP or Azure) \| `None` \|
#55	\| `pod_config` \| Configuration for pod-based deployment \| `None` \|
#56	\| `hybrid_search` \| Whether to enable hybrid search \| `False` \|
#57	\| `metric` \| Distance metric for vector similarity \| `"cosine"` \|
#58	\| `batch_size` \| Batch size for operations \| `100` \|
#59	\| `namespace` \| Namespace for the collection, useful for multi-tenancy. \| `None` \|
#60
#61	> Important: You must choose either `serverless_config` or `pod_config` for your deployment, but not both.
#62
#63	#### Serverless Config Example
#64	```python
#65	config = {
#66	"vector_store": {
#67	"provider": "pinecone",
#68	"config": {
#69	"collection_name": "memory_index",
#70	"embedding_model_dims": 1536, # For OpenAI's text-embedding-3-small
#71	"namespace": "my-namespace", # Optional: custom namespace
#72	"serverless_config": {
#73	"cloud": "aws", # or "gcp" or "azure"
#74	"region": "us-east-1" # Choose appropriate region
#75	}
#76	}
#77	}
#78	}
#79	```
#80
#81	#### Pod Config Example
#82	```python
#83	config = {
#84	"vector_store": {
#85	"provider": "pinecone",
#86	"config": {
#87	"collection_name": "memory_index",
#88	"embedding_model_dims": 1536, # For OpenAI's text-embedding-ada-002
#89	"namespace": "my-namespace", # Optional: custom namespace
#90	"pod_config": {
#91	"environment": "gcp-starter",
#92	"replicas": 1,
#93	"pod_type": "starter"
#94	}
#95	}
#96	}
#97	}
#98	```

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public