my-project-public

repository

loading code, commits, and activity

repositories

loading repo index

#1	### Vertex AI
#2
#3	To use Google Cloud's Vertex AI for text embedding models, set the `GOOGLE_APPLICATION_CREDENTIALS` environment variable to point to the path of your service account's credentials JSON file. These credentials can be created in the [Google Cloud Console](https://console.cloud.google.com/).
#4
#5	### Usage
#6
#7	```python
#8	import os
#9	from mem0 import Memory
#10
#11	# Set the path to your Google Cloud credentials JSON file
#12	os.environ["GOOGLE_APPLICATION_CREDENTIALS"] = "/path/to/your/credentials.json"
#13	os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
#14
#15	config = {
#16	"embedder": {
#17	"provider": "vertexai",
#18	"config": {
#19	"model": "text-embedding-004",
#20	"memory_add_embedding_type": "RETRIEVAL_DOCUMENT",
#21	"memory_update_embedding_type": "RETRIEVAL_DOCUMENT",
#22	"memory_search_embedding_type": "RETRIEVAL_QUERY"
#23	}
#24	}
#25	}
#26
#27	m = Memory.from_config(config)
#28	messages = [
#29	{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
#30	{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
#31	{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
#32	{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
#33	]
#34	m.add(messages, user_id="john")
#35	```
#36	The embedding types can be one of the following:
#37	- SEMANTIC_SIMILARITY
#38	- CLASSIFICATION
#39	- CLUSTERING
#40	- RETRIEVAL_DOCUMENT, RETRIEVAL_QUERY, QUESTION_ANSWERING, FACT_VERIFICATION
#41	- CODE_RETRIEVAL_QUERY
#42	Check out the [Vertex AI documentation](https://cloud.google.com/vertex-ai/generative-ai/docs/embeddings/task-types#supported_task_types) for more information.
#43
#44	### Config
#45
#46	Here are the parameters available for configuring the Vertex AI embedder:
#47
#48	\| Parameter \| Description \| Default Value \|
#49	\| ------------------------- \| ------------------------------------------------ \| -------------------- \|
#50	\| `model` \| The name of the Vertex AI embedding model to use \| `text-embedding-004` \|
#51	\| `vertex_credentials_json` \| Path to the Google Cloud credentials JSON file \| `None` \|
#52	\| `embedding_dims` \| Dimensions of the embedding model \| `256` \|
#53	\| `memory_add_embedding_type` \| The type of embedding to use for the add memory action \| `RETRIEVAL_DOCUMENT` \|
#54	\| `memory_update_embedding_type` \| The type of embedding to use for the update memory action \| `RETRIEVAL_DOCUMENT` \|
#55	\| `memory_search_embedding_type` \| The type of embedding to use for the search memory action \| `RETRIEVAL_QUERY` \|
#56

z6Mkq5mY3JWtxoxUobWcfNHm7AkRubgSWEZTkBVqZXJviFZ5/my-project-public