Update Docs (#3520)
This commit is contained in:
Deshraj Yadav
@@ -41,7 +41,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -23,7 +23,7 @@ config = {
|
||||
"embedder": {
|
||||
"provider": "azure_openai",
|
||||
"config": {
|
||||
"model": "text-embedding-3-large"
|
||||
"model": "text-embedding-3-large",
|
||||
"azure_kwargs": {
|
||||
"api_version": "",
|
||||
"azure_deployment": "",
|
||||
@@ -40,7 +40,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -68,7 +68,7 @@ const memory = new Memory(config);
|
||||
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -26,7 +26,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -50,7 +50,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -24,7 +24,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -36,7 +36,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -66,7 +66,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -20,7 +20,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -29,10 +29,10 @@ m.add(messages, user_id="john")
|
||||
|
||||
### Config
|
||||
|
||||
Here are the parameters available for configuring Ollama embedder:
|
||||
Here are the parameters available for configuring LM Studio embedder:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
| `model` | The name of the OpenAI model to use | `nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.f16.gguf` |
|
||||
| `model` | The name of the LM Studio model to use | `nomic-embed-text-v1.5-GGUF/nomic-embed-text-v1.5.f16.gguf` |
|
||||
| `embedding_dims` | Dimensions of the embedding model | `1536` |
|
||||
| `lmstudio_base_url` | Base URL for LM Studio connection | `http://localhost:1234/v1` |
|
||||
@@ -21,7 +21,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -44,7 +44,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -25,7 +25,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -27,7 +27,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -27,7 +27,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -29,6 +29,6 @@ See the list of supported embedders below.
|
||||
|
||||
## Usage
|
||||
|
||||
To utilize a embedder, you must provide a configuration to customize its usage. If no configuration is supplied, a default configuration will be applied, and `OpenAI` will be used as the embedder.
|
||||
To utilize an embedding model, you must provide a configuration to customize its usage. If no configuration is supplied, a default configuration will be applied, and `OpenAI` will be used as the embedding model.
|
||||
|
||||
For a comprehensive list of available parameters for embedder configuration, please refer to [Config](./config).
|
||||
For a comprehensive list of available parameters for embedding model configuration, please refer to [Config](./config).
|
||||
|
||||
@@ -29,7 +29,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -54,7 +54,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -31,7 +31,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -48,7 +48,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -77,7 +77,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -28,7 +28,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -30,7 +30,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -55,7 +55,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -38,7 +38,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -69,7 +69,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -22,7 +22,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -29,7 +29,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -57,7 +57,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -28,7 +28,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -53,7 +53,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -1,4 +1,8 @@
|
||||
You can use LLMs from Ollama to run Mem0 locally. These [models](https://ollama.com/search?c=tools) support tool support.
|
||||
---
|
||||
title: Ollama
|
||||
---
|
||||
|
||||
You can use LLMs from Ollama to run Mem0 locally. These [models](https://ollama.com/search?c=tools) support tool calling.
|
||||
|
||||
## Usage
|
||||
|
||||
@@ -23,7 +27,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -47,7 +51,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -40,7 +40,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -65,7 +65,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -28,7 +28,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -1,4 +1,8 @@
|
||||
To use TogetherAI LLM models, you have to set the `TOGETHER_API_KEY` environment variable. You can obtain the TogetherAI API key from their [Account settings page](https://api.together.xyz/settings/api-keys).
|
||||
---
|
||||
title: Together
|
||||
---
|
||||
|
||||
To use Together LLM models, you have to set the `TOGETHER_API_KEY` environment variable. You can obtain the Together API key from their [Account settings page](https://api.together.xyz/settings/api-keys).
|
||||
|
||||
## Usage
|
||||
|
||||
@@ -23,7 +27,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -32,4 +36,4 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
|
||||
## Config
|
||||
|
||||
All available parameters for the `togetherai` config are present in [Master List of All Params in Config](../config).
|
||||
All available parameters for the `together` config are present in [Master List of All Params in Config](../config).
|
||||
@@ -29,7 +29,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -27,7 +27,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -107,13 +107,13 @@ To enable Role-Based Access Control (RBAC) for Azure AI Search, follow these ste
|
||||
- Click **Add** > **Add role assignment**.
|
||||
6. **Choose Role:**
|
||||
- Mem0 requires the **Search Index Data Contributor** and **Search Service Contributor** role.
|
||||
7. **Choose Member**
|
||||
- To assign to a User, Group, Service Principle or Managed Identity:
|
||||
7. **Choose Member**
|
||||
- To assign to a User, Group, Service Principal or Managed Identity:
|
||||
- For production it is recommended to use a service principal or managed identity.
|
||||
- For a service principal: select **User, group, or service principal** and search for the service principal.
|
||||
- For a managed identity: select **Managed identity** and choose the managed identity.
|
||||
- For development, you can assign the role to a user account.
|
||||
- For development: select ***User, group, or service principal** and pick a Azure Entra ID account (the same used with `az login`).
|
||||
- For development: select **User, group, or service principal** and pick an Azure Entra ID account (the same used with `az login`).
|
||||
8. **Complete the Assignment:**
|
||||
- Click **Review + Assign**.
|
||||
|
||||
@@ -133,7 +133,7 @@ config = {
|
||||
}
|
||||
```
|
||||
|
||||
### Environment Variables to set to use Azure Identity Credential:
|
||||
### Environment Variables to Use Azure Identity Credential
|
||||
* For an Environment Credential, you will need to setup a Service Principal and set the following environment variables:
|
||||
- `AZURE_TENANT_ID`: Your Azure Active Directory tenant ID.
|
||||
- `AZURE_CLIENT_ID`: The client ID of your service principal or managed identity.
|
||||
@@ -142,7 +142,7 @@ config = {
|
||||
- `AZURE_CLIENT_ID`: The client ID of the user-assigned managed identity.
|
||||
* For a System-Assigned Managed Identity, no additional environment variables are needed.
|
||||
|
||||
### Developer logins to use for a Azure Identity Credential:
|
||||
### Developer Logins for Azure Identity Credential
|
||||
* For an Azure CLI Credential, you need to have the Azure CLI installed and logged in with `az login`.
|
||||
* For an Azure PowerShell Credential, you need to have the Azure PowerShell module installed and logged in with `Connect-AzAccount`.
|
||||
* For an Azure Developer CLI Credential, you need to have the Azure Developer CLI installed and logged in with `azd auth login`.
|
||||
|
||||
@@ -37,7 +37,7 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
|
||||
### Config
|
||||
|
||||
Here are the available parameters for the `mochow` config:
|
||||
Here are the parameters available for configuring Baidu VectorDB:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
|
||||
@@ -26,7 +26,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -31,7 +31,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -40,7 +40,7 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
|
||||
### Config
|
||||
|
||||
Let's see the available parameters for the `elasticsearch` config:
|
||||
Here are the parameters available for configuring Elasticsearch:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| ---------------------- | -------------------------------------------------- | ------------- |
|
||||
|
||||
@@ -22,7 +22,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -38,7 +38,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -64,12 +64,12 @@ const memory = new Memory(config);
|
||||
|
||||
const messages = [
|
||||
{ role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
|
||||
{ role: "assistant", content: "How about a thriller movies? They can be quite engaging." },
|
||||
{ role: "assistant", content: "How about thriller movies? They can be quite engaging." },
|
||||
{ role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
|
||||
{ role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." }
|
||||
]
|
||||
|
||||
memory.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
|
||||
```
|
||||
</CodeGroup>
|
||||
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
[Milvus](https://milvus.io/) Milvus is an open-source vector database that suits AI applications of every size from running a demo chatbot in Jupyter notebook to building web-scale search that serves billions of users.
|
||||
[Milvus](https://milvus.io/) is an open-source vector database that suits AI applications of every size, from running a demo chatbot in a Jupyter notebook to building web-scale search that serves billions of users.
|
||||
|
||||
### Usage
|
||||
|
||||
@@ -22,7 +22,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -31,7 +31,7 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
|
||||
### Config
|
||||
|
||||
Here's the parameters available for configuring Milvus Database:
|
||||
Here are the parameters available for configuring Milvus:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
|
||||
@@ -24,7 +24,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -40,6 +40,6 @@ Here are the parameters available for configuring MongoDB:
|
||||
| db_name | Name of the MongoDB database | `"mem0_db"` |
|
||||
| collection_name | Name of the MongoDB collection | `"mem0_collection"` |
|
||||
| embedding_model_dims | Dimensions of the embedding vectors | `1536` |
|
||||
| mongo_uri | The mongo URI connection string | mongodb://username:password@localhost:27017 |
|
||||
| mongo_uri | The MongoDB URI connection string | `mongodb://username:password@localhost:27017` |
|
||||
|
||||
> **Note**: If Mongo_uri is not provided it will default to mongodb://username:password@localhost:27017.
|
||||
> **Note**: If `mongo_uri` is not provided, it will default to `mongodb://username:password@localhost:27017`.
|
||||
|
||||
@@ -58,7 +58,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -74,8 +74,8 @@ results = m.search("What kind of movies does Alice like?", user_id="alice")
|
||||
### Features
|
||||
|
||||
- Fast and Efficient Vector Search
|
||||
- Can be deployed on-premises, in containers, or on cloud platforms like AWS OpenSearch Service.
|
||||
- Multiple Authentication and Security Methods (Basic Authentication, API Keys, LDAP, SAML, and OpenID Connect)
|
||||
- Can be deployed on-premises, in containers, or on cloud platforms like AWS OpenSearch Service
|
||||
- Multiple authentication and security methods (Basic Authentication, API Keys, LDAP, SAML, and OpenID Connect)
|
||||
- Automatic index creation with optimized mappings for vector search
|
||||
- Memory Optimization through Disk-Based Vector Search and Quantization
|
||||
- Real-Time Analytics and Observability
|
||||
- Memory optimization through disk-based vector search and quantization
|
||||
- Real-time analytics and observability
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
[pgvector](https://github.com/pgvector/pgvector) is open-source vector similarity search for Postgres. After connecting with postgres run `CREATE EXTENSION IF NOT EXISTS vector;` to create the vector extension.
|
||||
[pgvector](https://github.com/pgvector/pgvector) is an open-source vector similarity search extension for Postgres. After connecting to Postgres, run `CREATE EXTENSION IF NOT EXISTS vector;` to create the vector extension.
|
||||
|
||||
### Usage
|
||||
|
||||
@@ -24,7 +24,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -54,7 +54,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -64,7 +64,7 @@ await memory.add(messages, { userId: "alice", metadata: { category: "movies" } }
|
||||
|
||||
### Config
|
||||
|
||||
Here's the parameters available for configuring pgvector:
|
||||
Here are the parameters available for configuring pgvector:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
|
||||
@@ -33,7 +33,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -23,7 +23,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -48,7 +48,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -34,7 +34,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -60,7 +60,7 @@ const config = {
|
||||
const memory = new Memory(config);
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
|
||||
@@ -48,7 +48,7 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
|
||||
### Config
|
||||
|
||||
Here are the available parameters for the `s3_vectors` config:
|
||||
Here are the parameters available for configuring Amazon S3 Vectors:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| ---------------------- | -------------------------------------------------------------------------------- | ------------------------------------- |
|
||||
|
||||
@@ -26,7 +26,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -53,7 +53,7 @@ const memory = new Memory(config);
|
||||
|
||||
const messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -109,7 +109,7 @@ end;
|
||||
$$;
|
||||
```
|
||||
|
||||
Goto [Supabase](https://supabase.com/dashboard/projects) and run the above SQL migrations inside the SQL Editor.
|
||||
Go to [Supabase](https://supabase.com/dashboard/projects) and run the above SQL migrations in the SQL Editor.
|
||||
|
||||
### Config
|
||||
|
||||
|
||||
@@ -26,7 +26,7 @@ config = {
|
||||
m = Memory.from_config(config)
|
||||
messages = [
|
||||
{"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
|
||||
{"role": "assistant", "content": "How about a thriller movies? They can be quite engaging."},
|
||||
{"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
|
||||
{"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
|
||||
{"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
|
||||
]
|
||||
@@ -35,7 +35,7 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
|
||||
## Parameters
|
||||
|
||||
Let's see the available parameters for the `valkey` config:
|
||||
Here are the parameters available for configuring Valkey:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
|
||||
@@ -31,7 +31,7 @@ await memory.add(messages, { userId: "bob", metadata: { interest: "books" } });
|
||||
|
||||
### Config
|
||||
|
||||
Let's see the available parameters for the `vectorize` config:
|
||||
Here are the parameters available for configuring Vectorize:
|
||||
|
||||
<Tabs>
|
||||
<Tab title="TypeScript">
|
||||
|
||||
@@ -37,7 +37,7 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
|
||||
|
||||
### Config
|
||||
|
||||
Let's see the available parameters for the `weaviate` config:
|
||||
Here are the parameters available for configuring Weaviate:
|
||||
|
||||
| Parameter | Description | Default Value |
|
||||
| --- | --- | --- |
|
||||
|
||||
@@ -17,7 +17,7 @@ See the list of supported vector databases below.
|
||||
<CardGroup cols={3}>
|
||||
<Card title="Qdrant" href="/components/vectordbs/dbs/qdrant"></Card>
|
||||
<Card title="Chroma" href="/components/vectordbs/dbs/chroma"></Card>
|
||||
<Card title="Pgvector" href="/components/vectordbs/dbs/pgvector"></Card>
|
||||
<Card title="PGVector" href="/components/vectordbs/dbs/pgvector"></Card>
|
||||
<Card title="Upstash Vector" href="/components/vectordbs/dbs/upstash-vector"></Card>
|
||||
<Card title="Milvus" href="/components/vectordbs/dbs/milvus"></Card>
|
||||
<Card title="Pinecone" href="/components/vectordbs/dbs/pinecone"></Card>
|
||||
@@ -44,12 +44,11 @@ For a comprehensive list of available parameters for vector database configurati
|
||||
|
||||
## Common issues
|
||||
|
||||
### Using model with different dimensions
|
||||
### Using Model with Different Dimensions
|
||||
|
||||
If you are using customized model, which is having different dimensions other than 1536
|
||||
for example 768, you may encounter below error:
|
||||
If you are using a customized model with different dimensions other than 1536 (for example, 768), you may encounter the following error:
|
||||
|
||||
`ValueError: shapes (0,1536) and (768,) not aligned: 1536 (dim 1) != 768 (dim 0)`
|
||||
|
||||
you could add `"embedding_model_dims": 768,` to the config of the vector_store to overcome this issue.
|
||||
You can add `"embedding_model_dims": 768,` to the config of the vector_store to resolve this issue.
|
||||
|
||||
|
||||
Reference in New Issue
Block a user