[feat add]FastEmbed embedding for local embeddings by lucifertrj · Pull Request #3552 · mem0ai/mem0

lucifertrj · 2025-10-08T20:24:02Z

Add: FastEmbed Embedding for the local embedding inference use cases

Type of change

Please delete options that are not relevant.

Bug fix (non-breaking change which fixes an issue)
New feature (non-breaking change which adds functionality)
Breaking change (fix or feature that would cause existing functionality to not work as expected)
Refactor (does not change functionality, e.g. code style improvements, linting)
Documentation update

How Has This Been Tested?

As of now, I have tested FastEmbed Embeddings with mem0 Memory Config directly.

from mem0 import Memory
import os
os.environ['GOOGLE_API_KEY'] = "<api-key>"

config = {
    "llm": {
        "provider": "gemini",
        "config": {
            "model": "gemini-2.5-flash-lite",
            "temperature": 0.8,
        }
    },
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "collection_name": "travel",
            "path": "/tmp/db",
            "embedding_model_dims": 768,
        }
    },
    "embedder": {
        "provider": "fastembed",
        "config": {
            "model": "jinaai/jina-embeddings-v2-base-en"
        }
    }
}
client = Memory.from_config(config)
messages = [
    {"role": "user", "content": "What is the must try food in Baroda"},
    {"role": "assistant", "content": "Sev Usal is must"},
    {"role": "user", "content": "I'm not into street food, I prefer Gujarati thalis."},
    {"role": "assistant", "content": "Head to Mandap in Baroda, it’s famous for authentic Gujarati thalis."},
]
result1 = client.add(messages, user_id="personal", metadata={"category": "food"})
print(result1)

I will push the testing scripts under the tests folder too.

Please delete options that are not relevant.

Unit Test
Test Script (please provide)

Checklist:

My code follows the style guidelines of this project
I have performed a self-review of my own code
I have commented my code, particularly in hard-to-understand areas
I have made corresponding changes to the documentation
My changes generate no new warnings
I have added tests that prove my fix is effective or that my feature works
New and existing unit tests pass locally with my changes
Any dependent changes have been merged and published in downstream modules
I have checked my code and corrected any misspellings

Maintainer Checklist

closes #xxxx (Replace xxxx with the GitHub issue number)
Made sure Checks passed

CLAassistant · 2025-10-08T20:24:08Z

All committers have signed the CLA.

parshvadaftari · 2025-10-10T22:44:49Z

Hey @lucifertrj Thank you for implementing this but can you please see for the failing tests?

parshvadaftari · 2025-10-11T15:14:29Z

mem0/embeddings/fastembed.py

+        self.config.model = self.config.model or "thenlper/gte-large"
+        self.config.embedding_dims = self.config.embedding_dims or 1024
+
+        self.dense_model = TextEmbedding(model_name = self.config.model,max_lenth = self.config.embedding_dims)


Can you remove max_lenth from here? Fastembed doesn't support this param.

can you check now

parshvadaftari · 2025-10-16T15:20:22Z

Hey @lucifertrj the tests are failing. Can you please check?

parshvadaftari · 2025-10-16T16:00:50Z

Can you resolve merge conflicts?

lucifertrj · 2025-10-16T16:07:01Z

Can you resolve merge conflicts?

I have resolved it. I am getting this Vercel Authorization required to deploy although I have already approved.

parshvadaftari · 2025-10-16T16:09:20Z

Vercel deployment is for the maintainers of the project, so that is fine and not an issue on your end.

lucifertrj · 2025-10-16T16:38:32Z

Vercel deployment is for the maintainers of the project, so that is fine and not an issue on your end.

Alright got it.

lucifertrj · 2025-10-16T16:41:34Z

this is test.py I used to test (PFA: Screenshot):

from mem0 import Memory
import os
os.environ['GOOGLE_API_KEY'] = ""

config = {
    "llm": {
        "provider": "gemini",
        "config": {
            "model": "gemini-2.5-flash-lite",
            "temperature": 0.8,
        }
    },
    "vector_store": {
        "provider": "qdrant",
        "config": {
            "collection_name": "devfestbaroda",
            "path": "/tmp/db",
            "embedding_model_dims": 768,
        }
    },
    "embedder": {
        "provider": "fastembed",
        "config": {
            "model": "jinaai/jina-embeddings-v2-base-en"
        }
    }
}
client = Memory.from_config(config)
messages = [
    {"role": "user", "content": "What is the must try food in Baroda"},
    {"role": "assistant", "content": "Sev Usal is must"},
    {"role": "user", "content": "I'm not into street food, I prefer Gujarati thalis."},
    {"role": "assistant", "content": "Head to Mandap in Baroda, it’s famous for authentic Gujarati thalis."},
]
result1 = client.add(messages, user_id="personal", metadata={"category": "food"})
print(result1)

parshvadaftari · 2025-10-16T16:48:01Z

@lucifertrj there's no support for the embedding_dims with the fastembed, how will the dimensions be decided and also what if I want to specify a specific dimension, that is something which should be either documented or implemented. Rest of the implementation looks good to me.

lucifertrj · 2025-10-16T16:49:37Z

@lucifertrj there's no support for the embedding_dims with the fastembed, how will the dimensions be decided and also what if I want to specify a specific dimension, that is something which should be documented. Rest of the implementation looks good to me.

In that case, they will have to use a specific vector store, mainly Qdrant. FastEmbed goes well in hand with Qdrant vector store. I can help out with documentation.

parshvadaftari · 2025-10-16T17:05:25Z

Okay cool it looks good to me!

parshvadaftari

Looks good to me!

parshvadaftari · 2025-10-16T17:22:51Z

Thanks a lot for your contribution @lucifertrj 🚀

lucifertrj · 2025-10-16T17:36:00Z

Thanks a lot for your contribution @lucifertrj 🚀

let's go. Let me add the documentation too...

parshvadaftari · 2025-10-16T17:37:19Z

Let me know once you raise the PR!🔥

add FastEmbed embedding for local embeddings

08f2aa3

lucifertrj added 2 commits October 9, 2025 01:54

add fastembed under EmbeddingFactory

2cf02bc

pytest for fastembed using different model

0132217

parshvadaftari suggested changes Oct 11, 2025

View reviewed changes

remove max_length

2d3ccbd

lucifertrj added 2 commits October 16, 2025 21:02

remove unused import statements

17d75b6

add fastembed in the dependency

87f728f

lucifertrj added 2 commits October 16, 2025 21:31

Merge branch 'main' into fastembed-embedding

941cca0

remove unwanted package

7fb0536

parshvadaftari approved these changes Oct 16, 2025

View reviewed changes

parshvadaftari merged commit 1090784 into mem0ai:main Oct 16, 2025
6 of 7 checks passed

garciaba79 pushed a commit to garciaba79/mem0 that referenced this pull request Feb 12, 2026

[feat add]FastEmbed embedding for local embeddings (mem0ai#3552)

4c86658

kartik-mem0 mentioned this pull request Mar 26, 2026

feat: FastEmbed Embeddings #2083

Closed

jamebobob pushed a commit to jamebobob/mem0-vigil-recall that referenced this pull request Mar 29, 2026

[feat add]FastEmbed embedding for local embeddings (mem0ai#3552)

7565336

Conversation

lucifertrj commented Oct 8, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Type of change

How Has This Been Tested?

Checklist:

Maintainer Checklist

Uh oh!

CLAassistant commented Oct 8, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

parshvadaftari commented Oct 10, 2025

Uh oh!

parshvadaftari Oct 11, 2025

Choose a reason for hiding this comment

Uh oh!

lucifertrj Oct 16, 2025

Choose a reason for hiding this comment

Uh oh!

parshvadaftari commented Oct 16, 2025

Uh oh!

parshvadaftari commented Oct 16, 2025

Uh oh!

lucifertrj commented Oct 16, 2025

Uh oh!

parshvadaftari commented Oct 16, 2025

Uh oh!

lucifertrj commented Oct 16, 2025

Uh oh!

lucifertrj commented Oct 16, 2025

Uh oh!

parshvadaftari commented Oct 16, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

lucifertrj commented Oct 16, 2025

Uh oh!

parshvadaftari commented Oct 16, 2025

Uh oh!

parshvadaftari left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

parshvadaftari commented Oct 16, 2025

Uh oh!

lucifertrj commented Oct 16, 2025

Uh oh!

parshvadaftari commented Oct 16, 2025

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

lucifertrj commented Oct 8, 2025 •

edited

Loading

CLAassistant commented Oct 8, 2025 •

edited

Loading

parshvadaftari commented Oct 16, 2025 •

edited

Loading