github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7242] api/embed endpoint is not working exactly like api/embeddings endpoint #30361

New Issue
Closed
opened 2026-04-22 09:56:09 -05:00 by GiteaMirror · 2 comments
GiteaMirror commented 2026-04-22 09:56:09 -05:00
Owner
Copy Link

Originally created by @hdnh2006 on GitHub (Oct 17, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7242

What is the issue?

Hi guys!

Thanks for this fantastic tool. This is the first time I use embeddings with ollama, I have just tried inference with LLM, and I realized that there is a big difference between the endpoints /embed and /embeddings.

I understand the /embeddings was deprecated but it is a common endpoint used by openai compatible applications and I am facing these results:


import requests

url = 'http://192.168.100.60:11434/api/embeddings'

data = {
    "model": "bge-large",
    "input": ["Why is the sky blue?", "Why is the grass green?"]

}

response = requests.post(url, json=data)

print(response.json())
{'embedding': []}

I should get the same results as the endpoint /embed:


import requests

url = 'http://192.168.100.60:11434/api/embed'
data = {
    "model": "bge-large",
    "input": ["Why is the sky blue?", "Why is the grass green?"]

}

response = requests.post(url, json=data)

print(response.json())
{'model': 'bge-large', 'embeddings': [[0.0013820849, -0.0021153516, 0.026703326, -0.019793263, -0.028357966, -0.0038778095, -0.0074022487, 0.026467843, 0.0390734, 0.064318694, -0.029173901, -0.016984569, 0.02871944, ...], [-0.009015707, -0.007080707, 0.012702042, 0.026064986, 0.0032204844, 0.03592011, 0.025629202, -3.0089186e-05, 0.030164663, 0.06953627, 0.02197145, -0.019186007, 0.031450707, 0.004626421, -0.01037141, 0.0134581905, ...]], 'total_duration': 351441147, 'load_duration': 1014270, 'prompt_eval_count': 12}

Am I doing something wrong? I need to call the endpoint embeddings as it is required to simulate my openai compatible application.

OS

Linux

GPU

Nvidia

CPU

AMD

Ollama version

ollama version is 0.3.12

Originally created by @hdnh2006 on GitHub (Oct 17, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7242 ### What is the issue? Hi guys! Thanks for this fantastic tool. This is the first time I use embeddings with ollama, I have just tried inference with LLM, and I realized that there is a big difference between the endpoints `/embed` and `/embeddings`. I understand the `/embeddings` was deprecated but it is a common endpoint used by `openai` compatible applications and I am facing these results: ```python import requests url = 'http://192.168.100.60:11434/api/embeddings' data = { "model": "bge-large", "input": ["Why is the sky blue?", "Why is the grass green?"] } response = requests.post(url, json=data) print(response.json()) {'embedding': []} ``` I should get the same results as the endpoint `/embed`: ```python import requests url = 'http://192.168.100.60:11434/api/embed' data = { "model": "bge-large", "input": ["Why is the sky blue?", "Why is the grass green?"] } response = requests.post(url, json=data) print(response.json()) {'model': 'bge-large', 'embeddings': [[0.0013820849, -0.0021153516, 0.026703326, -0.019793263, -0.028357966, -0.0038778095, -0.0074022487, 0.026467843, 0.0390734, 0.064318694, -0.029173901, -0.016984569, 0.02871944, ...], [-0.009015707, -0.007080707, 0.012702042, 0.026064986, 0.0032204844, 0.03592011, 0.025629202, -3.0089186e-05, 0.030164663, 0.06953627, 0.02197145, -0.019186007, 0.031450707, 0.004626421, -0.01037141, 0.0134581905, ...]], 'total_duration': 351441147, 'load_duration': 1014270, 'prompt_eval_count': 12} ``` Am I doing something wrong? I need to call the endpoint `embeddings` as it is required to simulate my openai compatible application. ### OS Linux ### GPU Nvidia ### CPU AMD ### Ollama version ollama version is 0.3.12
GiteaMirror added the bug label 2026-04-22 09:56:09 -05:00
GiteaMirror commented 2026-04-22 09:56:11 -05:00
Author
Owner
Copy Link

@rick-github commented on GitHub (Oct 18, 2024):

The /api/embeddings endpoint uses prompt, not input. But it's deprecated and returns different values. If you want OpenAI compatabiity, use the OpenAI compatibility endpoint, /v1/embeddings.

<!-- gh-comment-id:2421029705 --> @rick-github commented on GitHub (Oct 18, 2024): The `/api/embeddings` endpoint uses `prompt`, not `input`. But it's deprecated and returns different values. If you want OpenAI compatabiity, use the [OpenAI compatibility endpoint](https://github.com/ollama/ollama/blob/main/docs/openai.md#v1embeddings), `/v1/embeddings`.
GiteaMirror commented 2026-04-22 09:56:12 -05:00
Author
Owner
Copy Link

@hdnh2006 commented on GitHub (Oct 18, 2024):

Thank you!!! @rick-github

<!-- gh-comment-id:2421912624 --> @hdnh2006 commented on GitHub (Oct 18, 2024): Thank you!!! @rick-github
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#30361
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?