github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 16:40:08 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #5907] Support token embeddings for v1/embeddings #65723

New Issue
Open
opened 2026-05-03 22:24:47 -05:00 by GiteaMirror · 5 comments
GiteaMirror commented 2026-05-03 22:24:47 -05:00
Owner
Copy Link

Originally created by @WoJiaoFuXiaoYun on GitHub (Jul 24, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/5907

Originally assigned to: @npardal on GitHub.

What is the issue?

When encoding with tiktoken, the interface is no longer compatible

tiktoken.get_encoding("cl100k_base").encode(text)

{
    "input": [30624,99849,64479,51392,31809,29207,233,45829],
    "model": "nomic-embed-text"
}

{
    "error": {
        "message": "invalid input type",
        "type": "api_error",
        "param": null,
        "code": null
    }
}

I hope it can be compatible, thank you

OS

No response

GPU

No response

CPU

No response

Ollama version

ollama version is 0.2.7

Originally created by @WoJiaoFuXiaoYun on GitHub (Jul 24, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/5907 Originally assigned to: @npardal on GitHub. ### What is the issue? When encoding with `tiktoken`, the interface is no longer compatible ``` tiktoken.get_encoding("cl100k_base").encode(text) ``` ```json { "input": [30624,99849,64479,51392,31809,29207,233,45829], "model": "nomic-embed-text" } ``` ``` { "error": { "message": "invalid input type", "type": "api_error", "param": null, "code": null } } ``` I hope it can be compatible, thank you ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version ollama version is 0.2.7
GiteaMirror added the feature requestapi labels 2026-05-03 22:24:48 -05:00
GiteaMirror commented 2026-05-03 22:24:52 -05:00
Author
Owner
Copy Link

@royjhan commented on GitHub (Jul 30, 2024):

The supported functionality can be found here: #5470
While we can't provide a timeline for support right now, we appreciate the issue and we are aware

<!-- gh-comment-id:2258877724 --> @royjhan commented on GitHub (Jul 30, 2024): The supported functionality can be found here: #5470 While we can't provide a timeline for support right now, we appreciate the issue and we are aware
GiteaMirror commented 2026-05-03 22:24:54 -05:00
Author
Owner
Copy Link

@xldistance commented on GitHub (Aug 3, 2024):

Version 0.3.3 is still not compatible with OpenAIEmbedding
The code I run is as follows

    text_embedder = OpenAIEmbedding(
        # ollama本地嵌入模型
        api_key="ollama",
        api_base="http://localhost:11434/v1",
        model="bge:m3",
        deployment_name="bge:m3",
        api_type=OpenaiApiType.OpenAI,
        max_retries=20,
    )

The runtime error is as follows

2024-08-03 23:59:34,423 - httpx - INFO - HTTP Request: POST http://localhost:11434/v1/embeddings "HTTP/1.1 400 Bad Request"
Error embedding chunk {'OpenAIEmbedding': "Error code: 400 - {'error': {'message': 'invalid input type', 'type': 'api_error', 'param': None, 'code': None}}"}
<!-- gh-comment-id:2266894465 --> @xldistance commented on GitHub (Aug 3, 2024): Version 0.3.3 is still not compatible with OpenAIEmbedding The code I run is as follows ``` text_embedder = OpenAIEmbedding( # ollama本地嵌入模型 api_key="ollama", api_base="http://localhost:11434/v1", model="bge:m3", deployment_name="bge:m3", api_type=OpenaiApiType.OpenAI, max_retries=20, ) ``` The runtime error is as follows ``` 2024-08-03 23:59:34,423 - httpx - INFO - HTTP Request: POST http://localhost:11434/v1/embeddings "HTTP/1.1 400 Bad Request" Error embedding chunk {'OpenAIEmbedding': "Error code: 400 - {'error': {'message': 'invalid input type', 'type': 'api_error', 'param': None, 'code': None}}"} ```
GiteaMirror commented 2026-05-03 22:24:55 -05:00
Author
Owner
Copy Link

@codefromthecrypt commented on GitHub (Sep 12, 2024):

ps here's the langchain workaround until this is in. While not perfect, certainly proceeds!

    # Until https://github.com/ollama/ollama/issues/5907, we cannot use OpenAIEmbeddings because it
    # produces embeddings requests with list of numbers, not a list of strings.
    # embeddings = OpenAIEmbeddings(base_url=ollama_base_url + '/v1', api_key="unused", model="all-minilm:33m")
    embeddings = OllamaEmbeddings(base_url=ollama_base_url, model="all-minilm:33m")
<!-- gh-comment-id:2345193247 --> @codefromthecrypt commented on GitHub (Sep 12, 2024): ps here's the langchain workaround until this is in. While not perfect, certainly proceeds! ```python # Until https://github.com/ollama/ollama/issues/5907, we cannot use OpenAIEmbeddings because it # produces embeddings requests with list of numbers, not a list of strings. # embeddings = OpenAIEmbeddings(base_url=ollama_base_url + '/v1', api_key="unused", model="all-minilm:33m") embeddings = OllamaEmbeddings(base_url=ollama_base_url, model="all-minilm:33m") ```
GiteaMirror commented 2026-05-03 22:24:56 -05:00
Author
Owner
Copy Link

@nidhishgajjar commented on GitHub (Apr 21, 2026):

Orb Code Review (powered by GLM-4.7 on Orb Cloud)## SummaryThis PR appears to be a minimal change. Please provide more context about what this PR aims to accomplish.## Assessment⚠️ Needs More InformationThe diff is very small. Please add a description, tests, or more substantial changes to facilitate a thorough review.

<!-- gh-comment-id:4286187138 --> @nidhishgajjar commented on GitHub (Apr 21, 2026): **Orb Code Review** (powered by GLM-4.7 on [Orb Cloud](https://orbcloud.dev))## SummaryThis PR appears to be a minimal change. Please provide more context about what this PR aims to accomplish.## Assessment⚠️ **Needs More Information**The diff is very small. Please add a description, tests, or more substantial changes to facilitate a thorough review.
GiteaMirror commented 2026-05-03 22:24:57 -05:00
Author
Owner
Copy Link

@nidhishgajjar commented on GitHub (Apr 21, 2026):

Orb Code Review (powered by GLM-4.7 on Orb Cloud)## SummaryThis PR appears to be a minimal change. Please provide more context about what this PR aims to accomplish.## Assessment⚠️ Needs More InformationThe diff is very small. Please add a description, tests, or more substantial changes to facilitate a thorough review.

<!-- gh-comment-id:4286189121 --> @nidhishgajjar commented on GitHub (Apr 21, 2026): **Orb Code Review** (powered by GLM-4.7 on [Orb Cloud](https://orbcloud.dev))## SummaryThis PR appears to be a minimal change. Please provide more context about what this PR aims to accomplish.## Assessment⚠️ **Needs More Information**The diff is very small. Please add a description, tests, or more substantial changes to facilitate a thorough review.
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 api feature request
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#65723
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?