github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-07-16 13:19:40 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #7653] Validation of Keys and Subkeys in Ollama API JSON Objects #4884

New Issue
Open
opened 2026-04-12 15:54:53 -05:00 by GiteaMirror · 0 comments
GiteaMirror commented 2026-04-12 15:54:53 -05:00
Owner
Copy Link

Originally created by @d-kleine on GitHub (Nov 13, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/7653

Originally assigned to: @ParthSareen on GitHub.

Problem:
When interacting with the Ollama API, developers may inadvertently pass incorrect keys or subkeys in their requests (e.g., due to typos or misunderstanding of the expected structure). Currently, the API does not provide feedback when this occurs, which can lead to silent failures where options are ignored without notifying the user. This behavior makes debugging difficult and increases the likelihood of unintended behavior.

Proposed Solution:
Implement a validation mechanism that checks for the existence of valid keys and subkeys in the JSON request object. If an invalid key or subkey is detected, return an informative error message detailing which key or subkey is incorrect. This will help developers quickly identify issues in their request payloads.

Expected Behavior:

  1. Validation on Request Submission: When a request is made to any endpoint (e.g., /generate, /chat), the API should validate all provided keys and subkeys against a predefined schema.
  2. Error Response for Invalid Keys: If an invalid key or subkey is detected, return an error response with a message such as: 
    KeyError("Invalid key 'num_predct' in 'options'. Did you mean 'num_predict'?")
  3. Graceful Handling of Missing Required Keys: If a required key (e.g., "model", "prompt") is missing, return an error indicating which required key is missing: 
    KeyError("Missing required key 'model'.")

Benefits:

  1. Improved Usability: Developers will receive immediate feedback when they make mistakes in their request payloads, reducing debugging time.
  2. Reduced Silent Failures: By explicitly notifying users of invalid keys or subkeys, you can eliminate silent failures where options are ignored without warning.
  3. Increased Confidence in Requests: Developers can be confident that all provided options are being processed as intended.
Originally created by @d-kleine on GitHub (Nov 13, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/7653 Originally assigned to: @ParthSareen on GitHub. **Problem:** When interacting with the Ollama API, developers may inadvertently pass incorrect keys or subkeys in their requests (e.g., due to typos or misunderstanding of the expected structure). Currently, the API does not provide feedback when this occurs, which can lead to silent failures where options are ignored without notifying the user. This behavior makes debugging difficult and increases the likelihood of unintended behavior. **Proposed Solution:** Implement a validation mechanism that checks for the existence of valid keys and subkeys in the JSON request object. If an invalid key or subkey is detected, return an informative error message detailing which key or subkey is incorrect. This will help developers quickly identify issues in their request payloads. ### Expected Behavior: 1. **Validation on Request Submission:** When a request is made to any endpoint (e.g., `/generate`, `/chat`), the API should validate all provided keys and subkeys against a predefined schema. 2. **Error Response for Invalid Keys:** If an invalid key or subkey is detected, return an error response with a message such as: ```python KeyError("Invalid key 'num_predct' in 'options'. Did you mean 'num_predict'?") ``` 4. **Graceful Handling of Missing Required Keys:** If a required key (e.g., `"model"`, `"prompt"`) is missing, return an error indicating which required key is missing: ```python KeyError("Missing required key 'model'.") ``` ### Benefits: 1. **Improved Usability:** Developers will receive immediate feedback when they make mistakes in their request payloads, reducing debugging time. 2. **Reduced Silent Failures:** By explicitly notifying users of invalid keys or subkeys, you can eliminate silent failures where options are ignored without warning. 3. **Increased Confidence in Requests:** Developers can be confident that all provided options are being processed as intended.
GiteaMirror added the feature requestapi labels 2026-04-12 15:54:53 -05:00
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#4884
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?