github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 00:51:34 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #6540] actively retrieves the content returned from the web page #50625

New Issue
Closed
opened 2026-04-28 16:35:49 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-28 16:35:49 -05:00
Owner
Copy Link

Originally created by @Nurburgring-Zhang on GitHub (Aug 28, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/6540

expected that ollama can automatically identify the model, and then when the problem exceeds the capacity of the model, ollama actively retrieves the content returned from the web page to the model, and the model analyzes the content returned and finally gives the answer.

Originally created by @Nurburgring-Zhang on GitHub (Aug 28, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/6540 expected that ollama can automatically identify the model, and then when the problem exceeds the capacity of the model, ollama actively retrieves the content returned from the web page to the model, and the model analyzes the content returned and finally gives the answer.
GiteaMirror added the feature request label 2026-04-28 16:35:49 -05:00
GiteaMirror commented 2026-04-28 16:35:53 -05:00
Author
Owner
Copy Link

@igorschlum commented on GitHub (Aug 28, 2024):

Hi @Nurburgring-Zhang Thank you for your suggestion! What you're proposing is a very interesting vision for the future of Ollama. The idea of a hybrid solution that combines local models with automatic web retrieval to provide more comprehensive answers is indeed promising and could significantly enhance the capabilities of LLMs.

However, implementing such a feature would require many steps and substantial technical development, including considerations for model capacity, security, data privacy, and performance. At this time, GitHub is primarily used for addressing short-term issues and features that are achievable in the near future.

This idea might be better suited for discussion on the Discord server, where the community often talks about future possibilities and explores more experimental concepts. Feel free to join the conversation there!

Since we aim to keep GitHub focused on actionable items to avoid having too many open tickets that can detract from the project's progress, it would be great if you could close this ticket.

Thanks again for your feedback and for sharing your thoughts!

<!-- gh-comment-id:2315809318 --> @igorschlum commented on GitHub (Aug 28, 2024): Hi @Nurburgring-Zhang Thank you for your suggestion! What you're proposing is a very interesting vision for the future of Ollama. The idea of a hybrid solution that combines local models with automatic web retrieval to provide more comprehensive answers is indeed promising and could significantly enhance the capabilities of LLMs. However, implementing such a feature would require many steps and substantial technical development, including considerations for model capacity, security, data privacy, and performance. At this time, GitHub is primarily used for addressing short-term issues and features that are achievable in the near future. This idea might be better suited for discussion on the Discord server, where the community often talks about future possibilities and explores more experimental concepts. Feel free to join the conversation there! Since we aim to keep GitHub focused on actionable items to avoid having too many open tickets that can detract from the project's progress, it would be great if you could close this ticket. Thanks again for your feedback and for sharing your thoughts!
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 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#50625
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?