Issue Station
Sign In
Tools hereToolbox

ollama - 💡(How to fix) Fix Deepseek V1-617b cloud and Deepseek V2 cloud cannot call functional tools for websearch in the graphical interface of ollama [3 comments, 1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
ollama/ollama#15115•Fetched 2026-04-08 01:45:35
View on GitHub
Comments
3
Participants
1
Timeline
8
Reactions
0
Author
createne1createne1
Participants
createne1createne1
Timeline (top)
commented ×3closed ×2labeled ×1renamed ×1

Code Example

Deepseek v3.2-cloud:
--(prompt)
Search difference in mac sequoia and mac tahoe in handling virtual memories
--
Thought for 6.0 seconds
--(answer)
<function_calls> macOS Tahoe virtual memory handling </function_calls>
(unable to continue)

Deepseek V3.1-cloud:
--(prompt)
Search difference in mac sequoia and mac tahoe in handling virtual memories
--
I'll search for information about the differences between macOS Sequoia and macOS Tahoe in handling virtual memory.

Searching for macOS Sequoia vs macOS Tahoe virtual memory management differences…

Search results for macOS Sequoia vs macOS Tahoe virtual memory management differences
--(answer)
Based on the search results, I can see there are significant differences between macOS Sequoia and macOS Tahoe in how they handle virtual memory, particularly on Macs with limited RAM. Let me fetch more detailed information from one of the key articles.
(unable to continue)
RAW_BUFFERClick to expand / collapse

What is the issue?

I found the recent ollama 0.18.3 cannot allow Deepseek V1-617b cloud and Deepseek V2 cloud to call functional tools for websearch. Some sample results:

Deepseek v3.2-cloud: --(prompt) Search difference in mac sequoia and mac tahoe in handling virtual memories

Thought for 6.0 seconds --(answer) <function_calls> macOS Tahoe virtual memory handling </function_calls> (unable to continue)

Deepseek V3.1-cloud --(prompt) Search difference in mac sequoia and mac tahoe in handling virtual memories

I'll search for information about the differences between macOS Sequoia and macOS Tahoe in handling virtual memory.

Searching for macOS Sequoia vs macOS Tahoe virtual memory management differences…

Search results for macOS Sequoia vs macOS Tahoe virtual memory management differences --(answer) Based on the search results, I can see there are significant differences between macOS Sequoia and macOS Tahoe in how they handle virtual memory, particularly on Macs with limited RAM. Let me fetch more detailed information from one of the key articles. (unable to continue)

Relevant log output

Deepseek v3.2-cloud:
--(prompt)
Search difference in mac sequoia and mac tahoe in handling virtual memories
--
Thought for 6.0 seconds
--(answer)
<function_calls> macOS Tahoe virtual memory handling </function_calls>
(unable to continue)

Deepseek V3.1-cloud:
--(prompt)
Search difference in mac sequoia and mac tahoe in handling virtual memories
--
I'll search for information about the differences between macOS Sequoia and macOS Tahoe in handling virtual memory.

Searching for macOS Sequoia vs macOS Tahoe virtual memory management differences…

Search results for macOS Sequoia vs macOS Tahoe virtual memory management differences
--(answer)
Based on the search results, I can see there are significant differences between macOS Sequoia and macOS Tahoe in how they handle virtual memory, particularly on Macs with limited RAM. Let me fetch more detailed information from one of the key articles.
(unable to continue)

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.18.3

extent analysis

Fix Plan

The issue seems to be related to the ollama version 0.18.3 not allowing Deepseek V1-617b cloud and Deepseek V2 cloud to call functional tools for websearch. To fix this, we need to update the ollama configuration to enable the websearch functionality.

Here are the steps to fix the issue:

  • Update the ollama configuration file to enable websearch:
# ollama_config.py
WEBSEARCH_ENABLED = True
  • Add the necessary dependencies for websearch:
pip install beautifulsoup4 requests
  • Update the Deepseek code to use the new ollama configuration:
# deepseek.py
import ollama

ollama_config = ollama.Config()
ollama_config.WEBSEARCH_ENABLED = True

# Use the updated ollama configuration
ollama.init(ollama_config)
  • Restart the Deepseek service to apply the changes.

Verification

To verify that the fix worked, try running the Deepseek tool with the updated ollama configuration:

deepseek --prompt "Search difference in mac sequoia and mac tahoe in handling virtual memories"

The output should include the search results and the ability to fetch more detailed information from the search results.

Extra Tips

Make sure to update the ollama version to the latest available version to ensure that the fix is applied correctly. Additionally, check the Deepseek documentation for any specific configuration requirements for websearch functionality.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#memory management#response parsing#generation error#database connection#vector store

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING