github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12425] Ollama completion issue #8252

New Issue
Closed
opened 2026-04-12 20:46:08 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 20:46:08 -05:00
Owner
Copy Link

Originally created by @SlareJ on GitHub (Sep 26, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12425

What is the issue?

Hi, I'm trying to configure the completion tool to work with ollama, but get this issue:

[parse] err: ...y/llm.nvim/lua/llm/common/completion/backends/ollama.lua:13: attempt to index field 'choices' (a nil value) chunk: {
  error = {
    code = vim.NIL,
    message = "registry.ollama.ai/library/qwen3:latest does not support insert",
    param = vim.NIL,
    type = "api_error"
  }
}

From the ollama logs:

[GIN] 2025/09/26 - 15:46:04 | 400 |   38.950625ms |             ::1 | POST     "/v1/completions"

Thought this might have something to do with fim, but it seems like it doesn't. I'm configuring the plugin using lazy, here's the config file:

return {
    "Kurama622/llm.nvim",
    dependencies = { "nvim-lua/plenary.nvim", "MunifTanjim/nui.nvim", "Exafunction/windsurf.nvim", },
    cmd = { "LLMSessionToggle", "LLMSelectedTextHandler", "LLMAppHandler" },
    enabled = true,
    config = function()
        local tools = require("llm.tools")
        require("llm").setup({
            url = "127.0.0.1:11434/api/chat",
            model = "qwen3",
            api_type = "ollama",
            keys = {
                -- The keyboard mapping for the input window.
                ["Input:Submit"]      = { mode = "n", key = "<cr>" },
                ["Input:Cancel"]      = { mode = { "n", "i" }, key = "<C-c>" },
                ["Input:Resend"]      = { mode = { "n", "i" }, key = "<C-r>" },

                -- only works when "save_session = true"
                ["Input:HistoryNext"] = { mode = { "n", "i" }, key = "<C-j>" },
                ["Input:HistoryPrev"] = { mode = { "n", "i" }, key = "<C-k>" },

                -- The keyboard mapping for the output window in "split" style.
                ["Output:Ask"]        = { mode = "n", key = "i" },
                ["Output:Cancel"]     = { mode = "n", key = "<C-c>" },
                ["Output:Resend"]     = { mode = "n", key = "<C-r>" },

                -- The keyboard mapping for the output and input windows in "float" style.
                ["Session:Toggle"]    = { mode = "n", key = "<leader>ac" },
                ["Session:Close"]     = { mode = "n", key = { "<esc>", "Q" } },

                -- Scroll [default]
                ["PageUp"]            = { mode = { "i", "n" }, key = "<C-b>" },
                ["PageDown"]          = { mode = { "i", "n" }, key = "<C-f>" },
                ["HalfPageUp"]        = { mode = { "i", "n" }, key = "<C-u>" },
                ["HalfPageDown"]      = { mode = { "i", "n" }, key = "<C-d>" },
                ["JumpToTop"]         = { mode = "n", key = "gg" },
                ["JumpToBottom"]      = { mode = "n", key = "G" }
            },

            app_handler = {
                Completion = {
                    handler = tools.completion_handler,
                    opts = {
                        url = "http://localhost:11434/v1/completions",
                        model = "qwen3",
                        api_type = "ollama",
                        style = "virtual_text",
                        n_completions = 1,
                        context_window = 512,
                        max_tokens = 256,

                        filetypes = { sh = false },
                        default_filetype_enabled = true,
                        auto_trigger = true,
                        -- style = "blink.cmp",
                        -- style = "nvim-cmp",
                        -- style = "virtual_text",
                        keymap = {
                            toggle = {
                                mode = "n",
                                keys = "<leader>cp",
                            },
                            virtual_text = {
                                accept = {
                                    mode = "i",
                                    keys = "<A-a>",
                                },
                                next = {
                                    mode = "i",
                                    keys = "<A-n>",
                                },
                                prev = {
                                    mode = "i",
                                    keys = "<A-p>",
                                },
                            },
                        },
                    },
                },
            }

        })
    end,
    keys = {
        { "<leader>ac", mode = "n", "<cmd>LLMSessionToggle<cr>" },
    },
}

Would appreciate any help.

Also, is it planned to develop open-ai compatible completion tool? Because I believe it is not supported at the moment.

Relevant log output

OS

macOS

GPU

No response

CPU

Apple

Ollama version

0.12.2

Originally created by @SlareJ on GitHub (Sep 26, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12425 ### What is the issue? Hi, I'm trying to configure the completion tool to work with ollama, but get this issue: ``` [parse] err: ...y/llm.nvim/lua/llm/common/completion/backends/ollama.lua:13: attempt to index field 'choices' (a nil value) chunk: { error = { code = vim.NIL, message = "registry.ollama.ai/library/qwen3:latest does not support insert", param = vim.NIL, type = "api_error" } } ``` From the ollama logs: ``` [GIN] 2025/09/26 - 15:46:04 | 400 | 38.950625ms | ::1 | POST "/v1/completions" ``` Thought this might have something to do with fim, but it seems like it doesn't. I'm configuring the plugin using lazy, here's the config file: ```lua return { "Kurama622/llm.nvim", dependencies = { "nvim-lua/plenary.nvim", "MunifTanjim/nui.nvim", "Exafunction/windsurf.nvim", }, cmd = { "LLMSessionToggle", "LLMSelectedTextHandler", "LLMAppHandler" }, enabled = true, config = function() local tools = require("llm.tools") require("llm").setup({ url = "127.0.0.1:11434/api/chat", model = "qwen3", api_type = "ollama", keys = { -- The keyboard mapping for the input window. ["Input:Submit"] = { mode = "n", key = "<cr>" }, ["Input:Cancel"] = { mode = { "n", "i" }, key = "<C-c>" }, ["Input:Resend"] = { mode = { "n", "i" }, key = "<C-r>" }, -- only works when "save_session = true" ["Input:HistoryNext"] = { mode = { "n", "i" }, key = "<C-j>" }, ["Input:HistoryPrev"] = { mode = { "n", "i" }, key = "<C-k>" }, -- The keyboard mapping for the output window in "split" style. ["Output:Ask"] = { mode = "n", key = "i" }, ["Output:Cancel"] = { mode = "n", key = "<C-c>" }, ["Output:Resend"] = { mode = "n", key = "<C-r>" }, -- The keyboard mapping for the output and input windows in "float" style. ["Session:Toggle"] = { mode = "n", key = "<leader>ac" }, ["Session:Close"] = { mode = "n", key = { "<esc>", "Q" } }, -- Scroll [default] ["PageUp"] = { mode = { "i", "n" }, key = "<C-b>" }, ["PageDown"] = { mode = { "i", "n" }, key = "<C-f>" }, ["HalfPageUp"] = { mode = { "i", "n" }, key = "<C-u>" }, ["HalfPageDown"] = { mode = { "i", "n" }, key = "<C-d>" }, ["JumpToTop"] = { mode = "n", key = "gg" }, ["JumpToBottom"] = { mode = "n", key = "G" } }, app_handler = { Completion = { handler = tools.completion_handler, opts = { url = "http://localhost:11434/v1/completions", model = "qwen3", api_type = "ollama", style = "virtual_text", n_completions = 1, context_window = 512, max_tokens = 256, filetypes = { sh = false }, default_filetype_enabled = true, auto_trigger = true, -- style = "blink.cmp", -- style = "nvim-cmp", -- style = "virtual_text", keymap = { toggle = { mode = "n", keys = "<leader>cp", }, virtual_text = { accept = { mode = "i", keys = "<A-a>", }, next = { mode = "i", keys = "<A-n>", }, prev = { mode = "i", keys = "<A-p>", }, }, }, }, }, } }) end, keys = { { "<leader>ac", mode = "n", "<cmd>LLMSessionToggle<cr>" }, }, } ``` Would appreciate any help. Also, is it planned to develop open-ai compatible completion tool? Because I believe it is not supported at the moment. ### Relevant log output ```shell ``` ### OS macOS ### GPU _No response_ ### CPU Apple ### Ollama version 0.12.2
GiteaMirror added the bug label 2026-04-12 20:46:08 -05:00
GiteaMirror commented 2026-04-12 20:46:11 -05:00
Author
Owner
Copy Link

@SlareJ commented on GitHub (Sep 26, 2025):

Posted on the wrong section, sorry

<!-- gh-comment-id:3338593671 --> @SlareJ commented on GitHub (Sep 26, 2025): Posted on the wrong section, sorry
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#8252
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?