ollama - 💡(How to fix) Fix lots of models tools are not working

[@ollama]# podman exec -it ollama ollama ls
NAME                        ID              SIZE      MODIFIED
devstral-small-2:24b        24277f07f62d    15 GB     18 hours ago
qwen3-coder:30b             06c1097efce0    18 GB     18 hours ago
qwen2.5-coder:1.5b          d7372fd82851    986 MB    5 days ago
deepseek-ocr:latest         0e7b018b8a22    6.7 GB    7 days ago
deepseek-coder:33b          acec7c0b0fd9    18 GB     7 days ago
deepseek-ocr:3b             0e7b018b8a22    6.7 GB    7 days ago
deepseek-r1:14b             c333b7232bdb    9.0 GB    7 days ago
deepseek-coder-v2:16b       63fb193b3a9b    8.9 GB    7 days ago
nomic-embed-text:latest     0a109f422b47    274 MB    12 days ago
qwen2.5-coder:32b           b92d6a0bd47e    19 GB     12 days ago
qwen2.5-coder:14b           9ec8897f747e    9.0 GB    12 days ago
mxbai-embed-large:latest    468836162de7    669 MB    2 weeks ago
llama3.1:latest             46e0c10c039e    4.9 GB    2 weeks ago
llama3:latest               365c0bd3c000    4.7 GB    2 months ago

---

podman exec -it ollama ollama -v
ollama version is 0.23.2

---

this partial llama3.1 tool dump (executes tool successfully)

E...J.@.@.c.........,.....wx/#.6P.......ed1d03f895bf2dc8dc6df21db3042284a6f4416b06a29\nTEMPLATE \"\"\"{{- if or .System .Tools }}\u003c|start_header_id|\u003esyst
em\u003c|end_header_id|\u003e\n{{- if .System }}\n\n{{ .System }}\n{{- end }}\n{{- if .Tools }}\n\nCutting Knowledge Date: December 2023\n\nWhen you receive a too
l call response, use the output to format an answer to the orginal user question.\n\nYou are a helpful assistant with tool calling capabilities.\n{{- end }}\u003c
|eot_id|\u003e\n{{- end }}\n{{- range $i, $_ := .Messages }}\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\n{{- if eq .Role \"user\" }}\u003c|start_header_id|
\u003euser\u003c|end_header_id|\u003e\n{{- if and $.Tools $last }}\n\nGiven the following functions, please respond with a JSON for a function call with its prope
r arguments that best answers the given prompt.\n\nRespond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}. Do
not use variables.\n\n{{ range $.Tools }}\n{{- . }}\n{{ end }}\nQuestion: {{ .Content }}\u003c|eot_id|\u003e\n{{- else }}\n\n{{ .Content }}\u003c|eot_id|\u003e\n{
{- end }}{{ if $last }}\u003c|start_header_id|\u003eassistant\u003c|end_header_id|\u003e\n\n{{ end }}\n{{- else if eq .Role \"assistant\" }}\u003c|start_header_id
|\u003eassistant\u003c|end_header_id|\u003e\n{{- if .ToolCalls }}\n{{ range .ToolCalls }}\n{\"name\": \"{{ .Function.Name }}\", \"parameters\": {{ .Function.Argum
ents }}}{{ end }}\n{{- else }}\n\n{{ .Cont
E...J!@.@.c.........,......./#.6P.......id|\u003e\"","template":"{{- if or .System .Tools }}\u003c|start_header_id|\u003esystem\u003c|end_header_id|\u003e\n{{- if
 .System }}\n\n{{ .System }}\n{{- end }}\n{{- if .Tools }}\n\nCutting Knowledge Date: December 2023\n\nWhen you receive a tool call response, use the output to fo
rmat an answer to the orginal user question.\n\nYou are a helpful assistant with tool calling capabilities.\n{{- end }}\u003c|eot_id|\u003e\n{{- end }}\n{{- range
 $i, $_ := .Messages }}\n{{- $last := eq (len (slice $.Messages $i)) 1 }}\n{{- if eq .Role \"user\" }}\u003c|start_header_id|\u003euser\u003c|end_header_id|\u003e
\n{{- if and $.Tools $last }}\n\nGiven the following functions, please respond with a JSON for a function call with its proper arguments that best answers the giv
en prompt.\n\nRespond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}. Do not use variables.\n\n{{ range $.Tool
s }}\n{{- . }}\n{{ end }}\nQuestion: {{ .Content }}\u003c|eot_id|\u003e\n{{- else }}\n\n{{ .Content }}\u003c|eot_id|\u003e\n{{- end }}{{ if $last }}\u003c|start_h
eader_id|\u003eassistant\u003c|end_header_id|\u003e\n\n{{ end }}\n{{- else if eq .Role \"assistant\" }}\u003c|start_header_id|\u003eassistant\u003c|end_header_id|
\u003e\n{{- if .ToolCalls }}\n{{ range .ToolCalls }}\n{\"name\": \"{{ .Function.Name }}\", \"parameters\": {{ .Function.Arguments }}}{{ end }}\n{{- else }}\n\n{{
.Content }}\n{{- end }}{{ if not $last }}\
{"model":"llama3.1:latest","messages":[{"role":"system","content":"<important_rules>\n  You are in agent mode.\n\n  If you need to use multiple tools, you can cal
l multiple read-only tools simultaneously.\n\n  Always include the language and file name in the info string when you write code blocks.\n  If you are editing \"s
rc/main.py\" for example, your code block should start with ' src/main.py'\n\n\nFor larger codeblocks (>20 lines), use brief language-appropriate placeho
lders for unmodified sections, e.g. '// ... existing code ...'\n\nHowever, only output codeblocks for suggestion and demonstration purposes, for example, when enu
merating multiple hypothetical options. For implementing changes, use the edit tools.\n\n</important_rules>\n\nWhen using the qdrant_find tool, always include the
 collection_name argument. Select the appropriate collection based on the content:  \n- Use \"wordpress-stubs\" for WordPress-related searches, themes, plugins, a
nd core functionality  \n\n \nNever omit the collection_name parameter. If unsure which collection to use, ask for clarification."},{"role":"user","content":"quer
y 'filter_wp_get_nav_menus' of wordpress-stubs"}],"options":{"num_predict":4096,"num_ctx":8192},"think":false,"keep_alive":1800
E...M.@...............,.2d.;*...P...S...,"tools":[{"type":"function","function":{"name":"qdrant_store","description":"Store information in the Qdrant database wit
h GPU-accelerated embeddings.","parameters":{"type":"object","properties":{"information":{"type":"string","description":"The text information to store. This will
be embedded and\n         made searchable via semantic similarity."},"collection_name":{"default":"","type":"string","description":"Name of the collection to stor
e in. Required if no\n             default collection is configured."},"metadata":{"anyOf":[{"additionalProperties":true,"type":"object"},{"type":"null"}],"defaul
t":null,"description":"Optional metadata dictionary to attach to the stored point."}},"required":["information"],"additionalProperties":false}}},{"type":"function
","function":{"name":"qdrant_find","description":"Search for relevant information in the Qdrant database using semantic similarity.","parameters":{"type":"object"
,"properties":{"query":{"type":"string","description":"Natural language query to search for. The query is embedded using\n   the same GPU model used for storage,
ensuring accurate results."},"collection_name":{"default":"","type":"string","description":"Name of the collection to search in. Required if no\n             defa
ult collection is configured."},"top_k":{"default":5,"type":"integer","description":"Maximum number of results to return (default: 5)."}},"required":["query"],"ad
ditionalProperties":false}}}]}
{"model":"llama3.1:latest","created_at":"2026-05-09T16:52:52.523682698Z","message":{"role":"assistant","content":"","tool_calls":[{"id":"call_k16gayjx","function"
:{"index":0,"name":"qdrant_find","arguments":{"collection_name":"wordpress-stubs","query":"filter_wp_get_nav_menus","top_k":10}}}]},"done":false}
{"model":"llama3.1:latest","created_at":"2026-05-09T16:52:52.532255652Z","message":{"role":"assistant","content":""},"done":true,"done_reason":"stop","total_durat
ion":656444213,"load_duration":130969511,"prompt_eval_count":569,"prompt_eval_duration":183408614,"eval_count":39,"eval_duration":271145353}
........{"model":"nomic-embed-text:latest","input":"filter_wp_get_nav_menus"}
{"model":"llama3.1:latest","messages":[{"role":"system","content":"<important_rules>\n  You are in agent mode.\n\n  If you need to use multiple tools, you can cal
l multiple read-only tools simultaneously.\n\n  Always include the language and file name in the info string when you write code blocks.\n  If you are editing \"s
rc/main.py\" for example, your code block should start with ' src/main.py'\n\n\nFor larger codeblocks (>20 lines), use brief language-appropriate placeho
lders for unmodified sections, e.g. '// ... existing code ...'\n\nHowever, only output codeblocks for suggestion and demonstration purposes, for example, when enumerating multiple hypothetical options. For implementing changes, use the edit tools.\n\n</important_rules>\n\nWhen using the qdrant_find tool, always include the collection_name argument. Select the appropriate collection based on the content:  \n- Use \"wordpress-stubs\" for WordPress-related searches, themes, plugins, and core functionality  \n\n \nNever omit the collection_name parameter. If unsure which collection to use, ask for clarification."},{"role":"user","content":"query 'filter_wp_get_nav_menus' of wordpress-stubs"},{"role":"assistant","content":" ","tool_calls":[{"function":{"name":"qdrant_f
E...U.@....q..........,..Bb..Q^.P....r..ind","arguments":{"collection_name":"wordpress-stubs","query":"filter_wp_get_nav_menus","top_k":10}}}]},{"role":"tool","content":"--- Result 1 (score: 0.7992) ---\nType: function\nSymbol: wp_nav_menu_setup\nQualified: wp_nav_menu_setup\nFile: wordpress-stubs/wordpress-stubs.php\n---\n    /**\n     * Register nav menu meta boxes and advanced menu items.\n     *\n     * @since 3.0.0\n     */\n    function wp_nav_menu_setup()\n    {\n    }\n\n--- Result 2 (score: 0.7922) ---\nClass: WP_Customize_Nav_Menus\nType: method\nSymbol: filter_wp_nav_menu\nQualified: WP_Customize_Nav_Menus::filter_wp_nav_menu\nFile: wordpress-stubs/wordpress-stubs.php\n---\n        /**\n         * Prepares wp_nav_menu() calls for partial refresh.\n         *\n         * Injects attributes into container element.\n         *\n         * @since 4.3.0\n         *\n         * @see wp_nav_menu()\n         *\n         * @param string $nav_menu_content The HTML content for the navigation menu.\n         * @param object $args             An object containing wp_nav_menu() arguments.\n         * @return string Nav menu HTML with selective refresh attributes added if partial can be refreshed.\n         */\n        public function filter_wp_nav_menu($nav_menu_content, $args)\n        {\n        }\n\n--- Result 3 (score: 0.7915) ---\nClass: WP_Customize_Nav_Menu_Setting\nType: method\nSymbol: filter_wp_get_nav_menu_object\nQualified: WP_Customize_Nav_Menu_Setting::filter_wp_get_nav_menu_object\nFile: wordpress-stubs/wordpress-stubs.php\n---\n        /**\n         * Filters the wp_get_nav_menu_object() result to supply the previewed menu object.\n         *\n         * Requesting a nav_menu object by anything but ID is not supported.\n         *\n         * @since 4.3.0\n         *\n         * @see wp_get_nav_menu_object()\n         *\n         * @param object|null $menu_obj Object returned by wp_get_nav_menu_object().\n         * @param string      $menu_id  ID of the nav_menu term. Requests by slug or name will be ignored.\n         * @return object|null\n         */\n        public function filter_wp_get_nav_menu_object($menu_obj, $menu_id)\n        {\n        }\n\n--- Result 4 (score: 0.7878) ---\nType: function\nSymbol: get_registered_nav_menus\nQualified: get_registered_nav_menus\nFile: wordpress-stubs/wordpress-stubs.php\n---\n    /**\n     * Retrieves all registered navigation menu locations in a theme.\n     *\n     * @since 3.0.0\n     *\n     * @global array $_wp_registered_nav_menus\n     *\n     * @return string[] Associative array of registered navigation menu descriptions keyed\n     *                  by their location. If none are registered, an empty array.\n     */\n    function get_registered_nav_menus()\n    {\n    }\n\n--- Result 5 (score: 0.7774) ---\nClass: WP_Custo


this is partial qwen2.5-coder dump (outputs json, does not call tool)

.","parameters":{"type":"object","properties":{"information":{"type":"string","description":"The text information to store. This will be embedded and\n         ma
de searchable via semantic similarity."},"collection_name":{"default":"","type":"string","description":"Name of the collection to store in. Required if no\n             default collection is configured."},"metadata":{"anyOf":[{"additionalProperties":true,"type":"object"},{"type":"null"}],"default":null,"description":"Optional metadata dictionary to attach to the stored point."}},"required":["information"],"additionalProperties":false}}},{"type":"function","function":{"name":"qdrant_find","description":"Search for relevant information in the Qdrant database using semantic similarity.","parameters":{"type":"object","properties":{"query":{"type":"string","description":"Natural language query to search for. The query is embedded using\n   the same GPU model used for storage, ensuring accurate results."},"collection_name":{"default":"","type":"string","description":"Name of the collection to search in. Required if no\n             default collection is configured."},"top_k":{"default":5,"type":"integer","description":"Maximum number of results to return (default: 5)."}},"required":["query"],"additionalProperties":false}}}]}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.608422856Z","message":{"role":"assistant","content":"{\n"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.630223381Z","message":{"role":"assistant","content":" "},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.6446433Z","message":{"role":"assistant","content":" \""},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.659207604Z","message":{"role":"assistant","content":"name"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.673770002Z","message":{"role":"assistant","content":"\":"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.688364944Z","message":{"role":"assistant","content":" \""},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.702808677Z","message":{"role":"assistant","content":"q"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.717267712Z","message":{"role":"assistant","content":"dr"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.731826227Z","message":{"role":"assistant","content":"ant"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.746295175Z","message":{"role":"assistant","content":"_find"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.760711903Z","message":{"role":"assistant","content":"\",\n"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.775205841Z","message":{"role":"assistant","content":" "},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.789688948Z","message":{"role":"assistant","content":" \""},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.804204056Z","message":{"role":"assistant","content":"arguments"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.818619299Z","message":{"role":"assistant","content":"\":"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.833163918Z","message":{"role":"assistant","content":" {\n"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.847782434Z","message":{"role":"assistant","content":"   "},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.86228024Z","message":{"role":"assistant","content":" \""},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.876704129Z","message":{"role":"assistant","content":"collection"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.891235434Z","message":{"role":"assistant","content":"_name"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.905640716Z","message":{"role":"assistant","content":"\":"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.920150512Z","message":{"role":"assistant","content":" \""},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.934602947Z","message":{"role":"assistant","content":"wordpress"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.949102033Z","message":{"role":"assistant","content":"-st"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.963500147Z","message":{"role":"assistant","content":"ubs"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.978040411Z","message":{"role":"assistant","content":"\",\n"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:57.992406573Z","message":{"role":"assistant","content":"   "},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.006921619Z","message":{"role":"assistant","content":" \""},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.021305316Z","message":{"role":"assistant","content":"query"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.0358614Z","message":{"role":"assistant","content":"\":"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.05024998Z","message":{"role":"assistant","content":" \""},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.064810173Z","message":{"role":"assistant","content":"filter"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.079217683Z","message":{"role":"assistant","content":"_wp"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.093700231Z","message":{"role":"assistant","content":"_get"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.108141766Z","message":{"role":"assistant","content":"_nav"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.122538101Z","message":{"role":"assistant","content":"_menus"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.136976701Z","message":{"role":"assistant","content":"\"\n"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.151489106Z","message":{"role":"assistant","content":" "},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.165900409Z","message":{"role":"assistant","content":" }\n"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.180350032Z","message":{"role":"assistant","content":"}"},"done":false}
{"model":"qwen2.5-coder:14b","created_at":"2026-05-09T17:00:58.194729378Z","message":{"role":"assistant","content":""},"done":true,"done_reason":"stop","total_duration":41643792520,"load_duration":40822669979,"prompt_eval_count":568,"prompt_eval_duration":220258472,"eval_count":41,"eval_duration":515836985}




deepseek r1 (has tools on the website)

There was an error handling the response from Deepseek R1 14B.

Please try to submit your message again.


Resubmit last message
View error output
"registry.ollama.ai/library/deepseek-r1:14b does not support tools"