Parth Sareen
5267d31d56
docs: ollama launch ( #13852 )
2026-01-23 23:18:50 -08:00
Parth Sareen
aae6ecbaff
cmd: rename ollama config to ollama launch ( #13871 )
2026-01-23 18:40:40 -08:00
Parth Sareen
771d9280ec
cmd: ollama config fix droid model name configuration ( #13856 )
2026-01-23 11:44:22 -08:00
Parth Sareen
199c41e16e
cmd: ollama config command to help configure integrations to use Ollama ( #13712 )
2026-01-22 20:17:11 -08:00
Parth Sareen
f52c21f457
fix: handle Enter key pressed during model loading ( #13839 )
2026-01-22 18:32:02 -08:00
Parth Sareen
b1a0db547b
docs: add env var needed for claude code in docs ( #13721 )
2026-01-15 10:11:00 -08:00
Parth Sareen
75d7b5f926
cmd: enable multi-line input and shift enter ( #13694 )
2026-01-14 17:52:46 -08:00
Parth Sareen
35c3c9e3c2
anthropic: allow non-thinking models when using Anthropic API ( #13692 )
2026-01-12 15:13:26 -08:00
Parth Sareen
d06acbcb19
x/cmd: enable web search and web fetch with flag ( #13690 )
2026-01-12 13:59:40 -08:00
Parth Sareen
2185112d84
x/cmd: connect /set flags to behavior in experimental mode ( #13684 )
2026-01-12 00:40:44 -08:00
Parth Sareen
91926601dc
x: add missing /set, /show, /load, /save commands to experimental mode ( #13682 )
2026-01-11 23:12:31 -08:00
Parth Sareen
1ef4241727
x: request access for all commands, add welcome message ( #13662 )
2026-01-09 18:20:39 -08:00
Parth Sareen
68fafd3002
x: improve approval selector with clearer labels ( #13663 )
2026-01-09 17:08:12 -08:00
Parth Sareen
2b2cda7a2b
api: implement anthropic api ( #13600 )
...
* api: add Anthropic Messages API compatibility layer
Add middleware to support the Anthropic Messages API format at /v1/messages.
This enables tools like Claude Code to work with Ollama local and cloud models through the
Anthropic API interface.
2026-01-09 11:53:36 -08:00
Parth Sareen
a23b559b4c
x: disable web search tool registration ( #13656 )
2026-01-09 01:42:20 -08:00
Parth Sareen
53a5a9e9ae
x: redesign agent UI with minimal styling ( #13650 )
2026-01-08 15:40:07 -08:00
Parth Sareen
e30e08a7d6
x: remove Ctrl+O tool output expansion feature ( #13640 )
2026-01-07 15:34:08 -08:00
Parth Sareen
12e2b3514a
x: agent loop ux improvements ( #13635 )
2026-01-07 01:27:15 -08:00
Parth Sareen
76912c062a
x: add experimental agent loop ( #13628 )
2026-01-05 23:38:40 -08:00
Parth Sareen
7325791599
parsers/renderers: functiongemma ( #13521 )
2025-12-18 07:55:37 -08:00
Parth Sareen
1c094038bc
types: add nested property support for tool definitions ( #13508 )
2025-12-17 11:54:09 -08:00
Parth Sareen
89eb795293
parsers/renderers: use think from user for nemotron ( #13492 )
2025-12-15 18:55:17 -08:00
Parth Sareen and Daniel Hiltgen
7e3ea813c1
llama/parsers/renderers: nemotron 3 nano ( #13489 )
...
---------
Co-authored-by: Daniel Hiltgen <daniel@ollama.com >
2025-12-15 18:00:08 -08:00
Parth Sareen
ffbe8e076d
model: add olmo3 and olmo3.1 ( #13415 )
2025-12-15 15:20:04 -08:00
Parth Sareen
e3731fb160
renderers: add olmo3.1 and olmo3 fixes ( #13447 )
2025-12-15 11:26:43 -08:00
Parth Sareen
9b2035d194
openai: add tool call appending to previous assistant message ( #13434 )
...
* openai: add tool call appending to previous asst message
* add tests for thinking appending
2025-12-11 17:30:12 -08:00
Parth Sareen
2bccf8c624
renderers/parsers: olmo3 instruct ( #13383 )
2025-12-09 11:12:27 -08:00
Parth Sareen
0c5e5f6630
parsers/renderers: olmo3 think ( #13290 )
2025-12-09 10:41:47 -08:00
Parth Sareen
ce29f695b4
docs: add logprobs to openapi ( #13090 )
2025-11-14 14:14:58 -08:00
Parth Sareen
c114987523
logprob: add bytes to logprobs ( #13068 )
2025-11-13 13:49:25 -08:00
Parth Sareen
755ac3b069
docs: update n8n URL for Ollama ( #12994 )
2025-11-07 20:07:26 -08:00
Parth Sareen
d828517e78
docs: update readme and links ( #12809 )
2025-10-28 16:20:02 -07:00
Parth Sareen
3d99d9779a
docs: add docs for docs.ollama.com ( #12805 )
2025-10-28 13:18:48 -07:00
Parth Sareen
6d02a43a75
docs: rename to mdx to setup docs site ( #12804 )
2025-10-28 13:04:31 -07:00
Parth Sareen
5483497d7a
Revert "docs: add reference to docs.ollama.com ( #12800 )" ( #12803 )
...
This reverts commit 934dd9e196
2025-10-28 12:52:49 -07:00
Parth Sareen
934dd9e196
docs: add reference to docs.ollama.com ( #12800 )
2025-10-28 12:44:02 -07:00
Parth Sareen
c4c5a4a01e
types: send index for tool calls ( #12625 )
2025-10-14 19:35:15 -07:00
Parth Sareen
77060d462c
routes: structured outputs for gpt-oss ( #12460 )
2025-10-08 19:13:38 -07:00
Parth Sareen
8d6fffaead
runner: simplify parser entrypoints in runner ( #12233 )
2025-09-10 11:24:42 -07:00
Parth Sareen
20b53eaa72
tests: add tool calling integration test ( #12232 )
2025-09-09 14:01:11 -07:00
Parth Sareen
1a558f98e2
runner: move harmony to runner ( #12052 )
2025-09-08 15:07:59 -07:00
Parth Sareen
7cce5aac76
harmony: move harmony parsing into a package ( #12016 )
2025-08-21 13:56:22 -07:00
Parth Sareen
4742e12c23
docs: update turbo model name ( #11707 )
2025-08-05 17:29:08 -07:00
Parth Sareen
d73f8aa8c3
cmd: add default assistant role to message construction ( #11431 )
2025-07-16 11:18:16 -07:00
Parth Sareen
43107b15b9
add tool_name to api.md ( #11326 )
2025-07-07 16:53:13 -07:00
Parth Sareen
1f91cb0c8c
template: add tool result compatibility ( #11294 )
2025-07-07 15:53:42 -07:00
Parth Sareen
65f10c2823
tools: resiliency upgrade to name and arg extraction from template ( #10917 )
2025-05-30 15:18:09 -07:00
Parth Sareen
066d0f4746
tools: relax JSON parse constraints for tool calling ( #10872 )
2025-05-26 18:59:06 -07:00
Parth Sareen
aea6fb9b58
tools: remove newline stripping ( #10869 )
2025-05-26 17:16:00 -07:00
Parth Sareen
e8b981fa5d
tools: refactor tool call parsing and enable streaming ( #10415 )
2025-05-23 14:19:31 -07:00
Parth Sareen
884d26093c
llama: add minimum memory for grammar ( #10820 )
2025-05-22 18:53:31 -07:00
Parth Sareen
8cc33f4c2b
llama: fix memory leak for grammar ( #10696 )
2025-05-13 15:39:27 -07:00
Parth Sareen
11dde41824
server: improve spacing for JSON grammar ( #10131 )
2025-04-24 16:47:57 -07:00
Parth Sareen
a53d744b01
llama: remove model loading for grammar ( #10096 )
2025-04-24 11:51:19 -07:00
Parth Sareen
6747099d71
types: add any type and validation for ToolFunction enum ( #10166 )
2025-04-08 15:05:38 -07:00
Parth Sareen
b816ff86c9
docs: make context length faq readable ( #10006 )
2025-03-26 17:34:18 -07:00
Parth Sareen
00ebda8cc4
Revert "parser: remove role validation from Modelfile parser" ( #9917 )
...
This reverts commit ffbfe833da
2025-03-21 12:38:09 -07:00
Parth Sareen
d14ce75b95
docs: update final response for /api/chat stream ( #9919 )
2025-03-21 12:35:47 -07:00
Parth Sareen
42a14f7f63
sample: add error handling for empty logits ( #9740 )
2025-03-20 11:11:18 -07:00
Parth Sareen
108fe02165
sample: make mutations in transforms explicit ( #9743 )
...
* updated minP to use early exit making use of sorted tokens
2025-03-17 11:24:18 -07:00
Parth Sareen
5c0b663969
sample: separate softmax and temperature transforms ( #9732 )
2025-03-13 09:53:27 -07:00
ParthSareen
4aeb67ef4c
sample: do all sorting in topK
2025-03-12 11:59:17 -07:00
ParthSareen
3ba91634c1
sample: simplify top_k=0 sorting
2025-03-12 11:59:17 -07:00
ParthSareen
1b7433b71e
sample: use container/heap for top_k
2025-03-12 11:59:17 -07:00
Parth Sareen
7e34f4fbfa
sample: add numerical stability to temperature/softmax transform ( #9631 )
2025-03-10 14:43:53 -07:00
Parth Sareen
0682dae027
sample: improve ollama engine sampler performance ( #9374 )
...
This change bring in various interface cleanups along with greatly improving the performance of the sampler.
Tested with llama3.2 on local machine.
Improves performance from ~ 70 tokens/s -> 135 tokens/s with topK(40) enabled.
Without topK performance is ~ 110 tokens/s
2025-03-07 12:37:48 -08:00
Parth Sareen
c245b0406f
sample: remove transforms from greedy sampling ( #9377 )
2025-02-27 15:44:53 -08:00
Parth Sareen
0b7e1676eb
sample: add sampling package for new engine ( #8410 )
2025-02-24 17:19:01 -08:00
Parth Sareen
314573bfe8
config: allow setting context length through env var ( #8938 )
...
* envconfig: allow setting context length through env var
2025-02-24 13:26:35 -08:00
Parth Sareen
711648c9bb
docs: update api.md with streaming with tools is enabled ( #8676 )
2025-01-29 15:14:30 -08:00
Parth Sareen
84a2314463
examples: remove codified examples ( #8267 )
2025-01-13 11:26:22 -08:00
Parth Sareen
290cf2040a
llama: test key order preservation in schema_to_grammar ( #8078 )
...
This change adds a test to catch a regression in schema_to_grammar where
the order of keys in the JSON schema is not preserved in the generated
grammar, which is critical for step-by-step reasoning.
2024-12-18 19:44:50 -08:00
Parth Sareen
18f6a98bd6
llama: enable JSON schema key ordering for generating grammars ( #8055 )
2024-12-11 17:17:36 -08:00
Parth Sareen
de52b6c2f9
bugfix: "null" value json mode ( #7979 )
2024-12-06 14:13:15 -08:00
Parth Sareen
f6e87fd628
docs: update readmes for structured outputs ( #7962 )
2024-12-06 10:35:37 -08:00
Parth Sareen
c6c526275d
api: add generate endpoint for structured outputs ( #7939 )
2024-12-04 17:37:12 -08:00
630e7dc6ff
api: structured outputs - chat endpoint ( #7900 )
...
Adds structured outputs to chat endpoint
---------
Co-authored-by: Michael Yang <mxyng@pm.me >
Co-authored-by: Hieu Nguyen <hieunguyen1053@outlook.com >
2024-12-04 16:31:19 -08:00
Parth Sareen
5f8051180e
Enable index tracking for tools - openai api support ( #7888 )
2024-11-29 20:00:09 -08:00
Parth Sareen
ce7455a8e1
api: enable tool streaming ( #7836 )
2024-11-27 13:40:57 -08:00
Parth Sareen