ollama

Commit Graph

Author	SHA1	Message	Date
Michael Yang	d290e87513	add suffix support to generate endpoint this change is triggered by the presence of "suffix", particularly useful for code completion tasks	2 years ago
Michael Yang	5a83f79afd	remove unneeded tool calls	2 years ago
Jeffrey Morgan	7ac6d462ec	server: return empty slice on empty `/api/embed` request (#5713 ) * server: return empty slice on empty `/api/embed` request * fix tests	2 years ago
Michael Yang	d02bbebb11	tools	2 years ago
Jeffrey Morgan	9e35d9bbee	server: lowercase roles for compatibility with clients (#5695 )	2 years ago
royjhan	b9f5e16c80	Introduce `/api/embed` endpoint supporting batch embedding (#5127 ) * Initial Batch Embedding * Revert "Initial Batch Embedding" This reverts commit `c22d54895a`. * Initial Draft * mock up notes * api/embed draft * add server function * check normalization * clean up * normalization * playing around with truncate stuff * Truncation * Truncation * move normalization to go * Integration Test Template * Truncation Integration Tests * Clean up * use float32 * move normalize * move normalize test * refactoring * integration float32 * input handling and handler testing * Refactoring of legacy and new * clear comments * merge conflicts * touches * embedding type 64 * merge conflicts * fix hanging on single string * refactoring * test values * set context length * clean up * testing clean up * testing clean up * remove function closure * Revert "remove function closure" This reverts commit `55d48c6ed1`. * remove function closure * remove redundant error check * clean up * more clean up * clean up	2 years ago
Patrick Devine	057d31861e	remove template (#5655 )	2 years ago
royjhan	996bb1b85e	OpenAI: /v1/models and /v1/models/{model} compatibility (#5007 ) * OpenAI v1 models * Refactor Writers * Add Test Co-Authored-By: Attila Kerekes * Credit Co-Author Co-Authored-By: Attila Kerekes <439392+keriati@users.noreply.github.com> * Empty List Testing * Use Namespace for Ownedby * Update Test * Add back envconfig * v1/models docs * Use ModelName Parser * Test Names * Remove Docs * Clean Up * Test name Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com> * Add Middleware for Chat and List * Testing Cleanup * Test with Fatal * Add functionality to chat test * OpenAI: /v1/models/{model} compatibility (#5028) * Retrieve Model * OpenAI Delete Model * Retrieve Middleware * Remove Delete from Branch * Update Test * Middleware Test File * Function name * Cleanup * Test Update * Test Update --------- Co-authored-by: Attila Kerekes <439392+keriati@users.noreply.github.com> Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>	2 years ago
Daniel Hiltgen	97c9e11768	Switch use_mmap to a pointer type This uses nil as undefined for a cleaner implementation.	2 years ago
Daniel Hiltgen	7e7749224c	Fix use_mmap parsing for modelfiles Add the new tristate parsing logic for the code path for modelfiles, as well as a unit test.	2 years ago
royjhan	fedf71635e	Extend api/show and ollama show to return more model info (#4881 ) * API Show Extended * Initial Draft of Information Co-Authored-By: Patrick Devine <pdevine@sonic.net> * Clean Up * Descriptive arg error messages and other fixes * Second Draft of Show with Projectors Included * Remove Chat Template * Touches * Prevent wrapping from files * Verbose functionality * Docs * Address Feedback * Lint * Resolve Conflicts * Function Name * Tests for api/show model info * Show Test File * Add Projector Test * Clean routes * Projector Check * Move Show Test * Touches * Doc update --------- Co-authored-by: Patrick Devine <pdevine@sonic.net>	2 years ago
Daniel Hiltgen	171796791f	Adjust mmap logic for cuda windows for faster model load On Windows, recent llama.cpp changes make mmap slower in most cases, so default to off. This also implements a tri-state for use_mmap so we can detect the difference between a user provided value of true/false, or unspecified.	2 years ago
royjhan	89c79bec8c	Add ModifiedAt Field to /api/show (#5033 ) * Add Mod Time to Show * Error Handling	2 years ago
Patrick Devine	c69bc19e46	move OLLAMA_HOST to envconfig (#5009 )	2 years ago
royjhan	4bf1da4944	Separate ListResponse and ModelResponse for api/tags vs api/ps (#4842 ) * Remove false time fields * Struct Separation for List and Process * Remove Marshaler	2 years ago
Michael Yang	e40145a39d	lint	2 years ago
Michael Yang	c895a7d13f	some gocritic	2 years ago
Patrick Devine	6845988807	Ollama `ps` command for showing currently loaded models (#4327 )	2 years ago
Jeffrey Morgan	6602e793c0	Use `--quantize` flag and `quantize` api parameter (#4321 ) * rename `--quantization` to `--quantize` * backwards * Update api/types.go Co-authored-by: Michael Yang <mxyng@pm.me> --------- Co-authored-by: Michael Yang <mxyng@pm.me>	2 years ago
Bruce MacDonald	c02db93243	omit empty done reason	2 years ago
Bruce MacDonald	cfa84b8470	add done_reason to the api (#4235 )	2 years ago
Jeffrey Morgan	d5eec16d23	use model defaults for `num_gqa`, `rope_frequency_base ` and `rope_frequency_scale` (#1983 )	2 years ago
Eli Bendersky	d77c1c5f9d	api: fill up API documentation (#3596 ) * api: fill up API documentation Followup for #2878 Now that the documentation is more complete, mention it in the README. Updates #2840 * fix typo/lint * Update README.md Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com> --------- Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>	2 years ago
Jackie Li	af47413dba	Add MarshalJSON to Duration (#3284 ) --------- Co-authored-by: Patrick Devine <patrick@infrahq.com>	2 years ago
Patrick Devine	9009bedf13	better checking for OLLAMA_HOST variable (#3661 )	2 years ago
Jeffrey Morgan	993cf8bf55	llm: limit generation to 10x context size to avoid run on generations (#3918 ) * llm: limit generation to 10x context size to avoid run on generations * add comment * simplify condition statement	2 years ago
Daniel Hiltgen	34b9db5afc	Request and model concurrency This change adds support for multiple concurrent requests, as well as loading multiple models by spawning multiple runners. The default settings are currently set at 1 concurrent request per model and only 1 loaded model at a time, but these can be adjusted by setting OLLAMA_NUM_PARALLEL and OLLAMA_MAX_LOADED_MODELS.	2 years ago
Cheng	62be2050dd	chore: use errors.New to replace fmt.Errorf will much better (#3789 )	2 years ago
Eli Bendersky	ad90b9ab3d	api: start adding documentation to package api (#2878 ) * api: start adding documentation to package api Updates #2840 * Fix lint typo report	2 years ago
Michael Yang	01114b4526	fix: rope	2 years ago
Michael Yang	9502e5661f	cgo quantize	2 years ago
Michael Yang	e1c9a2a00f	no blob create if already exists	2 years ago
Michael Yang	be517e491c	no rope parameters	2 years ago
Patrick Devine	1b272d5bcd	change `github.com/jmorganca/ollama` to `github.com/ollama/ollama` (#3347 )	2 years ago
Patrick Devine	47cfe58af5	Default Keep Alive environment variable (#3094 ) --------- Co-authored-by: Chris-AS1 <8493773+Chris-AS1@users.noreply.github.com>	2 years ago
Jeffrey Morgan	3b4bab3dc5	Fix embeddings load model behavior (#2848 )	2 years ago
Ikko Eltociear Ashimine	e95b896790	Update types.go (#2744 ) specfied -> specified	2 years ago
Michael Yang	897b213468	use http.DefaultClient (#2530 ) default client already handles proxy	2 years ago
bnorick	caf2b13c10	Fix infinite keep_alive (#2480 )	3 years ago
Patrick Devine	b5cf31b460	add keep_alive to generate/chat/embedding api endpoints (#2146 )	3 years ago
Patrick Devine	7c40a67841	Save and load sessions (#2063 )	3 years ago
Michael Yang	745b5934fa	add model to ModelResponse	3 years ago
Michael Yang	a38d88d828	api: add model for all requests prefer using req.Model and fallback to req.Name	3 years ago
Michael Yang	5ffbbea1d7	remove client.py	3 years ago
Patrick Devine	22e93efa41	add show info command and fix the modelfile	3 years ago
Brian Murray	0d6e3565ae	Add embeddings to API (#1773 )	3 years ago
Jeffrey Morgan	55978c1dc9	clean up cache api option	3 years ago
Jeffrey Morgan	d4ebdadbe7	enable `cache_prompt` by default	3 years ago
K0IN	10da41d677	Add Cache flag to api (#1642 )	3 years ago
Bruce MacDonald	d99fa6ce0a	send empty messages on last chat response (#1530 )	3 years ago

1 2 3 4 5

224 Commits (main)