Commit graph

1667 commits

Author SHA1 Message Date
Bruce MacDonald
884d78ceb3 allow embedding from model binary 2023-08-08 14:38:57 -04:00
Bruce MacDonald
3ceac05108 Add embedding docs 2023-08-08 14:04:11 -04:00
Bruce MacDonald
21ddcaa1f1 pr comments
- default to embeddings enabled
- move embedding logic for loaded model to request
- allow embedding full directory
- close llm on reload
2023-08-08 13:49:37 -04:00
Michael Yang
f2074ed4c0
Merge pull request #306 from jmorganca/default-keep-system
automatically set num_keep if num_keep < 0
2023-08-08 09:25:34 -07:00
Bruce MacDonald
a6f6d18f83 embed text document in modelfile 2023-08-08 11:27:17 -04:00
Bruce MacDonald
34a13a9d05
pass flags to serve to allow setting allowed-origins + host and port 2023-08-08 10:41:42 -04:00
Jeffrey Morgan
8713ac23a8 allow overriding template and system in /api/generate
Fixes #297
Fixes #296
2023-08-08 00:55:34 -04:00
Jeffrey Morgan
5eb712f962 trim whitespace before checking stop conditions
Fixes #295
2023-08-08 00:29:19 -04:00
Michael Yang
4dc5b117dd automatically set num_keep if num_keep < 0
num_keep defines how many tokens to keep in the context when truncating
inputs. if left to its default value of -1, the server will calculate
num_keep to be the left of the system instructions
2023-08-07 16:19:12 -07:00
Matt Williams
931a5f3cb9
Merge pull request #304 from jmorganca/matt/docs
missed a backtick
2023-08-07 15:14:06 -07:00
Jeffrey Morgan
639288bf2b make ollama binary executable on build 2023-08-07 18:10:37 -04:00
Jeffrey Morgan
d112c15d58 remove old library and web directories 2023-08-07 18:09:24 -04:00
Matt Williams
1267895e44 missed a backtick
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-07 13:53:49 -07:00
Matt Williams
089d03bc8d
Merge pull request #289 from jmorganca/docs
First draft of API Docs
2023-08-07 13:46:22 -07:00
Matt Williams
e37f4c4f42 DockerIt example
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-07 13:45:22 -07:00
Michael Yang
ab3ced9d32
Merge pull request #276 from jmorganca/rope-freq
configurable rope frequency parameters
2023-08-07 13:39:38 -07:00
Matt Williams
0c52b4509b get rid of namespace and site
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-07 13:27:58 -07:00
Matt Williams
13aace3d34 clarify some more
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-07 13:21:54 -07:00
Matt Williams
2b3bb41598 model name format added
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-07 13:17:16 -07:00
cmiller01
93492f1e18 correct precedence of serve params (args over env over default) 2023-08-07 19:55:20 +00:00
Michael Chiang
54ba3e2ceb
langchain JS integration (#302)
langchain JS integration
2023-08-07 12:21:36 -04:00
Matt Williams
4904cd8bcd update simpler code samples
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-07 07:40:38 -07:00
Matt Williams
8a45359ec6
Update docs/api.md
Co-authored-by: Jeffrey Morgan <jmorganca@gmail.com>
2023-08-07 07:33:05 -07:00
cmiller01
fb593b7bfc pass flags to serve to allow setting allowed-origins + host and port
* resolves: https://github.com/jmorganca/ollama/issues/300 and
https://github.com/jmorganca/ollama/issues/282

* example usage:
```
ollama serve --port 9999 --allowed-origins "http://foo.example.com,http://192.0.0.1"
```
2023-08-07 03:34:37 +00:00
Matt Williams
2544b8afa1 update as per Mike's comments
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-04 17:42:24 -07:00
Matt Williams
ac1b04f271
Update docs/api.md
Co-authored-by: Michael Yang <mxyng@pm.me>
2023-08-04 17:40:52 -07:00
Matt Williams
123fdeb919
Update docs/api.md
Co-authored-by: Michael Yang <mxyng@pm.me>
2023-08-04 17:38:52 -07:00
Matt Williams
5c82bf95d1
Update docs/api.md
Co-authored-by: Michael Yang <mxyng@pm.me>
2023-08-04 17:12:24 -07:00
Matt Williams
38a9b1618c missed some quotes
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-04 16:09:07 -07:00
Matt Williams
c18be72a3b complete 1st draft of api docs
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-04 16:08:11 -07:00
Matt Williams
a101fe51a7 clean up
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-04 12:56:41 -07:00
Bruce MacDonald
06fc48ad66
Update README.md (#285)
Ollama now supports Intel Macs
2023-08-04 15:45:55 -04:00
Matt Williams
d93e2f9210 fleshing out response
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-04 12:38:58 -07:00
Matt Williams
31edc829fc continuing
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-04 12:30:23 -07:00
Matt Williams
b31104768c filling out generate
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-04 12:27:47 -07:00
Matt Williams
b662d9fd8c starting to build out some docs
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-04 11:55:00 -07:00
Matt Williams
da36196d79 Update the modelfile
needed to override the system prompt
from orca and make it easier for a downstream
user to define their system prompt

Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-04 08:11:24 -07:00
Michael Yang
b9f4d67554 configurable rope frequency parameters 2023-08-03 22:11:58 -07:00
Matt Williams
42903973b7 Added an example to generate a list of 10 tweets
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-03 17:26:05 -07:00
Matt Williams
8f2df948ab Create a sentiments example
Signed-off-by: Matt Williams <m@technovangelist.com>
2023-08-03 16:38:31 -07:00
Jeffrey Morgan
e3fb1fd3f1 server: compare options correctly 2023-08-03 15:55:40 -04:00
Michael Yang
29b897f525
Merge pull request #253 from jmorganca/upload
use a pipe to push to registry with progress
2023-08-03 12:11:23 -07:00
Michael Yang
85aeb42869
Merge pull request #270 from jmorganca/update-llama-cpp
update llama.cpp
2023-08-03 12:09:00 -07:00
Michael Yang
c5bcf32823 update llama.cpp 2023-08-03 11:50:24 -07:00
Michael Yang
a71ff3f6a2 use a pipe to push to registry with progress
switch to a monolithic upload instead of a chunk upload through a pipe
to report progress
2023-08-03 10:37:13 -07:00
Michael Chiang
f0b365a478
Merge pull request #268 from jmorganca/mchiang0610-patch-2
Update README.md
2023-08-03 11:23:31 -04:00
Michael Chiang
df8048fecd
Update README.md 2023-08-03 11:22:57 -04:00
Michael Yang
da2459d519
Update README.md (#265) 2023-08-02 22:38:32 -04:00
Bruce MacDonald
bd6d741d87
tell users to check the server error logs 2023-08-02 17:08:11 -04:00
Bruce MacDonald
8b1e791820
allow specifying zero values in modelfile 2023-08-02 17:07:53 -04:00