Michael Yang
fccf8d179f
partial decode ggml bin for more info
2023-08-10 09:23:10 -07:00
Bruce MacDonald
5b5cc9c9f1
embeddings endpoint
2023-08-10 11:49:55 -04:00
Bruce MacDonald
4b3507f036
embeddings endpoint
...
Co-Authored-By: Jeffrey Morgan <jmorganca@gmail.com>
2023-08-10 11:45:57 -04:00
Jun Tian
5ebce03c77
Add an example on multiline input ( #311 )
2023-08-10 08:22:28 -07:00
Bruce MacDonald
5e25f801ed
fix a typo in the tweetwriter example Modelfile
2023-08-10 10:19:53 -04:00
Bruce MacDonald
8e1234b758
fix embeddings invalid values
2023-08-10 10:17:00 -04:00
Soroush Javadi
10885986b8
fix a typo in the tweetwriter example Modelfile
2023-08-10 15:12:48 +03:30
Bruce MacDonald
984c9c628c
fix embeddings invalid values
2023-08-09 16:50:53 -04:00
Bruce MacDonald
43c40c500e
add embed docs for modelfile
2023-08-09 16:14:58 -04:00
Bruce MacDonald
c4861360ec
remove embed docs
2023-08-09 16:14:19 -04:00
Bruce MacDonald
9738ef85db
allow for concurrent pulls of the same files
2023-08-09 11:35:24 -04:00
Bruce MacDonald
ac971c56d1
Update images.go
2023-08-09 11:31:54 -04:00
Bruce MacDonald
8228d166ce
pr comments
2023-08-09 11:31:54 -04:00
Bruce MacDonald
907e6c56b3
unlock downloadu in case or requestDownload err
2023-08-09 11:31:54 -04:00
Bruce MacDonald
868e3b31c7
allow for concurrent pulls of the same files
2023-08-09 11:31:54 -04:00
Bruce MacDonald
09d8bf6730
fix build errors
2023-08-09 10:45:57 -04:00
Bruce MacDonald
7a5f3616fd
embed text document in modelfile
2023-08-09 10:26:19 -04:00
Jeffrey Morgan
cff002b824
use content type application/x-ndjson
for streaming responses
2023-08-08 21:38:10 -07:00
Jeffrey Morgan
55cf5021f0
update langchain example to include python
2023-08-08 21:03:10 -07:00
Jeffrey Morgan
f58caa5ab5
update README.md
2023-08-08 15:50:23 -07:00
Jeffrey Morgan
82df473ec9
use note syntax in README.md
2023-08-08 15:49:50 -07:00
Jeffrey Morgan
e184c1d035
Link to api.md
in README.md
2023-08-08 15:48:47 -07:00
Jeffrey Morgan
371d4e5df3
docs: fix invalid json in api.md
2023-08-08 15:46:05 -07:00
Jeffrey Morgan
1f78e409b4
docs: format with prettier
2023-08-08 15:41:48 -07:00
Jeffrey Morgan
34a88cd776
docs: update api.md
formatting
2023-08-08 15:41:19 -07:00
Bruce MacDonald
1bee2347be
pr feedback
...
- defer closing llm on embedding
- do not override licenses
- remove debugging print line
- reformat model file docs
2023-08-08 17:01:37 -04:00
Jeffrey Morgan
a027a7dd65
add 0.0.0.0
as an allowed origin by default
...
Fixes #282
2023-08-08 13:39:50 -07:00
Jeffrey Morgan
22986ccb38
add llama2:70b
to the model library list
2023-08-08 13:08:05 -07:00
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