baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

api.md cleanup & formatting

Browse source
This commit is contained in:
Jeffrey Morgan 2023-12-27 14:32:35 -05:00
parent 55978c1dc9
commit 2a2fa3c329
1 changed files with 35 additions and 37 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

62
docs/api.md
View file

@ -27,7 +27,6 @@ All durations are returned in nanoseconds.
Certain endpoints stream responses as JSON objects and can optional return non-streamed responses.
## Generate a completion
```shell
@ -104,12 +103,12 @@ To calculate how fast the response is generated in tokens per second (token/s),
"response": "",
"done": true,
"context": [1, 2, 3],
"total_duration":10706818083,
"load_duration":6338219291,
"prompt_eval_count":26,
"prompt_eval_duration":130079000,
"eval_count":259,
"eval_duration":4232710000
"total_duration": 10706818083,
"load_duration": 6338219291,
"prompt_eval_count": 26,
"prompt_eval_duration": 130079000,
"eval_count": 259,
"eval_duration": 4232710000
}
```
@ -235,6 +234,7 @@ curl http://localhost:11434/api/generate -d '{
#### Request (Raw Mode)
In some cases, you may wish to bypass the templating system and provide a full prompt. In this case, you can use the `raw` parameter to disable templating. Also note that raw mode will not return a context.
##### Request
```shell
@ -306,8 +306,7 @@ curl http://localhost:11434/api/generate -d '{
"embedding_only": false,
"rope_frequency_base": 1.1,
"rope_frequency_scale": 0.8,
"num_thread": 8,
"cache": true
"num_thread": 8
}
}'
```
@ -348,10 +347,10 @@ A single JSON object is returned:
```json
{
"model":"llama2",
"created_at":"2023-12-18T19:52:07.071755Z",
"response":"",
"done":true
"model": "llama2",
"created_at": "2023-12-18T19:52:07.071755Z",
"response": "",
"done": true
}
```
@ -425,12 +424,12 @@ Final response:
"model": "llama2",
"created_at": "2023-08-04T19:22:45.499127Z",
"done": true,
"total_duration":4883583458,
"load_duration":1334875,
"prompt_eval_count":26,
"prompt_eval_duration":342546000,
"eval_count":282,
"eval_duration":4535599000
"total_duration": 4883583458,
"load_duration": 1334875,
"prompt_eval_count": 26,
"prompt_eval_duration": 342546000,
"eval_count": 282,
"eval_duration": 4535599000
}
```
@ -520,12 +519,12 @@ Final response:
"model": "llama2",
"created_at": "2023-08-04T19:22:45.499127Z",
"done": true,
"total_duration":8113331500,
"load_duration":6396458,
"prompt_eval_count":61,
"prompt_eval_duration":398801000,
"eval_count":468,
"eval_duration":7701267000
"total_duration": 8113331500,
"load_duration": 6396458,
"prompt_eval_count": 61,
"prompt_eval_duration": 398801000,
"eval_count": 468,
"eval_duration": 7701267000
}
```
@ -560,12 +559,12 @@ curl http://localhost:11434/api/chat -d '{
"images": null
},
"done": true,
"total_duration":1668506709,
"load_duration":1986209,
"prompt_eval_count":26,
"prompt_eval_duration":359682000,
"eval_count":83,
"eval_duration":1303285000
"total_duration": 1668506709,
"load_duration": 1986209,
"prompt_eval_count": 26,
"prompt_eval_duration": 359682000,
"eval_count": 83,
"eval_duration": 1303285000
}
```
@ -625,7 +624,6 @@ HEAD /api/blobs/:digest
Ensures that the file blob used for a FROM or ADAPTER field exists on the server. This is checking your Ollama server and not Ollama.ai.
#### Query Parameters
- `digest`: the SHA256 digest of the blob