Skip to content

Commit 8748447

Browse files
committed
Added tools to what is shinkai + edited ollama models
1 parent 8fa2090 commit 8748447

File tree

12 files changed

+88
-53
lines changed

12 files changed

+88
-53
lines changed

.DS_Store

0 Bytes
Binary file not shown.

advanced/baml.mdx

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3,5 +3,6 @@ title: 'BAML'
33
description: 'Using BAML to create Workflows'
44
---
55

6+
BAML is a domain-specific-language to write and test LLM functions.
67

78
In BAML, Prompts are functions

advanced/model-install.mdx

Lines changed: 7 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -34,12 +34,6 @@ There are several model options available to choose from: **OpenAI, Together AI,
3434
</CardGroup>
3535

3636
<CardGroup cols={3}>
37-
<Card
38-
title="Ollama"
39-
icon="robot"
40-
>
41-
Install any model from Ollama
42-
</Card>
4337
<Card
4438
title="Gemini"
4539
icon="robot"
@@ -54,5 +48,12 @@ There are several model options available to choose from: **OpenAI, Together AI,
5448
>
5549
Install Groq AI models in two simple steps
5650
</Card>
51+
<Card
52+
title="Ollama"
53+
icon="robot"
54+
href="/advanced/models/ollama"
55+
>
56+
Install other Ollama models in Shinkai
57+
</Card>
5758

5859
</CardGroup>

advanced/models/ollama.mdx

Lines changed: 58 additions & 45 deletions
Original file line numberDiff line numberDiff line change
@@ -6,59 +6,72 @@ description: 'Learn how to install Ollama models in Shinkai'
66
**Ollama** is an innovative Al platform designed to democratize access to large language models (LLMs) by allowing users to run these models locally on their machines.
77
This capability enhances privacy and control over data, as it mitigates concerns associated with cloud-based solutions.
88

9-
<Note>Note that all AI models in Shinkai are powered by Ollama. Before installing Ollama models manually, check the available models list for quick installation.</Note>
10-
<Frame>
11-
<img src="/images/ollama-models.jpg" style={{ borderRadius: '0.5rem' }}/>
12-
</Frame>
13-
14-
15-
`ollama ls`to list models installed
16-
`ollama pull <model>`to install models
17-
18-
19-
20-
219

2210
## Step-by-step installation guide
2311

2412
<Steps>
25-
<Step title="Download Ollama in your device">
26-
Go to [Ollama](https://ollama.com/) > Create your account > Download Ollama to your device > Install it.
27-
28-
</Step>
29-
<Step title="Check if the model is available for quick installation">
30-
In Ollama's website, open your **user's dropdown menu** in the upper-right corner > Click [Settings](https://ollama.com/settings/keys) > Select `Ollama Keys`.
31-
32-
Click the `Add Ollama Public Key` button > Generate your key.
33-
34-
<Tip>If you have a password app, like 1Password, it can generate the key automatically for you and save it to your keychain.</Tip>
35-
36-
![Add key to Ollama](/images/ollama-key.jpg)
37-
13+
<Step title="Check if model is available for quick installation">
14+
<Note>Note that all AI models in Shinkai are powered by Ollama. Before installing Ollama models manually, check the available models list for quick installation.</Note>
15+
<Frame>
16+
<img src="/images/ollama-models.jpg" style={{ borderRadius: '0.5rem' }}/>
17+
</Frame>
18+
19+
You can also check in your terminal the installed models in your device:
20+
21+
```Bash
22+
$ ollama ls
23+
NAME ID SIZE MODIFIED
24+
bespoke-minicheck:7b 66607904c165 4.7 GB 4 hours ago
25+
aya:8b 7ef8c4942023 4.8 GB 4 hours ago
26+
llama3.1:8b-instruct-q4_1 e129e608a752 5.1 GB 3 days ago
27+
snowflake-arctic-embed:xs bf75350e1752 45 MB 3 days ago
28+
```
29+
<Tip>If the model cannot be found in the quick installation list, proceed to step 2. </Tip>
3830
</Step>
39-
<Step title="Run the model you want to import">
40-
Browse the models' library in Ollama > Select the one you'd like to use in Shinkai > Choose the [parameters](/advanced/custom-ai) of the model (*i.e., 2b, 8b, etc.*)
41-
42-
![run ollama models](/images/ollama-run.jpg)
31+
<Step title="Pull new model from Ollama">
32+
Go to Ollama, and browse the model you want to install.
33+
Copy the code `ollama run <model>` and paste it in your terminal.
34+
35+
For example:
36+
```Bash
37+
$ ollama run bespoke-minicheck
38+
pulling manifest
39+
pulling 78b0a71988a5... 100% ▕████████████████████████████▏ 4.7 GB
40+
pulling 016aea4b585f... 100% ▕████████████████████████████▏ 340 B
41+
pulling 60ed67c565f8... 100% ▕████████████████████████████▏ 506 B
42+
pulling 7a3775deddf8... 100% ▕████████████████████████████▏ 50 B
43+
pulling a870cda2bff0... 100% ▕████████████████████████████▏ 495 B
44+
verifying sha256 digest
45+
writing manifest
46+
success
47+
48+
```
49+
Check that the model is now installed in your device:
50+
51+
```Bash
52+
$ ollama ls
53+
NAME ID SIZE MODIFIED
54+
bespoke-minicheck:latest 66607904c165 4.7 GB 2 minutes ago
55+
paraphrase-multilingual:latest ba13c2e06707 562 MB 11 minutes ago
56+
bespoke-minicheck:7b 66607904c165 4.7 GB 5 hours ago
57+
aya:8b 7ef8c4942023 4.8 GB 5 hours ago
58+
llama3.1:8b-instruct-q4_1 e129e608a752 5.1 GB 3 days ago
59+
snowflake-arctic-embed:xs bf75350e1752 45 MB 3 days ago
60+
61+
```
4362

44-
Copy the command `ollama run <model>` > Open your Terminal and run it.
45-
46-
It should look something like this:
47-
![Terminal](/images/terminal.jpg)
4863
</Step>
49-
<Step title="Add the model into Shinkai">
50-
- Open Shinkai > Go to `AIs` > `+ Add AI` > `+ Manually Add AI`
51-
1. Select **Ollama** in Model Provider
52-
2. Choose a model from the list or select 'Custom model' if it does not appear.
53-
3. Give your AI a name.
54-
<Note>This field only accepts alphanumeric characters and underscores</Note>
55-
4. Add the **Ollama Key** that you generated in step 2.
56-
![add ollama model](/images/add-ollama.jpg)
64+
<Step title="Add model to Shinkai">
65+
Open Shinkai > Go to `AIs` > `+ Add AI` > `+ Manually Add AI`
66+
- 1. Select **Ollama** in Model Provider.
67+
- 2. Select the **Model Type** you just pulled in step 2.
68+
- (Optional) You can edit the **AI Name** --> This is how it will be displayed in your Chats view.
69+
<Note>This field only accepts alphanumeric characters and underscores. </Note>
70+
- 3. You DO NOT need an API key, as Ollama runs locally on your device.
71+
72+
![Install Ollama Model](/images/ollama-installed.jpg)
5773
</Step>
74+
5875
</Steps>
5976

6077
Congratulations! You have now installed a new Ollama model in your Shinkai Desktop App!
61-
62-
<Frame>
63-
<img src="/images/ollama-installed.jpg" style={{ borderRadius: '0.5rem' }}/>
64-
</Frame>

images/add-ollama.jpg

-214 KB
Binary file not shown.

images/ollama-installed.jpg

-1.2 MB
Loading

images/ollama-key.jpg

-35.2 KB
Binary file not shown.

images/ollama-run.jpg

-279 KB
Binary file not shown.

images/terminal.jpg

-805 KB
Binary file not shown.

mint.json

Lines changed: 2 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -76,7 +76,8 @@
7676
"advanced/models/gpt",
7777
"advanced/models/openrouter",
7878
"advanced/models/gemini",
79-
"advanced/models/groq"
79+
"advanced/models/groq",
80+
"advanced/models/ollama"
8081
]
8182
},
8283
"advanced/visor",

0 commit comments

Comments
 (0)