Skip to content

Commit 85cdca2

Browse files
waleedlatif1waleedlatif1
authored
v0.3.21: gpt-5, copilot files, configurable rate limits, fix deployed state
2 parents 9f2ff7e + 75963eb commit 85cdca2

File tree

123 files changed

+7358
-852
lines changed

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

123 files changed

+7358
-852
lines changed

‎.github/CONTRIBUTING.md‎

Lines changed: 7 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -164,10 +164,14 @@ Access the application at [http://localhost:3000/](http://localhost:3000/)
164164

165165
To use local models with Sim:
166166

167-
1. Pull models using our helper script:
167+
1. Install Ollama and pull models:
168168

169169
```bash
170-
./apps/sim/scripts/ollama_docker.sh pull <model_name>
170+
# Install Ollama (if not already installed)
171+
curl -fsSL https://ollama.ai/install.sh | sh
172+
173+
# Pull a model (e.g., gemma3:4b)
174+
ollama pull gemma3:4b
171175
```
172176

173177
2. Start Sim with local model support:
@@ -533,7 +537,7 @@ This visibility system ensures clean user interfaces while maintaining full flex
533537
534538
### Guidelines & Best Practices
535539
536-
- **Code Style:** Follow the project's ESLint and Prettier configurations. Use meaningful variable names and small, focused functions.
540+
- **Code Style:** Follow the project's Biome configurations. Use meaningful variable names and small, focused functions.
537541
- **Documentation:** Clearly document the purpose, inputs, outputs, and any special behavior for your block/tool.
538542
- **Error Handling:** Implement robust error handling and provide user-friendly error messages.
539543
- **Parameter Visibility:** Always specify the appropriate visibility level for each parameter to ensure proper UI behavior and LLM integration.

‎README.md‎

Lines changed: 9 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -59,27 +59,21 @@ docker compose -f docker-compose.prod.yml up -d
5959

6060
Access the application at [http://localhost:3000/](http://localhost:3000/)
6161

62-
#### Using Local Models
62+
#### Using Local Models with Ollama
6363

64-
To use local models with Sim:
65-
66-
1. Pull models using our helper script:
64+
Run Sim with local AI models using [Ollama](https://ollama.ai) - no external APIs required:
6765

6866
```bash
69-
./apps/sim/scripts/ollama_docker.sh pull <model_name>
70-
```
67+
# Start with GPU support (automatically downloads gemma3:4b model)
68+
docker compose -f docker-compose.ollama.yml --profile setup up -d
7169

72-
2. Start Sim with local model support:
70+
# For CPU-only systems:
71+
docker compose -f docker-compose.ollama.yml --profile cpu --profile setup up -d
72+
```
7373

74+
Wait for the model to download, then visit [http://localhost:3000](http://localhost:3000). Add more models with:
7475
```bash
75-
# With NVIDIA GPU support
76-
docker compose --profile local-gpu -f docker-compose.ollama.yml up -d
77-
78-
# Without GPU (CPU only)
79-
docker compose --profile local-cpu -f docker-compose.ollama.yml up -d
80-
81-
# If hosting on a server, update the environment variables in the docker-compose.prod.yml file to include the server's public IP then start again (OLLAMA_URL to i.e. http://1.1.1.1:11434)
82-
docker compose -f docker-compose.prod.yml up -d
76+
docker compose -f docker-compose.ollama.yml exec ollama ollama pull llama3.1:8b
8377
```
8478

8579
### Option 3: Dev Containers

‎apps/docs/content/docs/blocks/agent.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -61,7 +61,7 @@ The user prompt represents the primary input data for inference processing. This
6161

6262
The Agent block supports multiple LLM providers through a unified inference interface. Available models include:
6363

64-
**OpenAI Models**: GPT-4o, o1, o3, o4-mini, gpt-4.1 (API-based inference)
64+
**OpenAI Models**: GPT-5, GPT-4o, o1, o3, o4-mini, gpt-4.1 (API-based inference)
6565
**Anthropic Models**: Claude 3.7 Sonnet (API-based inference)
6666
**Google Models**: Gemini 2.5 Pro, Gemini 2.0 Flash (API-based inference)
6767
**Alternative Providers**: Groq, Cerebras, xAI, DeepSeek (API-based inference)

‎apps/docs/content/docs/connections/data-structure.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -84,7 +84,7 @@ Different block types produce different output structures. Here's what you can e
8484
```json
8585
{
8686
"content": "Evaluation summary",
87-
"model": "gpt-4o",
87+
"model": "gpt-5",
8888
"tokens": {
8989
"prompt": 120,
9090
"completion": 85,

‎apps/docs/content/docs/tools/file.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -50,7 +50,7 @@ The File Parser tool is particularly useful for scenarios where your agents need
5050

5151
## Usage Instructions
5252

53-
Upload and extract contents from structured file formats including PDFs, CSV spreadsheets, and Word documents (DOCX). Upload files directly. Specialized parsers extract text and metadata from each format. You can upload multiple files at once and access them individually or as a combined document.
53+
Upload and extract contents from structured file formats including PDFs, CSV spreadsheets, and Word documents (DOCX). You can either provide a URL to a file or upload files directly. Specialized parsers extract text and metadata from each format. You can upload multiple files at once and access them individually or as a combined document.
5454

5555

5656

‎apps/docs/content/docs/tools/hunter.mdx‎

Lines changed: 1 addition & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -38,6 +38,7 @@ With Hunter.io, you can:
3838
In Sim, the Hunter.io integration enables your agents to programmatically search for and verify email addresses, discover companies, and enrich contact data using Hunter.io’s API. This allows you to automate lead generation, contact enrichment, and email verification directly within your workflows. Your agents can leverage Hunter.io’s tools to streamline outreach, keep your CRM up-to-date, and power intelligent automation scenarios for sales, recruiting, and more.
3939
{/* MANUAL-CONTENT-END */}
4040

41+
4142
## Usage Instructions
4243

4344
Search for email addresses, verify their deliverability, discover companies, and enrich contact data using Hunter.io's powerful email finding capabilities.

‎apps/docs/content/docs/tools/knowledge.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -64,7 +64,7 @@ Search for similar content in a knowledge base using vector similarity
6464
| Parameter | Type | Required | Description |
6565
| --------- | ---- | -------- | ----------- |
6666
| `knowledgeBaseId` | string | Yes | ID of the knowledge base to search in |
67-
| `query` | string | Yes | Search query text |
67+
| `query` | string | No | Search query text \(optional when using tag filters\) |
6868
| `topK` | number | No | Number of most similar results to return \(1-100\) |
6969
| `tagFilters` | any | No | Array of tag filters with tagName and tagValue properties |
7070

‎apps/docs/content/docs/tools/meta.json‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -29,9 +29,11 @@
2929
"mem0",
3030
"memory",
3131
"microsoft_excel",
32+
"microsoft_planner",
3233
"microsoft_teams",
3334
"mistral_parse",
3435
"notion",
36+
"onedrive",
3537
"openai",
3638
"outlook",
3739
"perplexity",
@@ -41,6 +43,7 @@
4143
"s3",
4244
"schedule",
4345
"serper",
46+
"sharepoint",
4447
"slack",
4548
"stagehand",
4649
"stagehand_agent",

‎apps/docs/content/docs/tools/microsoft_planner.mdx‎

Lines changed: 178 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,178 @@
1+
---
2+
title: Microsoft Planner
3+
description: Read and create tasks in Microsoft Planner
4+
---
5+
6+
import { BlockInfoCard } from "@/components/ui/block-info-card"
7+
8+
<BlockInfoCard
9+
type="microsoft_planner"
10+
color="#E0E0E0"
11+
icon={true}
12+
iconSvg={`<svg className="block-icon" fill='currentColor' viewBox='-1 -1 27 27' xmlns='http://www.w3.org/2000/svg'>
13+
<defs>
14+
<linearGradient
15+
id='paint0_linear_3984_11038'
16+
x1='6.38724'
17+
y1='3.74167'
18+
x2='2.15779'
19+
y2='12.777'
20+
gradientUnits='userSpaceOnUse'
21+
>
22+
<stop stopColor='#8752E0' />
23+
<stop offset='1' stopColor='#541278' />
24+
</linearGradient>
25+
<linearGradient
26+
id='paint1_linear_3984_11038'
27+
x1='8.38032'
28+
y1='11.0696'
29+
x2='4.94062'
30+
y2='7.69244'
31+
gradientUnits='userSpaceOnUse'
32+
>
33+
<stop offset='0.12172' stopColor='#3D0D59' />
34+
<stop offset='1' stopColor='#7034B0' stopOpacity='0' />
35+
</linearGradient>
36+
<linearGradient
37+
id='paint2_linear_3984_11038'
38+
x1='18.3701'
39+
y1='-3.33385e-05'
40+
x2='9.85717'
41+
y2='20.4192'
42+
gradientUnits='userSpaceOnUse'
43+
>
44+
<stop stopColor='#DB45E0' />
45+
<stop offset='1' stopColor='#6C0F71' />
46+
</linearGradient>
47+
<linearGradient
48+
id='paint3_linear_3984_11038'
49+
x1='18.3701'
50+
y1='-3.33385e-05'
51+
x2='9.85717'
52+
y2='20.4192'
53+
gradientUnits='userSpaceOnUse'
54+
>
55+
<stop stopColor='#DB45E0' />
56+
<stop offset='0.677403' stopColor='#A829AE' />
57+
<stop offset='1' stopColor='#8F28B3' />
58+
</linearGradient>
59+
<linearGradient
60+
id='paint4_linear_3984_11038'
61+
x1='18.0002'
62+
y1='7.49958'
63+
x2='14.0004'
64+
y2='23.9988'
65+
gradientUnits='userSpaceOnUse'
66+
>
67+
<stop stopColor='#3DCBFF' />
68+
<stop offset='1' stopColor='#00479E' />
69+
</linearGradient>
70+
<linearGradient
71+
id='paint5_linear_3984_11038'
72+
x1='18.2164'
73+
y1='7.92626'
74+
x2='10.5237'
75+
y2='22.9363'
76+
gradientUnits='userSpaceOnUse'
77+
>
78+
<stop stopColor='#3DCBFF' />
79+
<stop offset='1' stopColor='#4A40D4' />
80+
</linearGradient>
81+
</defs>
82+
<path
83+
d='M8.25809 15.7412C7.22488 16.7744 5.54971 16.7744 4.5165 15.7412L0.774909 11.9996C-0.258303 10.9664 -0.258303 9.29129 0.774908 8.25809L4.5165 4.51655C5.54971 3.48335 7.22488 3.48335 8.25809 4.51655L11.9997 8.2581C13.0329 9.29129 13.0329 10.9664 11.9997 11.9996L8.25809 15.7412Z'
84+
fill='url(#paint0_linear_3984_11038)'
85+
/>
86+
<path
87+
d='M8.25809 15.7412C7.22488 16.7744 5.54971 16.7744 4.5165 15.7412L0.774909 11.9996C-0.258303 10.9664 -0.258303 9.29129 0.774908 8.25809L4.5165 4.51655C5.54971 3.48335 7.22488 3.48335 8.25809 4.51655L11.9997 8.2581C13.0329 9.29129 13.0329 10.9664 11.9997 11.9996L8.25809 15.7412Z'
88+
fill='url(#paint1_linear_3984_11038)'
89+
/>
90+
<path
91+
d='M0.774857 11.9999C1.80809 13.0331 3.48331 13.0331 4.51655 11.9999L15.7417 0.774926C16.7749 -0.258304 18.4501 -0.258309 19.4834 0.774914L23.225 4.51655C24.2583 5.54977 24.2583 7.22496 23.225 8.25819L11.9999 19.4832C10.9667 20.5164 9.29146 20.5164 8.25822 19.4832L0.774857 11.9999Z'
92+
fill='url(#paint2_linear_3984_11038)'
93+
/>
94+
<path
95+
d='M0.774857 11.9999C1.80809 13.0331 3.48331 13.0331 4.51655 11.9999L15.7417 0.774926C16.7749 -0.258304 18.4501 -0.258309 19.4834 0.774914L23.225 4.51655C24.2583 5.54977 24.2583 7.22496 23.225 8.25819L11.9999 19.4832C10.9667 20.5164 9.29146 20.5164 8.25822 19.4832L0.774857 11.9999Z'
96+
fill='url(#paint3_linear_3984_11038)'
97+
/>
98+
<path
99+
d='M4.51642 15.7413C5.54966 16.7746 7.22487 16.7746 8.25812 15.7413L15.7415 8.25803C16.7748 7.2248 18.45 7.2248 19.4832 8.25803L23.2249 11.9997C24.2582 13.0329 24.2582 14.7081 23.2249 15.7413L15.7415 23.2246C14.7083 24.2579 13.033 24.2579 11.9998 23.2246L4.51642 15.7413Z'
100+
fill='url(#paint4_linear_3984_11038)'
101+
/>
102+
<path
103+
d='M4.51642 15.7413C5.54966 16.7746 7.22487 16.7746 8.25812 15.7413L15.7415 8.25803C16.7748 7.2248 18.45 7.2248 19.4832 8.25803L23.2249 11.9997C24.2582 13.0329 24.2582 14.7081 23.2249 15.7413L15.7415 23.2246C14.7083 24.2579 13.033 24.2579 11.9998 23.2246L4.51642 15.7413Z'
104+
fill='url(#paint5_linear_3984_11038)'
105+
/>
106+
</svg>`}
107+
/>
108+
109+
{/* MANUAL-CONTENT-START:intro */}
110+
[Microsoft Planner](https://www.microsoft.com/en-us/microsoft-365/planner) is a task management tool that helps teams organize work visually using boards, tasks, and buckets. Integrated with Microsoft 365, it offers a simple, intuitive way to manage team projects, assign responsibilities, and track progress.
111+
112+
With Microsoft Planner, you can:
113+
114+
- **Create and manage tasks**: Add new tasks with due dates, priorities, and assigned users
115+
- **Organize with buckets**: Group tasks by phase, status, or category to reflect your team’s workflow
116+
- **Visualize project status**: Use boards, charts, and filters to monitor workload and track progress
117+
- **Stay integrated with Microsoft 365**: Seamlessly connect tasks with Teams, Outlook, and other Microsoft tools
118+
119+
In Sim, the Microsoft Planner integration allows your agents to programmatically create, read, and manage tasks as part of their workflows. Agents can generate new tasks based on incoming requests, retrieve task details to drive decisions, and track status across projects — all without human intervention. Whether you're building workflows for client onboarding, internal project tracking, or follow-up task generation, integrating Microsoft Planner with Sim gives your agents a structured way to coordinate work, automate task creation, and keep teams aligned.
120+
{/* MANUAL-CONTENT-END */}
121+
122+
123+
## Usage Instructions
124+
125+
Integrate Microsoft Planner functionality to manage tasks. Read all user tasks, tasks from specific plans, individual tasks, or create new tasks with various properties like title, description, due date, and assignees using OAuth authentication.
126+
127+
128+
129+
## Tools
130+
131+
### `microsoft_planner_read_task`
132+
133+
Read tasks from Microsoft Planner - get all user tasks or all tasks from a specific plan
134+
135+
#### Input
136+
137+
| Parameter | Type | Required | Description |
138+
| --------- | ---- | -------- | ----------- |
139+
| `accessToken` | string | Yes | The access token for the Microsoft Planner API |
140+
| `planId` | string | No | The ID of the plan to get tasks from \(if not provided, gets all user tasks\) |
141+
| `taskId` | string | No | The ID of the task to get |
142+
143+
#### Output
144+
145+
| Parameter | Type | Description |
146+
| --------- | ---- | ----------- |
147+
| `task` | json | The Microsoft Planner task object, including details such as id, title, description, status, due date, and assignees. |
148+
| `metadata` | json | Additional metadata about the operation, such as timestamps, request status, or other relevant information. |
149+
150+
### `microsoft_planner_create_task`
151+
152+
Create a new task in Microsoft Planner
153+
154+
#### Input
155+
156+
| Parameter | Type | Required | Description |
157+
| --------- | ---- | -------- | ----------- |
158+
| `accessToken` | string | Yes | The access token for the Microsoft Planner API |
159+
| `planId` | string | Yes | The ID of the plan where the task will be created |
160+
| `title` | string | Yes | The title of the task |
161+
| `description` | string | No | The description of the task |
162+
| `dueDateTime` | string | No | The due date and time for the task \(ISO 8601 format\) |
163+
| `assigneeUserId` | string | No | The user ID to assign the task to |
164+
| `bucketId` | string | No | The bucket ID to place the task in |
165+
166+
#### Output
167+
168+
| Parameter | Type | Description |
169+
| --------- | ---- | ----------- |
170+
| `task` | json | The Microsoft Planner task object, including details such as id, title, description, status, due date, and assignees. |
171+
| `metadata` | json | Additional metadata about the operation, such as timestamps, request status, or other relevant information. |
172+
173+
174+
175+
## Notes
176+
177+
- Category: `tools`
178+
- Type: `microsoft_planner`

‎apps/docs/content/docs/tools/mistral_parse.mdx‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -79,7 +79,7 @@ The Mistral Parse tool is particularly useful for scenarios where your agents ne
7979

8080
## Usage Instructions
8181

82-
Extract text and structure from PDF documents using Mistral's OCR API. Configure processing options and get the content in your preferred format. For URLs, they must be publicly accessible and point to a valid PDF file. Note: Google Drive, Dropbox, and other cloud storage links are not supported; use a direct download URL from a web server instead.
82+
Extract text and structure from PDF documents using Mistral's OCR API. Either enter a URL to a PDF document or upload a PDF file directly. Configure processing options and get the content in your preferred format. For URLs, they must be publicly accessible and point to a valid PDF file. Note: Google Drive, Dropbox, and other cloud storage links are not supported; use a direct download URL from a web server instead.
8383

8484

8585

0 commit comments

Comments
 (0)