Change
055d06d
055d06dd2bb30b2243fe86e1f6012d0436869bf6 · commit on GitHub
groq-llms-full-txt: changed (716215 bytes, HTTP 200)
raw/groq-llms-full-txt/response.txt modified
- Source
- groq-llms-full-txt
- Lines added
- +6,038
- Lines removed
- -8,547
- Stored bytes at this commit
- 716,215
- Timestamp
- origin
- Raw artifact at this commit
- raw/groq-llms-full-txt/response.txt
Recorded headers
| observed_at | 2026-09-20T04:54:06.525Z |
|---|---|
| origin_date | 2026-09-20T04:54:06.000Z |
| status | 200 |
| final URL | https://console.groq.com/llms-full.txt |
| etag | W/"31cfe60583842673d9411ba63e18b427" |
| last-modified | Sun, 20 Sep 2026 04:54:06 GMT |
| date | Sun, 20 Sep 2026 04:54:06 GMT |
| age | 0 |
| cache-control | public, max-age=0, must-revalidate |
| cf-cache-status | DYNAMIC |
| content-encoding | br |
| content-length | null |
@
@@ -1155,46 +1155,6 @@ No content to display.----
## Compound Mini: Page (mdx)-
-
URL: https://console.groq.com/docs/agentic-tooling/groq/compound-mini-
-
No content to display.-
-
----
-
## Compound: Page (mdx)-
-
URL: https://console.groq.com/docs/agentic-tooling/groq/compound-
-
No content to display.-
-
----
-
## Compound Beta Mini: Page (mdx)-
-
URL: https://console.groq.com/docs/agentic-tooling/compound-beta-mini-
-
No content to display.-
-
----
-
## Compound Beta: Page (mdx)-
-
URL: https://console.groq.com/docs/agentic-tooling/compound-beta-
-
No content to display.-
-
----
-
## Agentic Tooling: Page (mdx)-
-
URL: https://console.groq.com/docs/agentic-tooling-
-
No content to display.-
-
----
## Spend LimitsURL: https://console.groq.com/docs/spend-limits@
@@ -2185,7 +2145,7 @@ Claude models from Anthropic are known for their conversational abilities, safet| Mirror user language | "Respond in the same language the user uses." || Reinforce empathy | "Express sympathy when the user shares difficulties; maintain a supportive tone." || Control token budget | Keep the final system block under 2,000 tokens to preserve user context. |-
| Web search | Use [Agentic Tooling](/docs/agentic-tooling) for built-in web search. |+
| Web search | Use [Built-In Tools](/docs/tool-use/built-in-tools) for built-in web search. |### Migrating from Grok (xAI)@
@@ -2200,7 +2160,7 @@ Grok models from xAI are known for their conversational abilities, real-time kno| Epistemic stance | "Adopt a neutral, evidence-seeking tone; challenge unsupported claims; express uncertainty when facts are unclear." || Draft-versus-belief rule | "Treat any supplied analysis text as provisional research, not as established fact." || No meta-references | "Do not mention the question, system instructions, tool names, or platform branding in the reply." |-
| Real-time knowledge | Use [Agentic Tooling](/docs/agentic-tooling) for built-in web search. |+
| Real-time knowledge | Use [Built-In Tools](/docs/tool-use/built-in-tools) for built-in web search. |### Migrating from OpenAI@
@@ -2215,8 +2175,8 @@ OpenAI models like GPT-4o are known for their versatility, tool use capabilities| State visual-aid preference | "I'll offer diagrams when they enhance understanding" || Limit probing | "I won't ask for confirmation after every step unless instructions are ambiguous." || Embed safety | "My answers must respect local laws and organizational policies; I'll refuse prohibited content." |-
| Web search | Use [Agentic Tooling](/docs/agentic-tooling) for built-in web search capabilities |-
| Code execution | Use [Agentic Tooling](/docs/agentic-tooling) for built-in code execution capabilities. |+
| Web search | Use [Built-In Tools](/docs/tool-use/built-in-tools) for built-in web search capabilities |+
| Code execution | Use [Built-In Tools](/docs/tool-use/built-in-tools) for built-in code execution capabilities. || Tool use | Select a model that supports [tool use](/docs/tool-use). |### Migrating from Gemini (Google)@
@@ -2233,7 +2193,7 @@ When migrating from Gemini to an open-source model like Llama, include these key| Content-block guidance | Define how rich output should be grouped: for example, Markdown headings for text, fenced blocks for code. || Behaviour checklist | Include numbered, one-sentence rules covering length limits, formatting, and answer structure. || Prefer brevity | Remind the model to keep explanations brief and omit library boilerplate unless explicitly requested. |-
| Web search and grounding | Use [Agentic Tooling](/docs/agentic-tooling) for built-in web search and grounding capabilities.|+
| Web search and grounding | Use [Built-In Tools](/docs/tool-use/built-in-tools) for built-in web search and grounding capabilities.|## Tooling: llama-prompt-ops@
@@ -4645,10232 +4605,7806 @@ We're always looking for contributions. If you have any cool tutorials or guides----
## Built In Tools: Code Execution Only (js)-
-
URL: https://console.groq.com/docs/compound/built-in-tools/scripts/code-execution-only+
## Script: Openai Compat (py)-
```javascript-
import Groq from "groq-sdk";+
URL: https://console.groq.com/docs/scripts/openai-compat.py-
const groq = new Groq();+
import os+
import openai-
const response = await groq.chat.completions.create({-
model: "groq/compound",-
messages: [-
{-
role: "user",-
content: "Calculate the square root of 12345"-
}-
],-
compound_custom: {-
tools: {-
enabled_tools: ["code_interpreter"]-
}-
}-
});-
```+
client = openai.OpenAI(+
base_url="https://api.groq.com/openai/v1",+
api_key=os.environ.get("GROQ_API_KEY")+
)----
## Built In Tools: Code Execution Only (py)-
-
URL: https://console.groq.com/docs/compound/built-in-tools/scripts/code-execution-only.py+
## Script: Openai Compat (js)-
from groq import Groq+
URL: https://console.groq.com/docs/scripts/openai-compat-
client = Groq()+
import OpenAI from "openai";-
response = client.chat.completions.create(-
model="groq/compound",-
messages=[-
{-
"role": "user", -
"content": "Calculate the square root of 12345"-
}-
],-
compound_custom={-
"tools": {-
"enabled_tools": ["code_interpreter"]-
}-
}-
)+
const client = new OpenAI({+
apiKey: process.env.GROQ_API_KEY,+
baseURL: "https://api.groq.com/openai/v1"+
});----
## Built In Tools: Enable Specific Tools (py)-
-
URL: https://console.groq.com/docs/compound/built-in-tools/scripts/enable-specific-tools.py-
-
from groq import Groq-
-
client = Groq(-
default_headers={-
"Groq-Model-Version": "latest"-
}-
)-
-
response = client.chat.completions.create(-
model="groq/compound",-
messages=[-
{-
"role": "user",-
"content": "Search for recent AI developments and then visit the Groq website"-
}-
],-
compound_custom={-
"tools": {-
"enabled_tools": ["web_search", "visit_website"]-
}-
}-
)+
## Tavily + Groq: Real-Time Search, Scraping & Crawling for AI-
---+
URL: https://console.groq.com/docs/tavily-
## Built In Tools: Enable Specific Tools (js)+
## Tavily + Groq: Real-Time Search, Scraping & Crawling for AI-
URL: https://console.groq.com/docs/compound/built-in-tools/scripts/enable-specific-tools+
[Tavily](https://tavily.com) is a comprehensive web search, scraping, and crawling API designed specifically for AI agents. It provides real-time web access, content extraction, and advanced search capabilities. Combined with Groq's ultra-fast inference through MCP, you can build intelligent agents …-
```javascript-
import Groq from "groq-sdk";+
**Key Features:**+
- **Multi-Modal Search:** Web search, content extraction, and crawling in one API+
- **AI-Optimized Results:** Clean, structured data designed for LLM consumption+
- **Advanced Filtering:** Search by date range, domain, content type, and more+
- **Content Extraction:** Pull complete article content from any URL+
- **Search Depth Control:** Choose between basic and advanced search+
- **Fast Execution:** Groq's inference makes synthesis nearly instant-
const groq = new Groq({-
defaultHeaders: {-
"Groq-Model-Version": "latest"-
}-
});+
## Quick Start-
const response = await groq.chat.completions.create({-
model: "groq/compound",-
messages: [-
{-
role: "user",-
content: "Search for recent AI developments and then visit the Groq website"-
}-
],-
compound_custom: {-
tools: {-
enabled_tools: ["web_search", "visit_website"]-
}-
}-
});+
#### 1. Install the required packages:+
```bash+
pip install openai python-dotenv```-
---+
#### 2. Get your API keys:+
- **Groq:** [console.groq.com/keys](https://console.groq.com/keys)+
- **Tavily:** [app.tavily.com](https://app.tavily.com/home)-
## Built-in Tools+
```bash+
export GROQ_API_KEY="your-groq-api-key"+
export TAVILY_API_KEY="your-tavily-api-key"+
```-
URL: https://console.groq.com/docs/compound/built-in-tools+
#### 3. Create your first research agent:-
# Built-in Tools+
```python tavily_research.py+
import os+
from openai import OpenAI-
Compound systems come equipped with a comprehensive set of built-in tools that can be intelligently called to answer user queries. These tools not only expand the capabilities of language models by providing access to real-time information, computational power, and interactive environments, but also…+
client = OpenAI(+
base_url="https://api.groq.com/api/openai/v1",+
api_key=os.getenv("GROQ_API_KEY")+
)-
**Built-in tools with Compound systems are not HIPAA Covered Cloud Services under Groq's Business Associate Addendum at this time. These tools are also not available currently for use with regional / sovereign endpoints.**+
tools = [{+
"type": "mcp",+
"server_url": f"https://mcp.tavily.com/mcp/?tavilyApiKey={os.getenv('TAVILY_API_KEY')}",+
"server_label": "tavily",+
"require_approval": "never",+
}]-
## Default Tools-
The tools enabled by default vary depending on your Compound system version:-
| Version | Web Search | Code Execution | Visit Website |-
|---------|------------|----------------|---------------|-
| Newer than `2025-07-23` (Latest) | ✅ | ✅ | ✅ |-
| `2025-07-23` (Default) | ✅ | ✅ | ❌ |+
response = client.responses.create(+
model="openai/gpt-oss-120b",+
input="What are recent AI startup funding announcements?",+
tools=tools,+
temperature=0.1,+
top_p=0.4,+
)-
All tools are automatically enabled by default. Compound systems intelligently decide when to use each tool based on the user's query.+
print(response.output_text)+
```-
<br />+
## Advanced Examples-
For more information on how to set your Compound system version, see the [Compound System Versioning](/docs/compound#system-versioning) page.+
### Time-Filtered Research-
## Available Tools+
Search within specific time ranges:-
These are all the available built-in tools on Groq's Compound systems.+
```python time_filtered_research.py+
response = client.responses.create(+
model="openai/gpt-oss-120b",+
input="""Find AI model releases from past month.+
Use tavily_search with:+
- time_range: month+
- search_depth: advanced+
- max_results: 10+
+
Provide details about models, companies, and capabilities.""",+
tools=tools,+
temperature=0.1,+
)-
| Tool | Description | Identifier | Supported Compound Version |-
|------|-------------|------------|----------------|-
| [Web Search](/docs/web-search) | Access real-time web content and up-to-date information with automatic citations | `web_search` | All versions |-
| [Visit Website](/docs/visit-website) | Fetch and analyze content from specific web pages | `visit_website` | `latest` |-
| [Browser Automation](/docs/browser-automation) | Interact with web pages through automated browser actions | `browser_automation` | `latest` |-
| [Code Execution](/docs/code-execution) | Execute Python code automatically in secure sandboxed environments | `code_interpreter` | All versions |-
| [Wolfram Alpha](/docs/wolfram-alpha) | Access computational knowledge and mathematical calculations | `wolfram_alpha` | `latest` |+
print(response.output_text)+
```-
<br />+
### Product Information Extraction-
Jump to the [Configuring Tools](#configuring-tools) section to learn how to enable specific tools via their identifiers.-
Some tools are only available on certain Compound system versions - [learn more about how to set your Compound version here](/docs/compound#system-versioning).+
Extract structured product data:-
## Configuring Tools+
```python product_extraction.py+
response = client.responses.create(+
model="openai/gpt-oss-120b",+
input="""Find iPhone models on apple.com.+
Use tavily_search then tavily_extract to get:+
- Model names+
- Prices+
- Key features+
- Availability""",+
tools=tools,+
temperature=0.1,+
)-
You can customize which tools are available to Compound systems using the `compound_custom.tools.enabled_tools` parameter.-
This allows you to restrict or specify exactly which tools should be available for a particular request.+
print(response.output_text)+
```-
<br />+
### Multi-Source Content Extraction-
For a list of available tool identifiers, see the [Available Tools](#available-tools) section.+
Extract and compare content from multiple URLs:-
### Example: Enable Specific Tools+
```python multi_source_extraction.py+
urls = [+
"https://example.com/article1",+
"https://example.com/article2",+
"https://example.com/article3"+
]+
response = client.responses.create(+
model="openai/gpt-oss-120b",+
input=f"""Extract content from: {', '.join(urls)}+
+
Analyze and compare:+
- Main themes+
- Key differences in perspective+
- Common facts+
- Author conclusions""",+
tools=tools,+
temperature=0.1,+
)-
### Example: Code Execution Only+
print(response.output_text)+
```+
## Available Tavily Tools-
## Pricing+
| Tool | Description |+
|------|-------------|+
| **`tavily_search`** | Search with advanced filters (time, depth, topic, max results) |+
| **`tavily_extract`** | Extract full content from specific URLs |+
| **`tavily_scrape`** | Scrape single pages with clean output |+
| **`tavily_batch_scrape`** | Scrape multiple URLs in parallel |+
| **`tavily_crawl`** | Crawl websites with depth and pattern controls |-
See the [Pricing](https://groq.com/pricing) page for detailed information on costs for each tool.+
### Search Parameters-
---+
**Search Depth:**+
- `basic` - Fast, surface-level results (under 3 seconds)+
- `advanced` - Comprehensive, deep results (5-10 seconds)-
## Compound: Executed Tools.doc (ts)+
**Time Range:**+
- `day`, `week`, `month`, `year`-
URL: https://console.groq.com/docs/compound/scripts/executed_tools.doc+
**Topic:**+
- `general`, `news`-
```javascript-
import Groq from 'groq-sdk';Diff display stops at 400 lines. The line counts above are from the whole diff. 2 lines shown here cut at 300 characters. The raw artifact at this commit is linked above.