### Go Image Generation Example

Source: https://docs.nexos.ai/openai-sdks/go-sdk

This Go code snippet demonstrates how to generate an image using the Nexos AI Go SDK. It uses the 'dall-e-3' model and a text prompt to create an image, returning its URL.

```Go
package main

import (
	"context"
	"fmt"
	"os"

	"github.com/joho/godotenv"
	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	err := godotenv.Load()
	if err != nil {
		panic(err)
	}
	apiKey := os.Getenv("API_KEY")
	apiUrl := os.Getenv("API_URL")
	client := openai.NewClient(
		option.WithBaseURL(apiUrl),
		option.WithAPIKey(apiKey),
	)
	response, err := client.Images.Generate(context.Background(), openai.ImageGenerateParams{
		Model:  "dall-e-3",
		Prompt: "three letters 'r' with strawberry texture",
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(response.Data[0].URL)
}
```

--------------------------------

### Go Chat Completion Example

Source: https://docs.nexos.ai/openai-sdks/go-sdk

This Go code snippet demonstrates how to perform a chat completion using the Nexos AI Go SDK. It requires API key and URL from environment variables and uses the 'gpt-3.5-turbo' model.

```Go
package main

import (
	"context"
	"fmt"
	"os"

	"github.com/joho/godotenv"
	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	err := godotenv.Load()
	if err != nil {
		panic(err)
	}
	apiKey := os.Getenv("API_KEY")
	apiUrl := os.Getenv("API_URL")
	client := openai.NewClient(
		option.WithBaseURL(apiUrl),
		option.WithAPIKey(apiKey),
	)
	response, err := client.Chat.Completions.New(context.Background(), openai.ChatCompletionNewParams{
		Model: "gpt-3.5-turbo",
		Messages: []openai.ChatCompletionMessageParamUnion{
			openai.UserMessage("how many letters 'r' in the word 'strawberry'"),
		},
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(response.Choices[0].Message.Content)
}
```

--------------------------------

### Go Audio Transcription Example

Source: https://docs.nexos.ai/openai-sdks/go-sdk

This Go code snippet demonstrates how to transcribe audio using the Nexos AI Go SDK. It takes an audio file ('sound.mp3') and uses the 'whisper-1' model to convert speech to text.

```Go
package main

import (
	"context"
	"fmt"
	"os"

	"github.com/joho/godotenv"
	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	err := godotenv.Load()
	if err != nil {
		panic(err)
	}
	apiKey := os.Getenv("API_KEY")
	apiUrl := os.Getenv("API_URL")
	client := openai.NewClient(
		option.WithBaseURL(apiUrl),
		option.WithAPIKey(apiKey),
	)
	file, err := os.Open("sound.mp3")
	if err != nil {
		panic(err)
	}
	defer file.Close()
	response, err := client.Audio.Transcriptions.New(context.Background(), openai.AudioTranscriptionNewParams{
		Model: "whisper-1",
		File: file,
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(response.Text)
}
```

--------------------------------

### Go Audio Generation Example

Source: https://docs.nexos.ai/openai-sdks/go-sdk

This Go code snippet shows how to generate audio using the Nexos AI Go SDK. It takes text input and converts it to speech using the 'tts-1' model, saving the output to 'generated.mp3'.

```Go
package main

import (
	"context"
	"io"
	"os"

	"github.com/joho/godotenv"
	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	err := godotenv.Load()
	if err != nil {
		panic(err)
	}
	apiKey := os.Getenv("API_KEY")
	apiUrl := os.Getenv("API_URL")
	client := openai.NewClient(
		option.WithBaseURL(apiUrl),
		option.WithAPIKey(apiKey),
	)
	response, err := client.Audio.Speech.New(context.Background(), openai.AudioSpeechNewParams{
		Model: "tts-1",
		Input: "There are three letters 'r' in the word 'strawberry'.",
		Voice: openai.AudioSpeechNewParamsVoiceAsh,
	})
	if err != nil {
		panic(err)
	}
	file, err := os.Create("generated.mp3")
	if err != nil {
		panic(err)
	}
	defer file.Close()
	_, err = io.Copy(file, response.Body)
	if err != nil {
		panic(err)
	}
}
```

--------------------------------

### Go Audio Translation Example

Source: https://docs.nexos.ai/openai-sdks/go-sdk

This Go code snippet shows how to translate audio using the Nexos AI Go SDK. It takes an audio file ('sound.mp3') and uses the 'whisper-1' model to translate the speech into English text.

```Go
package main

import (
	"context"
	"fmt"
	"os"

	"github.com/joho/godotenv"
	"github.com/openai/openai-go"
	"github.com/openai/openai-go/option"
)

func main() {
	err := godotenv.Load()
	if err != nil {
		panic(err)
	}
	apiKey := os.Getenv("API_KEY")
	apiUrl := os.Getenv("API_URL")
	client := openai.NewClient(
		option.WithBaseURL(apiUrl),
		option.WithAPIKey(apiKey),
	)
	file, err := os.Open("sound.mp3")
	if err != nil {
		panic(err)
	}
	defer file.Close()
	response, err := client.Audio.Translations.New(context.Background(), openai.AudioTranslationNewParams{
		Model: "whisper-1",
		File: file,
	})
	if err != nil {
		panic(err)
	}
	fmt.Println(response.Text)
}
```

--------------------------------

### Python SDK: Chat Completion

Source: https://docs.nexos.ai/openai-sdks/python-sdk

Generates a chat completion using the OpenAI SDK. It takes a user message and a model name as input and prints the AI's response.

```Python
from openai import OpenAI
from openai.types.chat import ChatCompletionUserMessageParam, ChatCompletion

openai = OpenAI(
    api_key=api_key,
    base_url=api_url,
)
message: ChatCompletionUserMessageParam = {
    "role": "user",
    "content": "how many letters 'r' in the word 'strawberry'",
}
response: ChatCompletion = openai.chat.completions.create(model="gpt-3.5-turbo", messages=[message])
print(response.choices[0].message.content)
```

--------------------------------

### Build Creative Brief

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Transforms scattered inputs into a structured creative brief for a team. It identifies objectives, audience, key messages, deliverables, and timelines, and can include public examples.

```English
Instructions
Parse inputs and detect objective, audience, single message, proof points, deliverables, timeline, mandatories.
Prefer internal references if available. Pull quotes or metrics with file and page.
If examples help, add two public examples labeled as external with links.
If inputs are thin, output a brief with clear placeholders and a list of missing items.

Brief Template: 
Objective
Audience and insight
Single message and tone
Proof and references
Deliverables and specs
Timeline and owners
Mandatories and constraints
Risks and open questions
```

--------------------------------

### Python SDK: Audio Generation

Source: https://docs.nexos.ai/openai-sdks/python-sdk

Generates speech audio from text using the OpenAI SDK. It takes text input, a model, and a voice type, then saves the audio to a file.

```Python
from openai import OpenAI

openai = OpenAI(
    api_key=api_key,
    base_url=api_url,
)
response = openai.audio.speech.create(
    input="There are three letters 'r' in the word 'strawberry'.",
    model="tts-1",
    voice="alloy",
)
response.write_to_file("generated.mp3")
```

--------------------------------

### Python SDK: Image Generation

Source: https://docs.nexos.ai/openai-sdks/python-sdk

Generates an image based on a text prompt using the OpenAI SDK's DALL-E model. It takes a prompt and model name, then prints the URL of the generated image.

```Python
from openai import OpenAI
from openai.types.images_response import ImagesResponse

openai = OpenAI(
    api_key=api_key,
    base_url=api_url,
)
response: ImagesResponse = openai.images.generate(
    prompt="three letters 'r' with strawberry texture",
    model="dall-e-3",
)
if response.data is not None:
    print(response.data[0].url)
```

--------------------------------

### API Response Example (JSON)

Source: https://docs.nexos.ai/gateway-api

This JSON structure represents a successful response from the Nexos AI image API, detailing the creation timestamp and an array of generated image data, which may include base64 encoded data or URLs.

```JSON
{
  "created": 1,
  "data": [
    {
      "b64_json": "text",
      "revised_prompt": "text",
      "url": "text"
    }
  ]
}
```

--------------------------------

### Python SDK: Audio Translation

Source: https://docs.nexos.ai/openai-sdks/python-sdk

Translates audio from one language to English using the OpenAI SDK's Whisper model. It reads an MP3 file and prints the translated text.

```Python
from openai import OpenAI

openai = OpenAI(api_key=api_key, base_url=api_url)
response = openai.audio.translations.create(file=open("sound.mp3", "rb"), model="whisper-1")
print(response.text)
```

--------------------------------

### Python SDK: Audio Transcription

Source: https://docs.nexos.ai/openai-sdks/python-sdk

Transcribes audio from a file into text using the OpenAI SDK's Whisper model. It reads an MP3 file and prints the transcribed text.

```Python
from openai import OpenAI

openai = OpenAI(api_key=api_key, base_url=api_url)
response = openai.audio.transcriptions.create(file=open('sound.mp3', 'rb'), model='whisper-1')
print(response.text)
```

--------------------------------

### Send Chat Completion Request (JavaScript)

Source: https://docs.nexos.ai/gateway-api

Example of sending a chat completion request using JavaScript with the fetch API. It shows how to configure the request headers and body for the chat completions endpoint.

```javascript
const fetch = require('node-fetch');

const response = await fetch("https://api.nexos.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Say this is a test!"}],
    "temperature": 0.7,
    "stream": true
  })
});

let data = await response.json();
```

--------------------------------

### Send Chat Completion Request (cURL)

Source: https://docs.nexos.ai/gateway-api

Example of sending a chat completion request using cURL. This demonstrates how to structure the request body with various parameters like model, messages, temperature, and stream.

```bash
curl https://api.nexos.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{ 
    "model": "gpt-3.5-turbo", 
    "messages": [{"role": "user", "content": "Say this is a test!"}], 
    "temperature": 0.7, 
    "stream": true 
  }'
```

--------------------------------

### Edit Image with Mask and Prompt (Python)

Source: https://docs.nexos.ai/gateway-api

This snippet provides a Python example for editing an image using the Nexos AI API. It details how to structure the request with image file, prompt, model, and optional parameters like mask, number of images, response format, and size.

```Python
import requests

url = "https://api.nexos.ai/v1/images/edits"
headers = {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN"
}

with open('image.png', 'rb') as image_file:
    files = {
        'image': image_file
    }
    payload = {
        'prompt': 'text',
        'model': '6948fe4d-98ce-4f36-bc49-5f652cc07b65',
        # Optional: 'mask': open('mask.png', 'rb'),
        # Optional: 'n': 1,
        # Optional: 'response_format': 'url',
        # Optional: 'size': '256x256'
    }
    response = requests.post(url, headers=headers, files=files, data=payload)

print(response.json())
```

--------------------------------

### Build Option Evidence Matrix

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Constructs a matrix comparing options based on Cost, Benefit, Risk, Effort, Confidence, and Evidence. Provides a recommendation with justifications and conditions for acceptance, listing necessary data if files are absent.

```Natural Language Processing
Build a matrix: Option, Cost, Benefit, Risk, Effort, Confidence, Evidence file and location.
Recommendation: one pick with 3 reasons and conditions to accept.
If no files exist, fill the matrix with placeholders and explicitly list the smallest data set needed to finalize. External benchmarks allowed, label external.
```

--------------------------------

### Get Storage File Details

Source: https://docs.nexos.ai/gateway-api

Retrieve details of a specific file from storage using its ID. Requires authorization and specifies the file_id as a path parameter. Returns file metadata upon success.

```cURL
GET /v1/storage/{file_id} HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_OAUTH2_TOKEN
Accept: */*
```

```JavaScript
fetch("https://api.nexos.ai/v1/storage/{file_id}", {
  method: "GET",
  headers: {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN",
    "Accept": "*/*"
  }
})
```

```Python
import requests

headers = {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN",
    "Accept": "*/*"
}
response = requests.get("https://api.nexos.ai/v1/storage/{file_id}", headers=headers)
print(response.json())
```

--------------------------------

### Marketing Assistant (Project-Aware)

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Acts as a project-aware marketer, answering queries using project files while adhering to company voice and formatting. It labels external sources and flags missing context. Web search may be used for trends but must be clearly marked as external.

```English
You handle all marketing queries using the materials in this Project.
Always follow the {COMPANY} custom instructions for tone and formatting. Your responses should be concise, aligned with our brand voice, and based on proven data from past campaigns.
When relevant, you may use web search to find fresh trends or examples, but clearly mark anything that comes from outside the Project.
If context is missing, say so directly and recommend what should be added.
```

--------------------------------

### Send Chat Completion Request (Python)

Source: https://docs.nexos.ai/gateway-api

Example of sending a chat completion request using Python's requests library. This code snippet illustrates how to make a POST request with JSON payload to the API.

```python
import openai

openai.api_key = "YOUR_API_KEY"

response = openai.ChatCompletion.create(
  model="gpt-3.5-turbo",
  messages=[
    {"role": "user", "content": "Say this is a test!"}
  ],
  temperature=0.7,
  stream=True
)
```

--------------------------------

### Marketing Assistant (Performance Metrics)

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Computes first-order Average Order Value (AOV), Customer Acquisition Cost (CAC), and Return on Ad Spend (ROAS) by channel, campaign, ad set, and creative. It ranks performance, provides insights and actions, and cites file names and dates. Missing UTM mapping or cost data requires specific file recommendations.

```English
You evaluate acquisition performance from this Project’s orders and ad exports. Compute first order AOV, CAC, and ROAS by channel, campaign, ad set, and creative. Rank winners and underperformers. If benchmarks are useful, pull them via web search and label as external. Output: metric table first, insights second, actions third. Cite file names and date ranges. If UTM mapping or cost data is missing, state the exact mapping or file required. No speculation. Show calculations clearly.
```

--------------------------------

### Story Point Packer Assistant

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Converts requirements into INVEST-compliant user stories, including acceptance criteria and edge cases. It outputs a backlog grouped by epic and priority, noting dependencies. If context is limited, it asks up to two questions before proceeding with assumptions.

```English
Instructions
From inputs given, requirement notes and any UX artifacts. help me with: 

For each story write As a, I want, so that, plus 3 to 5 acceptance criteria and edge cases.

Output a backlog grouped by epic and priority. Include dependencies where obvious.

If context is thin, ask up to 2 questions, then proceed with tagged assumptions.
```

--------------------------------

### Assemble Meeting Pre-reads

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Assembles concise pre-read documents for meetings, including a summary, key facts and metrics, questions to resolve, and source links. If no project data is available, it creates a template with placeholders and a list of required inputs.

```Natural Language Processing
Assemble a pre-read. Sections and caps:

-summary 120 words

-key facts and metrics (max 7 bullets) with citations

-questions to resolve (max 5)

- links to sources with file and page or sheet

If Project has nothing, build the frame with placeholders and a short list of must-have inputs. External data allowed, label external.
```

--------------------------------

### Translate Audio to English Text

Source: https://docs.nexos.ai/gateway-api

Translates audio files into English text. Supports various audio formats and allows for optional prompts to guide the translation. The response format can be customized to JSON, text, SRT, or VTT.

```HTTP
POST /v1/audio/translations HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_OAUTH2_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 121

{
  "file": "binary",
  "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65",
  "prompt": "text",
  "response_format": "json",
  "temperature": 0
}
```

```cURL
curl -X POST https://api.nexos.ai/v1/audio/translations \
  -H "Authorization: Bearer YOUR_OAUTH2_TOKEN" \
  -H "Content-Type: multipart/form-data" \
  -F "file=@your_audio.flac" \
  -F "model=6948fe4d-98ce-4f36-bc49-5f652cc07b65" \
  -F "prompt=text" \
  -F "response_format=json" \
  -F "temperature=0"
```

```JavaScript
const axios = require('axios');
const fs = require('fs');

const translateAudio = async () => {
  const formData = new FormData();
  formData.append('file', fs.createReadStream('your_audio.flac'));
  formData.append('model', '6948fe4d-98ce-4f36-bc49-5f652cc07b65');
  formData.append('prompt', 'text');
  formData.append('response_format', 'json');
  formData.append('temperature', 0);

  try {
    const response = await axios.post('https://api.nexos.ai/v1/audio/translations', formData, {
      headers: {
        'Authorization': 'Bearer YOUR_OAUTH2_TOKEN',
        'Content-Type': 'multipart/form-data',
      },
    });
    console.log(response.data);
  } catch (error) {
    console.error('Error translating audio:', error);
  }
};

translateAudio();
```

```Python
import requests

url = "https://api.nexos.ai/v1/audio/translations"
headers = {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN"
}
files = {
    "file": open("your_audio.flac", "rb")
}
data = {
    "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65",
    "prompt": "text",
    "response_format": "json",
    "temperature": 0
}

response = requests.post(url, headers=headers, files=files, data=data)

if response.status_code == 200:
    print(response.json())
else:
    print(f"Error: {response.status_code}, {response.text}")
```

--------------------------------

### Generate Market View from Project Reports

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Creates a concise market overview from project reports, including key findings, competitor analysis, and risk assessment. It can also label and cite external news sources.

```English
You produce a short market view based on reports and notes in this Project. Start with key findings, then competitor table, then risks and opportunities. If fresh news matters, use web search, label as external, and link it. Cite report file names and page numbers where possible. If a claim cannot be verified in Project materials, say so.
```

--------------------------------

### Provide Legal Clause Explanations

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Extracts exact clauses from contracts and policies within a project and provides a plain-language explanation. It also notes exceptions and cites external public law references.

```English
Answer using contracts and policies in this Project. Start with a direct answer, then quote the clause with file and location.
Explain in plain language, note exceptions. If you reference public law, label external and link.
If the contract is missing, name it and stop.
```

--------------------------------

### Generate Market Snapshot

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Produces a concise market snapshot including size, trends, key players, and risks, using project reports and notes. It can incorporate external news and cite sources.

```English
Produce a snapshot using reports and notes in this Project. Start with key findings, then competitor table, then risks and opportunities.
If fresh news matters, search the web, label external, link.
Cite report files and pages. If a claim cannot be verified here, say so.
```

--------------------------------

### Outcome KPI Setter Assistant

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Defines success metrics and guardrails for initiatives by establishing a north star metric, key drivers, and guardrails. It provides formulas, data sources, and a KPI table with ownership and review cadence. If data is missing, it recommends a minimal tracking plan.

```English
Define one north star, 3 to 5 drivers, and 2 guardrails. Provide formulas and data sources.

Output:
KPI table with owner and review cadence
risks if gamed and how to counter
sources or schema request
If data does not exist, recommend a minimal tracking plan.
```

--------------------------------

### Generate Executive One-Pager

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Creates a concise one-page summary for leaders, including facts, metrics, risks, opportunities, questions, and asks with dates. It cites internal sources or provides placeholders and a checklist for missing data, keeping prose under 250 words.

```Natural Language Processing
Sections in order: facts and metrics, top risks, opportunities, open questions, asks with dates.
Cite internal sources inline. If none exist, produce the sections with placeholders and a checklist of the minimum data to finalize. Keep prose under 250 words total. External items must be labeled.
```

--------------------------------

### Analyze Competitor Messaging and Strategy

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Extracts and summarizes competitor messaging, product changes, pricing, and partnerships from project notes. It suggests response ideas and labels external information.

```English
From this Project’s competitive notes, and our listed competitors, extract the main messaging in their homepages and shifts. Summarize product changes, pricing, messaging, partnerships.
Add 3 response ideas tied to our positioning. Any public items must be labeled external with links.
If a competitor file is missing, or you need more information - tell me. 
You always offer outside of the box solutions to approach our competition.
```

--------------------------------

### Generate Speech Audio from Text (JavaScript)

Source: https://docs.nexos.ai/gateway-api

This JavaScript snippet demonstrates how to use the Fetch API to call the Nexos AI /v1/audio/speech endpoint. It sends a POST request with a JSON body containing the model, input text, voice, response format, and speed.

```JavaScript
const options = {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_OAUTH2_TOKEN',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: '6948fe4d-98ce-4f36-bc49-5f652cc07b65',
    input: 'text',
    voice: 'alloy',
    response_format: 'mp3',
    speed: 1
  })
};

fetch('https://api.nexos.ai/v1/audio/speech', options)
  .then(response => response.blob()) // Assuming the response is binary audio data
  .then(blob => {
    // Handle the audio blob, e.g., play it or save it
    const url = window.URL.createObjectURL(blob);
    const audio = new Audio(url);
    audio.play();
  })
  .catch(error => console.error('Error:', error));
```

--------------------------------

### Upgrade Macro Library

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Enhances a macro library for faster and more consistent customer support replies. It merges duplicates, adds variants, and inserts variables based on existing macros, tickets, and policy documents.

```English
Inputs accepted: existing macros, recent tickets, policy PDFs.

Build:

1. merge duplicate macros
2. add missing variants for top 5 issues
3. insert variables and guardrails

Output:

macro set with titles and bodies
mapping text to issues
gaps list with sources

If no macros exist, create a starter set based on ticket patterns.
```

--------------------------------

### Review DPA Readiness

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Assists in reviewing draft Data Processing Agreements (DPAs) to ensure they meet customer expectations. It checks critical sections and provides a structured output with status, evidence, and suggested fixes.

```English
Inputs accepted: draft DPA, security overview.

Checklist sections: roles, subprocessors, transfer mechanism, security measures, breach notice, audit rights, deletion, liability, governing law.

Output:

-checklist: item, status, evidence, gap, suggested fix

- Red flag summary in 80 words
Cite section and page for each item. If a section is missing, state it plainly.
```

--------------------------------

### Product Strategy Evaluation Assistant

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Evaluates a product strategy by comparing it to market offerings, identifying shortcomings, and performing KANO and MoSCoW prioritization. It requires clarification of scope and can ask up to three questions if goals, users, or constraints are unclear. The output includes a product summary, market scan, gap analysis, KANO classification, and MoSCoW prioritization.

```English
Follow {COMPANY} custom instructions for tone, terminology, and confidentiality.

Clarify scope first. Ask up to 3 precise questions if goals, target users, or constraints are unclear. If answers are not available, proceed with clearly tagged assumptions.

1. Build a concise product summary:

target users and primary jobs to be done
current solution overview and key flows
success metrics used today if provided

2. Run a focused market scan:

if competitor names or docs are provided, use them first
if not, request names the team considers peers
only when helpful, use web search, label findings as external, and include links
compile a short table: competitor, segment, core claim, pricing signal, notable strengths, notable weaknesses

3. Perform a gap analysis on our solution. Organize gaps by category: usability, capability, performance, integration, security and compliance, trust, pricing and packaging. For each gap add severity, evidence, and quick fix or experiment.

4. Produce KANO classification for missing or underperforming features:

categories: must-have, performance, delighter, indifferent, reverse
table columns: feature, user outcome, category, evidence source or assumption, risk if omitted
summary: what must be fixed now to avoid dissatisfaction, what can differentiate, what to avoid

5. Produce MoSCoW prioritization for the backlog:

groups: must, should, could, won’t for now
include dependency or enabling work where relevant
table columns: item, rationale, dependency, estimate range if available

Do not guess facts. Keep rationales short and specific. Where data is missing, state exactly what file or field would resolve the uncertainty.
```

--------------------------------

### Transcribe Audio to Text (Python)

Source: https://docs.nexos.ai/gateway-api

This Python snippet demonstrates audio transcription using the `requests` library. It sends a POST request with `multipart/form-data` to the Nexos AI API, including the audio file and transcription parameters.

```Python
import requests

url = "https://api.nexos.ai/v1/audio/transcriptions"
headers = {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN"
}

files = {
    'file': open('/path/to/your/audio.mp3', 'rb')
}

data = {
    "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65",
    "language": "en",
    "response_format": "json",
    "temperature": 0,
    "timestamp_granularities[]": "word"
}

response = requests.post(url, headers=headers, files=files, data=data)

if response.status_code == 200:
    print("Transcription successful:", response.json())
else:
    print(f"Error: {response.status_code}, {response.text}")
```

--------------------------------

### List Available Models

Source: https://docs.nexos.ai/gateway-api

Retrieve a list of all models available to the user. This endpoint requires authorization and returns a list of model objects, each containing details like ID, name, and ownership.

```cURL
GET /v1/models HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_OAUTH2_TOKEN
Accept: */*
```

```JavaScript
fetch("https://api.nexos.ai/v1/models", {
  method: "GET",
  headers: {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN",
    "Accept": "*/*"
  }
})
```

```Python
import requests

headers = {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN",
    "Accept": "*/*"
}
response = requests.get("https://api.nexos.ai/v1/models", headers=headers)
print(response.json())
```

--------------------------------

### Draft Project Scope and Plan

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Transforms problem statements from files and user prompts into a project scope, including deliverables, acceptance criteria, timeline, owners, and risks. It can search the web for patterns, label external sources, and identify missing inputs.

```Natural Language Processing
From problem statements in files and my prompts, help to draft scope, deliverables, acceptance criteria, timeline, owners, and risks.
If you need patterns, search the web, label external, link.
List any missing inputs by file or field and stop.
```

--------------------------------

### Generate Images from Text Prompt

Source: https://docs.nexos.ai/gateway-api

Generates images based on a provided text description. Users can specify the number of images, quality, format, size, and style. The response includes a URL or base64 encoded JSON of the generated image(s).

```HTTP
POST /v1/images/generations HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_OAUTH2_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 148

{
  "prompt": "text",
  "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65",
  "n": 1,
  "quality": "standard",
  "response_format": "url",
  "size": "256x256",
  "style": "vivid"
}
```

```cURL
curl -X POST https://api.nexos.ai/v1/images/generations \
  -H "Authorization: Bearer YOUR_OAUTH2_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{ 
    "prompt": "text", 
    "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65", 
    "n": 1, 
    "quality": "standard", 
    "response_format": "url", 
    "size": "256x256", 
    "style": "vivid" 
  }'
```

```JavaScript
const axios = require('axios');

const generateImage = async () => {
  const data = {
    prompt: 'text',
    model: '6948fe4d-98ce-4f36-bc49-5f652cc07b65',
    n: 1,
    quality: 'standard',
    response_format: 'url',
    size: '256x256',
    style: 'vivid'
  };

  try {
    const response = await axios.post('https://api.nexos.ai/v1/images/generations', data, {
      headers: {
        'Authorization': 'Bearer YOUR_OAUTH2_TOKEN',
        'Content-Type': 'application/json',
      },
    });
    console.log(response.data);
  } catch (error) {
    console.error('Error generating image:', error);
  }
};

generateImage();
```

```Python
import requests

url = "https://api.nexos.ai/v1/images/generations"
headers = {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN",
    "Content-Type": "application/json"
}
data = {
    "prompt": "text",
    "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65",
    "n": 1,
    "quality": "standard",
    "response_format": "url",
    "size": "256x256",
    "style": "vivid"
}

response = requests.post(url, headers=headers, json=data)

if response.status_code == 200:
    print(response.json())
else:
    print(f"Error: {response.status_code}, {response.text}")
```

--------------------------------

### Normalize Scattered Notes into Themes

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Ingests and processes scattered notes to deduplicate, group by theme, and retain only evidence-backed points. Returns themes with insights, quotes, or evidence, and open questions, tagging each item with its source.

```Natural Language Processing
Ingest scattered notes. Deduplicate, group by theme, keep only evidence-backed points.
Return: themes with 1-sentence insight, quotes or evidence, open questions.
Tag each item with Source file and location or Assumption. If Project is empty, build the structure from the prompt and flag evidence gaps.
```

--------------------------------

### Convert Meeting Minutes to Actions

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Transforms meeting transcripts or notes into decisions and an action table (Owner, Task, Due, Status). It assigns tentative owners/dates when missing and cites timestamps or pages. Provides a blank template if no notes exist.

```Natural Language Processing
Turn transcripts or notes into:

-decisions

-action table Owner, Task, Due, Status

-blockers and dependencies

Rules: assign tentative owners or dates only when missing and mark as tentative. Cite timestamps or pages when possible. If no notes exist, return a blank template with a 3-line guide on how to capture them next time.
```

--------------------------------

### Generate Speech Audio from Text (Python)

Source: https://docs.nexos.ai/gateway-api

This Python snippet shows how to use the `requests` library to interact with the Nexos AI /v1/audio/speech endpoint. It sends a POST request with the necessary headers and a JSON payload for speech generation.

```Python
import requests

url = "https://api.nexos.ai/v1/audio/speech"
headers = {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN",
    "Content-Type": "application/json"
}

data = {
    "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65",
    "input": "text",
    "voice": "alloy",
    "response_format": "mp3",
    "speed": 1
}

response = requests.post(url, headers=headers, json=data)

if response.status_code == 200:
    # Assuming the response is binary audio data
    with open("output.mp3", "wb") as audio_file:
        audio_file.write(response.content)
    print("Audio generated successfully!")
else:
    print(f"Error: {response.status_code}, {response.text}")
```

--------------------------------

### Mine CSAT Drivers from Conversations

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Analyzes static conversation exports to identify factors influencing Customer Satisfaction (CSAT) scores. It segments data, computes CSAT deltas, and surfaces top drivers and coaching themes.

```English
1.segment by channel, topic, agent, first response time, resolution time

2. compute CSAT deltas by segment

3. surface top 5 drivers, positive and negative

Output:

driver list with effect size

example snippets with ticket ids and timestamps

3 coaching themes and macros to add or edit

If key columns are missing, name them and proceed with partial analysis.
```

--------------------------------

### Prioritize Roadmap Initiatives

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Prioritizes initiatives using specified scoring methods (RICE, WSJF, or MoSCoW). Outputs a table with Item, Score, Effort, Owner, Quarter, and Dependencies, indicating any missing fields required for scoring.

```Natural Language Processing
Prioritize initiatives using {RICE, WSJF or MoSCoW}.
Output table with Item, Score, Effort, Owner, Quarter, Dependencies.
If a value is missing, state the exact field needed to score.
```

--------------------------------

### Transcribe Audio to Text (JavaScript)

Source: https://docs.nexos.ai/gateway-api

This JavaScript snippet shows how to upload an audio file for transcription using the Fetch API. It sends a POST request with `multipart/form-data` and includes parameters like model, language, and response format.

```JavaScript
const fileInput = document.getElementById('audioFile'); // Assuming you have an input element with id 'audioFile'
const file = fileInput.files[0];

const formData = new FormData();
formData.append('file', file);
formData.append('model', '6948fe4d-98ce-4f36-bc49-5f652cc07b65');
formData.append('language', 'en');
formData.append('response_format', 'json');
formData.append('temperature', 0);
formData.append('timestamp_granularities[]', 'word');

const options = {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_OAUTH2_TOKEN'
    // Content-Type is automatically set by FormData
  },
  body: formData
};

fetch('https://api.nexos.ai/v1/audio/transcriptions', options)
  .then(response => response.json())
  .then(data => {
    console.log('Transcription:', data);
  })
  .catch(error => console.error('Error:', error));
```

--------------------------------

### Download Storage File Contents

Source: https://docs.nexos.ai/gateway-api

Download the content of a file from storage using its ID. This endpoint requires authorization and the file_id as a path parameter. The response is the binary content of the file.

```cURL
GET /v1/storage/{file_id}/content HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_OAUTH2_TOKEN
Accept: */*
```

```JavaScript
fetch("https://api.nexos.ai/v1/storage/{file_id}/content", {
  method: "GET",
  headers: {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN",
    "Accept": "*/*"
  }
})
```

```Python
import requests

headers = {
    "Authorization": "Bearer YOUR_OAUTH2_TOKEN",
    "Accept": "*/*"
}
response = requests.get("https://api.nexos.ai/v1/storage/{file_id}/content", headers=headers)
# The response content will be binary data
print(response.content)
```

--------------------------------

### Extract Action Register from Sources

Source: https://docs.nexos.ai/workspace/assistants/prompt-library

Scans notes, tickets, and documents to extract an action register including Task, Context, Owner, Due, Dependency, Priority, and Source. It proposes defaults for missing information and ensures tasks have clear outcomes.

```Natural Language Processing
Scan notes, tickets, and docs. Output a register: Task, Context, Owner, Due, Dependency, Priority, Source.
Rules: propose defaults only when missing and mark tentative. No tasks without a clear outcome.
If owners are unknown, suggest the most likely function and why. Cite sources when available.
```

--------------------------------

### Generate Speech Audio from Text (HTTP)

Source: https://docs.nexos.ai/gateway-api

This snippet demonstrates how to generate speech audio from text using the Nexos AI API. It requires specifying the model, input text, voice, and optionally the response format and speed.

```HTTP
POST /v1/audio/speech HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_OAUTH2_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 113

{
  "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65",
  "input": "text",
  "voice": "alloy",
  "response_format": "mp3",
  "speed": 1
}
```

--------------------------------

### Edit Image with Mask and Prompt (HTTP/cURL)

Source: https://docs.nexos.ai/gateway-api

This snippet demonstrates how to edit an image using a mask and a text prompt via an HTTP POST request. It requires the image file, an optional mask file, a prompt, and a model ID. The response format and image size can also be specified.

```cURL
POST /v1/images/edits HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_OAUTH2_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 144

{
  "image": "binary",
  "mask": "binary",
  "prompt": "text",
  "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65",
  "n": 1,
  "response_format": "url",
  "size": "256x256"
}
```

--------------------------------

### Transcribe Audio to Text (HTTP)

Source: https://docs.nexos.ai/gateway-api

This snippet shows the HTTP request structure for transcribing audio to text using the Nexos AI API. It uses `multipart/form-data` and includes parameters like file, model, language, response format, and temperature.

```HTTP
POST /v1/audio/transcriptions HTTP/1.1
Host: api.nexos.ai
Authorization: Bearer YOUR_OAUTH2_TOKEN
Content-Type: multipart/form-data
Accept: */*
Content-Length: 176

{
  "file": "binary",
  "model": "6948fe4d-98ce-4f36-bc49-5f652cc07b65",
  "language": "text",
  "prompt": "text",
  "response_format": "json",
  "temperature": 0,
  "timestamp_granularities[]": [
    "word"
  ]
}
```