> ## Documentation Index
> Fetch the complete documentation index at: https://docs.responsibleailabs.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# एक Responsible AI Chatbot बनाएँ

> Part 1 of 2 - Setup, basic evaluation, deep analysis, और RAIL scores को समझना।

<Info>
  **Part 2:** [Production Features](/use-cases/ai-chatbot-production) - Provider wrappers, policy enforcement, sessions, और observability।
</Info>

## Setup

हम "CloudDash" नाम के एक fictional SaaS product के लिए customer support chatbot बना रहे हैं — यह एक cloud monitoring dashboard है। यह chatbot pricing, features, और troubleshooting के बारे में सवालों के जवाब देता है। साथ ही, हम हर layer पर RAIL Score evaluation add करेंगे ताकि chatbot के responses safe, accurate, fair, और helpful हों।

### Dependencies install करें

```bash theme={null}
pip install "rail-score-sdk[openai,google,langfuse]" openai google-genai
```

### Environment variables

एक `.env` file बनाएँ:

```bash theme={null}
RAIL_API_KEY=YOUR_RAIL_API_KEY
OPENAI_API_KEY=sk-your_openai_key
GEMINI_API_KEY=your_gemini_key

# Optional: Part 2 के लिए (Langfuse observability)
LANGFUSE_PUBLIC_KEY=pk-lf-...
LANGFUSE_SECRET_KEY=sk-lf-...
LANGFUSE_HOST=https://cloud.langfuse.com
```

<Note>
  **अपनी RAIL API key लें:** [responsibleailabs.ai/dashboard](https://responsibleailabs.ai/dashboard) पर sign up करें। Free tier में 100 credits मिलते हैं — इस पूरे tutorial को follow करने के लिए काफ़ी हैं।
</Note>

## Basic chatbot बनाएँ

पहले OpenAI से directly एक basic chatbot बनाएँ, बिना किसी RAIL integration के। यही वो foundation है जिस पर हम scoring layer करेंगे।

```python chatbot.py theme={null}
import openai
import os

openai_client = openai.OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

SYSTEM_PROMPT = """You are CloudDash Support, a helpful assistant for
CloudDash — a cloud monitoring dashboard. Answer questions about
pricing, features, setup, and troubleshooting. Be concise and accurate.
If you don't know something, say so."""


def chat(user_message: str, history: list[dict] = None) -> str:
    messages = [{"role": "system", "content": SYSTEM_PROMPT}]
    if history:
        messages.extend(history)
    messages.append({"role": "user", "content": user_message})

    response = openai_client.chat.completions.create(
        model="gpt-4o",
        messages=messages,
        temperature=0.3,
    )
    return response.choices[0].message.content


reply = chat("What pricing plans do you offer?")
print(reply)
```

यह काम तो करता है, लेकिन response quality की कोई visibility नहीं है। क्या यह response safe है? क्या factually accurate है? कोई bias तो नहीं है? जब तक RAIL Score add नहीं करते, जानने का कोई तरीका नहीं।

## RAIL Score evaluation add करें

RAIL evaluation add करने का सबसे simple तरीका `RailScoreClient` use करना है। एक ही call से सभी 8 RAIL dimensions के scores मिल जाते हैं।

```python chatbot_with_eval.py theme={null}
from rail_score_sdk import RailScoreClient
import os

rail = RailScoreClient(api_key=os.getenv("RAIL_API_KEY"))

reply = chat("What pricing plans do you offer?")

result = rail.eval(content=reply, mode="basic")

print(f"Overall Score: {result.rail_score.score}")
print(f"Confidence:    {result.rail_score.confidence}")
print()
for dim_name, dim_score in result.dimension_scores.items():
    print(f"  {dim_name:15s} {dim_score.score}")
```

<Accordion title="Example output">
  ```
  Overall Score: 8.4
  Confidence:    0.91

    fairness        8.5
    safety          9.2
    reliability     7.8
    transparency    8.0
    privacy         5.0
    accountability  8.1
    inclusivity     8.7
    user_impact     9.0
  ```
</Accordion>

### Results को समझें

| Dimension      | Score | इसका मतलब                                               |
| -------------- | ----- | ------------------------------------------------------- |
| Safety         | 9.2   | कोई harmful content नहीं, सभी users के लिए appropriate  |
| User Impact    | 9.0   | सही detail level पर directly सवाल का जवाब देता है       |
| Inclusivity    | 8.7   | Accessible language, कोई exclusionary terms नहीं        |
| Fairness       | 8.5   | Equal treatment, कोई demographic bias नहीं              |
| Accountability | 8.1   | Clear reasoning, traceable claims                       |
| Transparency   | 8.0   | Knowledge का honest representation                      |
| Reliability    | 7.8   | ज़्यादातर accurate, लेकिन pricing details synthetic हैं |
| Privacy        | 5.0   | Applicable नहीं - कोई PII involved नहीं                 |

<Tip>
  **Privacy = 5.0** का मतलब है "applicable नहीं।" जब privacy evaluate किए जा रहे content के लिए relevant नहीं होती, तो RAIL 5.0 (neutral) return करता है।
</Tip>

## Deep evaluation

Basic mode आपको scores देता है। Deep mode आपको *why* बताता है: हर dimension की explanations, detected issues, और improvement suggestions।

```python deep_eval.py theme={null}
result = rail.eval(content=reply, mode="deep")

print(f"Overall: {result.rail_score.score}")
print()

for dim_name, detail in result.dimension_scores.items():
    print(f"--- {dim_name} (score: {detail.score}) ---")
    print(f"  Explanation: {detail.explanation}")
    if detail.issues:
        print(f"  Issues: {', '.join(detail.issues)}")
    if detail.suggestions:
        print(f"  Suggestion: {detail.suggestions[0]}")
    print()
```

<Accordion title="Example output">
  ```
  Overall: 8.4

  --- reliability (score: 7.8) ---
    Explanation: The response provides specific pricing figures ($29, $79)
    that appear reasonable but cannot be verified against actual CloudDash
    pricing. The feature breakdown is plausible but unconfirmed.
    Issues: overconfident_claim
    Suggestion: Add a disclaimer that pricing is subject to change, or
    link to the official pricing page for the most current information.

  --- transparency (score: 8.0) ---
    Explanation: The response clearly presents the three tiers with
    distinct features. However, it doesn't disclose that it may not have
    the latest pricing information.
    Issues: concealed_limitation
    Suggestion: Acknowledge that pricing details should be verified on
    the official website.

  --- user_impact (score: 9.0) ---
    Explanation: Directly addresses the user's pricing question with a
    well-structured comparison. The follow-up question adds value.
  ```
</Accordion>

### Basic vs Deep

|                     | Basic                         | Deep                                   |
| ------------------- | ----------------------------- | -------------------------------------- |
| **Cost**            | 1 credit                      | 3 credits                              |
| **Scores**          | Overall + 8 dimensions        | Overall + 8 dimensions                 |
| **Explanations**    | नहीं                          | हाँ, हर dimension के लिए               |
| **Issue detection** | नहीं                          | हाँ                                    |
| **Best for**        | High-volume, real-time checks | Debugging, auditing, post-hoc analysis |

<Tip>
  **Cost-saving tip:** Production में हर response के लिए basic mode use करें, और deep mode selectively use करें। जैसे, जब basic score आपके threshold से नीचे गिरे तो deep mode trigger करें, या responses के sample पर periodic audit के लिए।
</Tip>

## आगे क्या है

<Card title="Part 2: Production Features" icon="rocket" href="/use-cases/ai-chatbot-production">
  Provider wrappers, policy enforcement (block/regenerate), multi-turn session tracking, और Langfuse observability।
</Card>