cURL Integration

Use cURL for quick testing and debugging without any dependencies.

Basic Request

Simple Chat Completion

curl -X POST http://localhost/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Hello, Enclava!"}]
  }'

Pretty JSON Output

curl -X POST http://localhost/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Hello!"}]
  }' | jq '.'

Environment Variables

Store your configuration in environment variables:

# Add to ~/.bashrc or ~/.zshrc
export ENCLAVA_URL="http://localhost/api/v1"
export ENCLAVA_API_KEY="YOUR_API_KEY"

# Reload shell
source ~/.bashrc

# Use in requests
curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Examples

List Models

curl -X GET $ENCLAVA_URL/models \
  -H "Authorization: Bearer $ENCLAVA_API_KEY"

Chat with System Prompt

curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful, friendly assistant."
      },
      {
        "role": "user",
        "content": "What is 2+2?"
      }
    ]
  }'

Chat with Temperature

# Low temperature (more focused)
curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "What is the capital of France?"}],
    "temperature": 0.2
  }'

# High temperature (more creative)
curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Write a creative story"}],
    "temperature": 1.5
  }'

Multi-turn Conversation

# First message
curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is 2+2?"}
    ]
  }'

# Second message with context
curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "What is 2+2?"},
      {"role": "assistant", "content": "2+2 equals 4."},
      {"role": "user", "content": "What about 5+3?"}
    ]
  }'

Generate Embeddings

curl -X POST $ENCLAVA_URL/embeddings \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-ada-002",
    "input": "The quick brown fox jumps over the lazy dog."
  }'

Multiple Text Embeddings

curl -X POST $ENCLAVA_URL/embeddings \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-ada-002",
    "input": [
      "The cat sat on the mat.",
      "The dog ran in the park."
    ]
  }'

Max Tokens Limit

curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Tell me about AI"}],
    "max_tokens": 100
  }'

Stop Sequences

curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Count from 1 to 10"}],
    "stop": ["11", "eleven"]
  }'

Streaming

Basic Streaming

curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Tell me a story"}],
    "stream": true
  }'

Parse Streaming Output

curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Write a poem"}],
    "stream": true
  }' | while read -r line; do
    if [[ $line == data:* ]]; then
      DATA="${line#data: }"
      if [[ "$DATA" == "[DONE]" ]]; then
        break
      fi
      echo "$DATA" | jq -r '.choices[0].delta.content // empty' 2>/dev/null | tr -d '\n'
    fi
  done

File Input

Using File for Messages

cat > messages.json << EOF
{
  "model": "gpt-3.5-turbo",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello from file!"}
  ]
}
EOF

curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d @messages.json

Using File for Input (Embeddings)

cat > input.txt << EOF
Hello, world!
This is a test document.
EOF

curl -X POST $ENCLAVA_URL/embeddings \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d "{
    \"model\": \"text-embedding-ada-002\",
    \"input\": \"$(cat input.txt)\"
  }"

Error Handling

Check HTTP Status

RESPONSE=$(curl -s -o /dev/null -w "%{http_code}" \
  -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer $ENCLAVA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Hello"}]
  }')

if [ "$RESPONSE" -eq 200 ]; then
  echo "✓ Request successful"
else
  echo "✗ Request failed with status $RESPONSE"
fi

Capture Errors

curl -X POST $ENCLAVA_URL/chat/completions \
  -H "Authorization: Bearer invalid_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo",
    "messages": [{"role": "user", "content": "Hello"}]
  }' | jq '.'

Useful cURL Options

Option	Description	Example
`-s`	Silent mode	`-s`
`-v`	Verbose output	`-v`
`-w "%{http_code}"`	Output status code only	`-w "%{http_code}"`
`-o file`	Save response to file	`-o response.json`
`-d @file`	Read data from file	`-d @data.json`
`-H "Header: Value"`	Add header	`-H "Content-Type: application/json"`

Scripts

Simple Chat Script

#!/bin/bash

ENCLAVA_URL="${ENCLAVA_URL:-http://localhost/api/v1}"
API_KEY="${ENCLAVA_API_KEY}"

chat() {
  local message="$1"
  curl -s -X POST "$ENCLAVA_URL/chat/completions" \
    -H "Authorization: Bearer $API_KEY" \
    -H "Content-Type: application/json" \
    -d "{
      \"model\": \"gpt-3.5-turbo\",
      \"messages\": [{\"role\": \"user\", \"content\": \"$message\"}]
    }" | jq -r '.choices[0].message.content'
}

chat "$1"

Usage:

./chat.sh "What is the capital of France?"

Batch Request Script

#!/bin/bash

ENCLAVA_URL="${ENCLAVA_URL:-http://localhost/api/v1}"
API_KEY="${ENCLAVA_API_KEY}"

MESSAGES=(
  "Hello, how are you?"
  "What is AI?"
  "Tell me a joke"
)

for msg in "${MESSAGES[@]}"; do
  echo "Processing: $msg"
  response=$(curl -s -X POST "$ENCLAVA_URL/chat/completions" \
    -H "Authorization: Bearer $API_KEY" \
    -H "Content-Type: application/json" \
    -d "{
      \"model\": \"gpt-3.5-turbo\",
      \"messages\": [{\"role\": \"user\", \"content\": \"$msg\"}]
    }")
  echo "Response: $(echo $response | jq -r '.choices[0].message.content')"
  echo "---"
done

Best Practices

Environment Variables: Store URL and API key in environment variables
Pretty Output: Use jq for readable JSON output
Error Checking: Check HTTP status codes
Silent Mode: Use -s for scripts
File Input: Use @file for large requests

Next Steps

Python Integration - Use with Python SDK
JavaScript Integration - Use with Node.js
Chat Completions - Full API documentation

Basic Request​

Simple Chat Completion​

Pretty JSON Output​

Environment Variables​

Examples​

List Models​

Chat with System Prompt​

Chat with Temperature​

Multi-turn Conversation​

Generate Embeddings​

Multiple Text Embeddings​

Max Tokens Limit​

Stop Sequences​

Streaming​

Basic Streaming​

Parse Streaming Output​

File Input​

Using File for Messages​

Using File for Input (Embeddings)​

Error Handling​

Check HTTP Status​

Capture Errors​

Useful cURL Options​

Scripts​

Simple Chat Script​

Batch Request Script​

Best Practices​

Next Steps​

Basic Request

Simple Chat Completion

Pretty JSON Output

Environment Variables

Examples

List Models

Chat with System Prompt

Chat with Temperature

Multi-turn Conversation

Generate Embeddings

Multiple Text Embeddings

Max Tokens Limit

Stop Sequences

Streaming

Basic Streaming

Parse Streaming Output

File Input

Using File for Messages

Using File for Input (Embeddings)

Error Handling

Check HTTP Status

Capture Errors

Useful cURL Options

Scripts

Simple Chat Script

Batch Request Script

Best Practices

Next Steps