Gemini 2.5 OpenAI-compatible implicit caching support

gemini_implicit_caching.sh

#!/bin/bash

# --- Configuration ---
API_ENDPOINT="https://generativelanguage.googleapis.com/v1beta/openai/chat/completions" # Replace with the actual endpoint (e.g., from Google AI Studio, a third-party provider, etc.)
API_KEY="Your Gemini API Key"                            # Replace with your actual API key
FILE_PATH="report.md"                                    # Replace with the path to your large text file
MODEL_NAME="gemini-2.5-flash-preview-04-17"              # Replace with the specific Gemini 2.5 model name supported by your endpoint

# --- Construct JSON Payload using jq ---
# Reads the file content and embeds it as a string within the JSON
# --- Construct JSON Payload using jq and pipe directly to curl ---
# Uses --rawfile based on your jq --help output
jq -n \
  --arg model "$MODEL_NAME" \
  --arg user "$1" \
  --rawfile file_content "$FILE_PATH" \
  '{
    "model": $model,
    "messages": [
      {
        "role": "user",
        "content": $file_content
      },
      {
        "role": "user",
        "content": $user
      }
    ],
    "max_tokens": 4096
  }' | curl -X POST "$API_ENDPOINT" \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer $API_KEY" \
     -d @-

# Note: The '| \' syntax pipes the output of the command on the left
# (jq...) to the command on the right (curl...).
# -d @- tells curl to read the POST data from stdin.