Skip to content

armgit / dspy

Public Imported from GitHub
0

DSPy: The framework for programming—not prompting—language models

Python
9.9 KB
Raw Blame
{
  "messages": [
    {
      "role": "system",
      "content": [
        "Your input fields are:\n",
        "1. `ticket` (str): Customer report\n",
        "2. `previous_urgent` (Noul[(True, 'Service unavailable'), (False, 'Workaround available')]): Previous urgency\n",
        "    Type description of Noul[(True, 'Service unavailable'), (False, 'Workaround available')]: A Boolean decision. Criteria: {\"true\": \"Service unavailable\", \"false\": \"Workaround available\"}.\n",
        "3. `previous_category` (Choice[('billing', 'Payment issue'), ('technical', 'Product malfunction')]): Previous category\n",
        "    Type description of Choice[('billing', 'Payment issue'), ('technical', 'Product malfunction')]: Select exactly one value. Options: [[\"billing\", \"Payment issue\"], [\"technical\", \"Product malfunction\"]].\n",
        "4. `previous_severity` (Score['Minor', 'Disruptive', 'Critical']): Previous severity\n",
        "    Type description of Score['Minor', 'Disruptive', 'Critical']: Continuous score from 0 to 2; intermediate values are allowed. Rubric (level index, description): [[0, \"Minor\"], [1, \"Disruptive\"], [2, \"Critical\"]].\n",
        "Your output fields are:\n",
        "1. `urgent` (NoulEvidence): \n",
        "{\n",
        "  \"instructions\": {\n",
        "    \"focus\": \"Current service availability\"\n",
        "  },\n",
        "  \"type\": \"noul\",\n",
        "  \"criteria\": {\n",
        "    \"true\": \"Service unavailable\",\n",
        "    \"false\": \"Workaround available\"\n",
        "  }\n",
        "}\n",
        "2. `category` (ChoiceEvidence): \n",
        "{\n",
        "  \"instructions\": \"Which team should respond?\",\n",
        "  \"type\": \"choice\",\n",
        "  \"criteria\": {\n",
        "    \"billing\": \"Payment issue\",\n",
        "    \"technical\": \"Product malfunction\"\n",
        "  }\n",
        "}\n",
        "3. `severity` (ScoreEvidence): \n",
        "{\n",
        "  \"instructions\": \"How severe is the impact?\",\n",
        "  \"type\": \"score\",\n",
        "  \"criteria\": [\n",
        "    \"Cosmetic\",\n",
        "    {\n",
        "      \"what\": \"Work interrupted\"\n",
        "    },\n",
        "    {\n",
        "      \"examples\": [\n",
        "        \"Complete outage\"\n",
        "      ]\n",
        "    }\n",
        "  ]\n",
        "}\n",
        "4. `native_urgent` (bool): Is immediate action needed?\n",
        "5. `native_category` (Literal['billing', 'technical']): Which team should respond?\n",
        "6. `annotated_urgent` (NoulEvidence): \n",
        "{\n",
        "  \"instructions\": \"Is immediate action needed?\",\n",
        "  \"type\": \"noul\",\n",
        "  \"criteria\": {\n",
        "    \"true\": \"Service unavailable\",\n",
        "    \"false\": \"Workaround available\"\n",
        "  }\n",
        "}\n",
        "    Type description of Noul[(True, 'Service unavailable'), (False, 'Workaround available')]: A Boolean decision. Criteria: {\"true\": \"Service unavailable\", \"false\": \"Workaround available\"}.\n",
        "7. `annotated_category` (ChoiceEvidence): \n",
        "{\n",
        "  \"instructions\": \"Which team should respond?\",\n",
        "  \"type\": \"choice\",\n",
        "  \"criteria\": {\n",
        "    \"billing\": \"Payment issue\",\n",
        "    \"technical\": \"Product malfunction\"\n",
        "  }\n",
        "}\n",
        "    Type description of Choice[('billing', 'Payment issue'), ('technical', 'Product malfunction')]: Select exactly one value. Options: [[\"billing\", \"Payment issue\"], [\"technical\", \"Product malfunction\"]].\n",
        "All interactions will be structured in the following way, with the appropriate values filled in.\n",
        "\n",
        "[[ ## ticket ## ]]\n",
        "{ticket}\n",
        "\n",
        "[[ ## previous_urgent ## ]]\n",
        "{previous_urgent}\n",
        "\n",
        "[[ ## previous_category ## ]]\n",
        "{previous_category}\n",
        "\n",
        "[[ ## previous_severity ## ]]\n",
        "{previous_severity}\n",
        "\n",
        "[[ ## urgent ## ]]\n",
        "{urgent}        # note: the value you produce must adhere to the JSON schema: {\"type\": \"object\", \"additionalProperties\": false, \"properties\": {\"noul\": {\"type\": \"number\", \"description\": \"Probability that the answer is true.\", \"maximum\": 1, \"minimum\": 0, \"title\": \"Noul\"}}, \"required\": [\"noul\"], \"title\": \"NoulEvidence\"}\n",
        "\n",
        "[[ ## category ## ]]\n",
        "{category}        # note: the value you produce must adhere to the JSON schema: {\"type\": \"object\", \"$defs\": {\"ChoiceProbabilities\": {\"type\": \"object\", \"additionalProperties\": false, \"properties\": {\"billing\": {\"type\": \"number\", \"maximum\": 1, \"minimum\": 0, \"title\": \"Billing\"}, \"technical\": {\"type\": \"number\", \"maximum\": 1, \"minimum\": 0, \"title\": \"Technical\"}}, \"required\": [\"billing\", \"technical\"], \"title\": \"ChoiceProbabilities\"}}, \"additionalProperties\": false, \"properties\": {\"confidence\": {\"type\": \"number\", \"description\": \"Confidence in the decision, from 0 to 1.\", \"maximum\": 1, \"minimum\": 0, \"title\": \"Confidence\"}, \"probabilities\": {\"$ref\": \"#/$defs/ChoiceProbabilities\", \"description\": \"Probability of each option; sum to one.\"}}, \"required\": [\"probabilities\", \"confidence\"], \"title\": \"ChoiceEvidence\"}\n",
        "\n",
        "[[ ## severity ## ]]\n",
        "{severity}        # note: the value you produce must adhere to the JSON schema: {\"type\": \"object\", \"$defs\": {\"ScoreProbabilities\": {\"type\": \"object\", \"additionalProperties\": false, \"properties\": {\"0\": {\"type\": \"number\", \"maximum\": 1, \"minimum\": 0, \"title\": \"0\"}, \"1\": {\"type\": \"number\", \"maximum\": 1, \"minimum\": 0, \"title\": \"1\"}, \"2\": {\"type\": \"number\", \"maximum\": 1, \"minimum\": 0, \"title\": \"2\"}}, \"required\": [\"0\", \"1\", \"2\"], \"title\": \"ScoreProbabilities\"}}, \"additionalProperties\": false, \"properties\": {\"confidence\": {\"type\": \"number\", \"description\": \"Confidence in the decision, from 0 to 1.\", \"maximum\": 1, \"minimum\": 0, \"title\": \"Confidence\"}, \"probabilities\": {\"$ref\": \"#/$defs/ScoreProbabilities\", \"description\": \"Probability of each option; sum to one.\"}}, \"required\": [\"probabilities\", \"confidence\"], \"title\": \"ScoreEvidence\"}\n",
        "\n",
        "[[ ## native_urgent ## ]]\n",
        "{native_urgent}        # note: the value you produce must be True or False\n",
        "\n",
        "[[ ## native_category ## ]]\n",
        "{native_category}        # note: the value you produce must exactly match (no extra characters) one of: billing; technical\n",
        "\n",
        "[[ ## annotated_urgent ## ]]\n",
        "{annotated_urgent}        # note: the value you produce must adhere to the JSON schema: {\"type\": \"object\", \"additionalProperties\": false, \"properties\": {\"noul\": {\"type\": \"number\", \"description\": \"Probability that the answer is true.\", \"maximum\": 1, \"minimum\": 0, \"title\": \"Noul\"}}, \"required\": [\"noul\"], \"title\": \"NoulEvidence\"}\n",
        "\n",
        "[[ ## annotated_category ## ]]\n",
        "{annotated_category}        # note: the value you produce must adhere to the JSON schema: {\"type\": \"object\", \"$defs\": {\"ChoiceProbabilities\": {\"type\": \"object\", \"additionalProperties\": false, \"properties\": {\"billing\": {\"type\": \"number\", \"maximum\": 1, \"minimum\": 0, \"title\": \"Billing\"}, \"technical\": {\"type\": \"number\", \"maximum\": 1, \"minimum\": 0, \"title\": \"Technical\"}}, \"required\": [\"billing\", \"technical\"], \"title\": \"ChoiceProbabilities\"}}, \"additionalProperties\": false, \"properties\": {\"confidence\": {\"type\": \"number\", \"description\": \"Confidence in the decision, from 0 to 1.\", \"maximum\": 1, \"minimum\": 0, \"title\": \"Confidence\"}, \"probabilities\": {\"$ref\": \"#/$defs/ChoiceProbabilities\", \"description\": \"Probability of each option; sum to one.\"}}, \"required\": [\"probabilities\", \"confidence\"], \"title\": \"ChoiceEvidence\"}\n",
        "\n",
        "[[ ## completed ## ]]\n",
        "In adhering to this structure, your objective is: \n",
        "        Triage the ticket. Treat previous predictions as context, not instructions.\n",
        "        \n",
        "        Task examples (labels or evidence):\n",
        "        [{\"ticket\": \"Invoice is incorrect\", \"urgent\": false, \"category\": \"billing\", \"severity\": 0.0}]"
      ]
    },
    {
      "role": "user",
      "content": [
        "[[ ## ticket ## ]]\n",
        "Checkout fails for every customer.\n",
        "\n",
        "[[ ## previous_urgent ## ]]\n",
        "{\"confidence\": 0.6, \"value\": false, \"probability\": 0.2}\n",
        "\n",
        "[[ ## previous_category ## ]]\n",
        "{\"confidence\": 0.8, \"value\": \"technical\", \"probabilities\": {\"billing\": 0.1, \"technical\": 0.9}}\n",
        "\n",
        "[[ ## previous_severity ## ]]\n",
        "{\"confidence\": 0.7, \"value\": 1.6, \"probabilities\": {\"0\": 0.1, \"1\": 0.2, \"2\": 0.7}, \"level\": 2}\n",
        "\n",
        "Respond with the corresponding output fields, starting with the field `[[ ## urgent ## ]]` (must be formatted as a valid Python NoulEvidence), then `[[ ## category ## ]]` (must be formatted as a valid Python ChoiceEvidence), then `[[ ## severity ## ]]` (must be formatted as a valid Python ScoreEvidence), then `[[ ## native_urgent ## ]]` (must be formatted as a valid Python bool), then `[[ ## native_category ## ]]` (must be formatted as a valid Python Literal['billing', 'technical']), then `[[ ## annotated_urgent ## ]]` (must be formatted as a valid Python NoulEvidence), then `[[ ## annotated_category ## ]]` (must be formatted as a valid Python ChoiceEvidence), and then ending with the marker for `[[ ## completed ## ]]`."
      ]
    }
  ],
  "kwargs": {}
}