Início Rápido: Usar detecção de fundamentação (versão prévia)

Esta seção mostra como funciona uma solicitação de exemplo com o cURL. Cole o comando abaixo em um editor de texto e faça as seguintes alterações.

1. substitua <endpoint> pela URL do ponto de extremidade associada ao recurso.

2. Substitua <your_subscription_key> por uma das chaves para o recurso.

3. Opcionalmente, substitua os campos "query" ou "text" no corpo por um texto próprio que você deseja analisar.

   curl --location --request POST '<endpoint>/contentsafety/text:detectGroundedness?api-version=2024-09-15-preview' \
   --header 'Ocp-Apim-Subscription-Key: <your_subscription_key>' \
   --header 'Content-Type: application/json' \
   --data-raw '{
     "domain": "Generic",
     "task": "QnA",
     "qna": {
       "query": "How much does she currently get paid per hour at the bank?"
     },
     "text": "12/hour",
     "groundingSources": [
       "I'm 21 years old and I need to make a decision about the next two years of my life. Within a week. I currently work for a bank that requires strict sales goals to meet. IF they aren't met three times (three months) you're canned. They pay me 10/hour and it's not unheard of to get a raise in 6ish months. The issue is, **I'm not a salesperson**. That's not my personality. I'm amazing at customer service, I have the most positive customer service \"reports\" done about me in the short time I've worked here. A coworker asked \"do you ask for people to fill these out? you have a ton\". That being said, I have a job opportunity at Chase Bank as a part time teller. What makes this decision so hard is that at my current job, I get 40 hours and Chase could only offer me 20 hours/week. Drive time to my current job is also 21 miles **one way** while Chase is literally 1.8 miles from my house, allowing me to go home for lunch. I do have an apartment and an awesome roommate that I know wont be late on his portion of rent, so paying bills with 20hours a week isn't the issue. It's the spending money and being broke all the time.\n\nI previously worked at Wal-Mart and took home just about 400 dollars every other week. So I know i can survive on this income. I just don't know whether I should go for Chase as I could definitely see myself having a career there. I'm a math major likely going to become an actuary, so Chase could provide excellent opportunities for me **eventually**."
     ],
     "reasoning": false
   }'
   

Abra um prompt de comando e execute o comando do cURL.

Crie um novo arquivo Python denominado quickstart.py. Abra o novo arquivo em seu IDE ou editor preferido.

1. Substitua o conteúdo do quickstart.py pelo código a seguir. Insira a URL do ponto de extremidade e a chave nos campos apropriados. Opcionalmente, substitua os campos "query" ou "text" no corpo por um texto próprio que você deseja analisar.

   import http.client
   import json
   
   endpoint = "<your_custom_subdomain>.cognitiveservices.azure.com"
   conn = http.client.HTTPSConnection(endpoint)
   payload = json.dumps({
     "domain": "Generic",
     "task": "QnA",
     "qna": {
       "query": "How much does she currently get paid per hour at the bank?"
     },
     "text": "12/hour",
     "groundingSources": [
       "I'm 21 years old and I need to make a decision about the next two years of my life. Within a week. I currently work for a bank that requires strict sales goals to meet. IF they aren't met three times (three months) you're canned. They pay me 10/hour and it's not unheard of to get a raise in 6ish months. The issue is, **I'm not a salesperson**. That's not my personality. I'm amazing at customer service, I have the most positive customer service \"reports\" done about me in the short time I've worked here. A coworker asked \"do you ask for people to fill these out? you have a ton\". That being said, I have a job opportunity at Chase Bank as a part time teller. What makes this decision so hard is that at my current job, I get 40 hours and Chase could only offer me 20 hours/week. Drive time to my current job is also 21 miles **one way** while Chase is literally 1.8 miles from my house, allowing me to go home for lunch. I do have an apartment and an awesome roommate that I know wont be late on his portion of rent, so paying bills with 20hours a week isn't the issue. It's the spending money and being broke all the time.\n\nI previously worked at Wal-Mart and took home just about 400 dollars every other week. So I know i can survive on this income. I just don't know whether I should go for Chase as I could definitely see myself having a career there. I'm a math major likely going to become an actuary, so Chase could provide excellent opportunities for me **eventually**."
     ],
     "reasoning": false
   })
   headers = {
     'Ocp-Apim-Subscription-Key': '<your_subscription_key>',
     'Content-Type': 'application/json'
   }
   conn.request("POST", "/contentsafety/text:detectGroundedness?api-version=2024-09-15-preview", payload, headers)
   res = conn.getresponse()
   data = res.read()
   print(data.decode("utf-8"))
   

   Importante

   Lembre-se de remover a chave do código quando terminar e nunca poste-a publicamente. Para produção, use uma maneira segura de armazenar e acessar suas credenciais. Para saber mais, veja Azure Key Vault

2. Execute o aplicativo com o comando python:

   python quickstart.py
   

   Leva alguns minutos para obter a resposta.

Esta seção mostra como funciona uma solicitação de exemplo com o cURL. Cole o comando abaixo em um editor de texto e faça as seguintes alterações.

1. Substitua <endpoint> pelo URL do ponto de extremidade associado ao recurso de Segurança de Conteúdo de IA do Azure.

2. Substitua <your_subscription_key> por uma das chaves para o recurso.

3. Substitua <your_OpenAI_endpoint> pelo URL do ponto de extremidade associado ao recurso do OpenAI do Azure.

4. Substitua <your_deployment_name> pelo nome da implantação do OpenAI do Azure.

5. Opcionalmente, substitua os campos "query" ou "text" no corpo por um texto próprio que você deseja analisar.

   curl --location --request POST '<endpoint>/contentsafety/text:detectGroundedness?api-version=2024-09-15-preview' \
   --header 'Ocp-Apim-Subscription-Key: <your_subscription_key>' \
   --header 'Content-Type: application/json' \
   --data-raw '{
     "domain": "Generic",
     "task": "QnA",
     "qna": {
       "query": "How much does she currently get paid per hour at the bank?"
     },
     "text": "12/hour",
     "groundingSources": [
       "I'm 21 years old and I need to make a decision about the next two years of my life. Within a week. I currently work for a bank that requires strict sales goals to meet. If they aren't met three times (three months) you're canned. They pay me 10/hour and it's not unheard of to get a raise in 6ish months. The issue is, **I'm not a salesperson**. That's not my personality. I'm amazing at customer service, I have the most positive customer service \"reports\" done about me in the short time I've worked here. A coworker asked \"do you ask for people to fill these out? you have a ton\". That being said, I have a job opportunity at Chase Bank as a part time teller. What makes this decision so hard is that at my current job, I get 40 hours and Chase could only offer me 20 hours/week. Drive time to my current job is also 21 miles **one way** while Chase is literally 1.8 miles from my house, allowing me to go home for lunch. I do have an apartment and an awesome roommate that I know wont be late on his portion of rent, so paying bills with 20hours a week isn't the issue. It's the spending money and being broke all the time.\n\nI previously worked at Wal-Mart and took home just about 400 dollars every other week. So I know i can survive on this income. I just don't know whether I should go for Chase as I could definitely see myself having a career there. I'm a math major likely going to become an actuary, so Chase could provide excellent opportunities for me **eventually**."
     ],
     "reasoning": true,
     "llmResource": {
           "resourceType": "AzureOpenAI",
           "azureOpenAIEndpoint": "<your_OpenAI_endpoint>",
           "azureOpenAIDeploymentName": "<your_deployment_name>"
   }'
   

6. Abra um prompt de comando e execute o comando do cURL.

Crie um novo arquivo Python denominado quickstart.py. Abra o novo arquivo em seu IDE ou editor preferido.

1. Substitua o conteúdo do quickstart.py pelo código a seguir. Insira a URL do ponto de extremidade e a chave nos campos apropriados. Insira também o ponto de extremidade e o nome de implantação do OpenAI do Azure. Opcionalmente, substitua os campos "query" ou "text" no corpo por um texto próprio que você deseja analisar.

   import http.client
   import json
   
   conn = http.client.HTTPSConnection("<endpoint>/contentsafety/text:detectGroundedness?api-version=2024-09-15-preview")
   payload = json.dumps({
     "domain": "Generic",
     "task": "QnA",
     "qna": {
       "query": "How much does she currently get paid per hour at the bank?"
     },
     "text": "12/hour",
     "groundingSources": [
       "I'm 21 years old and I need to make a decision about the next two years of my life. Within a week. I currently work for a bank that requires strict sales goals to meet. IF they aren't met three times (three months) you're canned. They pay me 10/hour and it's not unheard of to get a raise in 6ish months. The issue is, **I'm not a salesperson**. That's not my personality. I'm amazing at customer service, I have the most positive customer service \"reports\" done about me in the short time I've worked here. A coworker asked \"do you ask for people to fill these out? you have a ton\". That being said, I have a job opportunity at Chase Bank as a part time teller. What makes this decision so hard is that at my current job, I get 40 hours and Chase could only offer me 20 hours/week. Drive time to my current job is also 21 miles **one way** while Chase is literally 1.8 miles from my house, allowing me to go home for lunch. I do have an apartment and an awesome roommate that I know wont be late on his portion of rent, so paying bills with 20hours a week isn't the issue. It's the spending money and being broke all the time.\n\nI previously worked at Wal-Mart and took home just about 400 dollars every other week. So I know i can survive on this income. I just don't know whether I should go for Chase as I could definitely see myself having a career there. I'm a math major likely going to become an actuary, so Chase could provide excellent opportunities for me **eventually**."
     ],
     "reasoning": True
     "llmResource": {
      "resourceType": "AzureOpenAI",
      "azureOpenAIEndpoint": "<your_OpenAI_endpoint>",
      "azureOpenAIDeploymentName": "<your_deployment_name>"
     }
   })
   headers = {
     'Ocp-Apim-Subscription-Key': '<your_subscription_key>',
     'Content-Type': 'application/json'
   }
   conn.request("POST", "/contentsafety/text:detectGroundedness?api-version=2024-09-15-preview", payload, headers)
   res = conn.getresponse()
   data = res.read()
   print(data.decode("utf-8"))
   

2. Execute o aplicativo com o comando python:

   python quickstart.py
   

   Leva alguns minutos para obter a resposta.

Essa seção demonstra uma solicitação de exemplo usando cURL. Substitua os espaços reservados conforme necessário:

• Substitua <endpoint> pelo URL do ponto de extremidade do recurso.
• Substitua <your_subscription_key> por sua chave de assinatura.
• Opcionalmente, substitua o campo "texto" pelo texto que você quer analisar.

curl --location --request POST '<endpoint>/contentsafety/text:detectGroundedness?api-version=2024-09-15-preview' \
--header 'Ocp-Apim-Subscription-Key: <your_subscription_key>' \
--header 'Content-Type: application/json' \
--data-raw '{
  "domain": "Generic",
  "task": "Summarization",
  "text": "The patient name is Kevin.",
  "groundingSources": [
    "The patient name is Jane."
  ],
  "correction": true,
  "llmResource": {
        "resourceType": "AzureOpenAI",
        "azureOpenAIEndpoint": "<your_OpenAI_endpoint>",
        "azureOpenAIDeploymentName": "<your_deployment_name>"
  }
}'

Crie um script Python chamado quickstart.py e inclua o código a seguir. Atualize o URL e a chave do ponto de extremidade conforme apropriado:

conn = http.client.HTTPSConnection("<endpoint>/contentsafety/text:detectGroundedness?api-version=2024-09-15-preview")
payload = json.dumps({
  "domain": "Generic",
  "task": "Summarization",
  "text": "The patient name is Kevin.",
  "groundingSources": [
    "The patient name is Jane."
  ],
  "correction": True,
  "llmResource": {
   "resourceType": "AzureOpenAI",
   "azureOpenAIEndpoint": "<your_OpenAI_endpoint>",
   "azureOpenAIDeploymentName": "<your_deployment_name>"
  }
})
headers = {
  'Ocp-Apim-Subscription-Key': '<your_subscription_key>',
  'Content-Type': 'application/json'
}
conn.request("POST", "/contentsafety/text:detectGroundedness?api-version=2024-09-15-preview", payload, headers)
res = conn.getresponse()
data = res.read()
print(data.decode("utf-8"))