Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.
# Model Titan Teks Amazon
Model Amazon Titan Text mendukung parameter inferensi berikut.
Untuk informasi selengkapnya tentang pedoman teknik prompt Titan teks, lihat [Pedoman Teknik Prompt Titan Teks](https://d2eo22ngex1n9g.cloudfront.net/Documentation/User+Guides/Titan/Amazon+Titan+Text+Prompt+Engineering+Guidelines.pdf).
Untuk informasi lebih lanjut tentang Titan model, lihat[Ikhtisar Titan model Amazon](titan-models.md).
**Topics**
+ [Permintaan dan tanggapan](#model-parameters-titan-request-response)
+ [Contoh kode](#inference-titan-code)
## Permintaan dan tanggapan
Badan permintaan diteruskan di `body` bidang [InvokeModelWithResponseStream](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModelWithResponseStream.html)permintaan [InvokeModel](https://docs.aws.amazon.com/bedrock/latest/APIReference/API_runtime_InvokeModel.html)atau permintaan.
------
#### [ Request ]
```
{
"inputText": string,
"textGenerationConfig": {
"temperature": float,
"topP": float,
"maxTokenCount": int,
"stopSequences": [string]
}
}
```
Parameter-parameter berikut diperlukan:
+ **InputText** — Prompt untuk menyediakan model untuk menghasilkan respons. Untuk menghasilkan tanggapan dalam gaya percakapan, kirimkan prompt dengan menggunakan format berikut:
```
"inputText": "User: {{}}\nBot:"
```
Format ini menunjukkan kepada model bahwa ia harus merespons pada baris baru setelah pengguna memberikan prompt.
`textGenerationConfig`Itu opsional. Anda dapat menggunakannya untuk mengonfigurasi [parameter inferensi](inference-parameters.md) berikut:
+ **suhu** — Gunakan nilai yang lebih rendah untuk mengurangi keacakan dalam respons.
****
[See the AWS documentation website for more details](http://docs.aws.amazon.com/id_id/bedrock/latest/userguide/model-parameters-titan-text.html)
+ **TopP** — Gunakan nilai yang lebih rendah untuk mengabaikan opsi yang kurang mungkin dan mengurangi keragaman respons.
****
[See the AWS documentation website for more details](http://docs.aws.amazon.com/id_id/bedrock/latest/userguide/model-parameters-titan-text.html)
+ **maxTokenCount**— Tentukan jumlah maksimum token yang akan dihasilkan dalam respons. Batas token maksimum diberlakukan secara ketat.
****
[See the AWS documentation website for more details](http://docs.aws.amazon.com/id_id/bedrock/latest/userguide/model-parameters-titan-text.html)
+ **StopSequences** - Tentukan urutan karakter untuk menunjukkan di mana model harus berhenti.
------
#### [ InvokeModel Response ]
```
{
"inputTextTokenCount": int,
"results": [{
"tokenCount": int,
"outputText": "\n{{}}\n",
"completionReason": "string"
}]
}
```
Badan respons berisi bidang-bidang berikut:
+ **inputTextTokenHitung** — Jumlah token dalam prompt.
+ **hasil** — Sebuah array dari satu item, sebuah objek yang berisi bidang-bidang berikut:
+ **TokenCount** — Jumlah token dalam respons.
+ **OutputText** — Teks dalam tanggapan.
+ **CompletionReason** — Alasan respon selesai dihasilkan. Alasan berikut mungkin:
+ SELESAI - Respons sepenuhnya dihasilkan.
+ PANJANG — Respons terpotong karena panjang respons yang Anda tetapkan.
+ STOP\_CRITERIA\_MET — Respons terpotong karena kriteria berhenti tercapai.
+ RAG\_QUERY\_WHEN\_RAG\_DISABLED — Fitur ini dinonaktifkan dan tidak dapat menyelesaikan kueri.
+ CONTENT\_FILTERED - Konten disaring atau dihapus oleh filter konten yang diterapkan.
------
#### [ InvokeModelWithResponseStream Response ]
Setiap potongan teks di badan aliran respons dalam format berikut. Anda harus memecahkan kode `bytes` bidang (lihat [Kirim satu prompt dengan InvokeModel](inference-invoke.md) contoh).
```
{
"chunk": {
"bytes": b'{
"index": int,
"inputTextTokenCount": int,
"totalOutputTextTokenCount": int,
"outputText": "{{}}",
"completionReason": "string"
}'
}
}
```
+ **indeks** — Indeks potongan dalam respons streaming.
+ **inputTextTokenHitung** — Jumlah token dalam prompt.
+ **totalOutputTextTokenCount**— Jumlah token dalam respons.
+ **OutputText** — Teks dalam tanggapan.
+ **CompletionReason** — Alasan respon selesai dihasilkan. Alasan berikut mungkin terjadi.
+ SELESAI - Respons sepenuhnya dihasilkan.
+ PANJANG — Respons terpotong karena panjang respons yang Anda tetapkan.
+ STOP\_CRITERIA\_MET — Respons terpotong karena kriteria berhenti tercapai.
+ RAG\_QUERY\_WHEN\_RAG\_DISABLED — Fitur ini dinonaktifkan dan tidak dapat menyelesaikan kueri.
+ CONTENT\_FILTERED — Isi disaring atau dihapus oleh filter yang diterapkan.
------
## Contoh kode
Contoh berikut menunjukkan cara menjalankan inferensi dengan model Amazon Titan Text Premier dengan Python SDK.
```
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to create a list of action items from a meeting transcript
with the Amazon Titan Text model (on demand).
"""
import json
import logging
import boto3
from botocore.exceptions import ClientError
class ImageError(Exception):
"Custom exception for errors returned by Amazon Titan Text models"
def __init__(self, message):
self.message = message
logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)
def generate_text(model_id, body):
"""
Generate text using Amazon Titan Text models on demand.
Args:
model_id (str): The model ID to use.
body (str) : The request body to use.
Returns:
response (json): The response from the model.
"""
logger.info(
"Generating text with Amazon Titan Text model %s", model_id)
bedrock = boto3.client(service_name='bedrock-runtime')
accept = "application/json"
content_type = "application/json"
response = bedrock.invoke_model(
body=body, modelId=model_id, accept=accept, contentType=content_type
)
response_body = json.loads(response.get("body").read())
finish_reason = response_body.get("error")
if finish_reason is not None:
raise ImageError(f"Text generation error. Error is {finish_reason}")
logger.info(
"Successfully generated text with Amazon Titan Text model %s", model_id)
return response_body
def main():
"""
Entrypoint for Amazon Titan Text model example.
"""
try:
logging.basicConfig(level=logging.INFO,
format="%(levelname)s: %(message)s")
# You can replace the model_id with any other Titan Text Models
# Titan Text Model family model_id is as mentioned below:
# amazon.titan-text-premier-v1:0, amazon.titan-text-express-v1, amazon.titan-text-lite-v1
model_id = 'amazon.titan-text-premier-v1:0'
prompt = """Meeting transcript: Miguel: Hi Brant, I want to discuss the workstream
for our new product launch Brant: Sure Miguel, is there anything in particular you want
to discuss? Miguel: Yes, I want to talk about how users enter into the product.
Brant: Ok, in that case let me add in Namita. Namita: Hey everyone
Brant: Hi Namita, Miguel wants to discuss how users enter into the product.
Miguel: its too complicated and we should remove friction.
for example, why do I need to fill out additional forms?
I also find it difficult to find where to access the product
when I first land on the landing page. Brant: I would also add that
I think there are too many steps. Namita: Ok, I can work on the
landing page to make the product more discoverable but brant
can you work on the additonal forms? Brant: Yes but I would need
to work with James from another team as he needs to unblock the sign up workflow.
Miguel can you document any other concerns so that I can discuss with James only once?
Miguel: Sure.
From the meeting transcript above, Create a list of action items for each person. """
body = json.dumps({
"inputText": prompt,
"textGenerationConfig": {
"maxTokenCount": 3072,
"stopSequences": [],
"temperature": 0.7,
"topP": 0.9
}
})
response_body = generate_text(model_id, body)
print(f"Input token count: {response_body['inputTextTokenCount']}")
for result in response_body['results']:
print(f"Token count: {result['tokenCount']}")
print(f"Output text: {result['outputText']}")
print(f"Completion reason: {result['completionReason']}")
except ClientError as err:
message = err.response["Error"]["Message"]
logger.error("A client error occurred: %s", message)
print("A client error occured: " +
format(message))
except ImageError as err:
logger.error(err.message)
print(err.message)
else:
print(
f"Finished generating text with the Amazon Titan Text Premier model {model_id}.")
if __name__ == "__main__":
main()
```
Contoh berikut menunjukkan cara menjalankan inferensi dengan Titan Text G1 - Express model Amazon dengan Python SDK.
```
# Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
# SPDX-License-Identifier: Apache-2.0
"""
Shows how to create a list of action items from a meeting transcript
with the Amazon &titan-text-express; model (on demand).
"""
import json
import logging
import boto3
from botocore.exceptions import ClientError
class ImageError(Exception):
"Custom exception for errors returned by Amazon &titan-text-express; model"
def __init__(self, message):
self.message = message
logger = logging.getLogger(__name__)
logging.basicConfig(level=logging.INFO)
def generate_text(model_id, body):
"""
Generate text using Amazon &titan-text-express; model on demand.
Args:
model_id (str): The model ID to use.
body (str) : The request body to use.
Returns:
response (json): The response from the model.
"""
logger.info(
"Generating text with Amazon &titan-text-express; model %s", model_id)
bedrock = boto3.client(service_name='bedrock-runtime')
accept = "application/json"
content_type = "application/json"
response = bedrock.invoke_model(
body=body, modelId=model_id, accept=accept, contentType=content_type
)
response_body = json.loads(response.get("body").read())
finish_reason = response_body.get("error")
if finish_reason is not None:
raise ImageError(f"Text generation error. Error is {finish_reason}")
logger.info(
"Successfully generated text with Amazon &titan-text-express; model %s", model_id)
return response_body
def main():
"""
Entrypoint for Amazon &titan-text-express; example.
"""
try:
logging.basicConfig(level=logging.INFO,
format="%(levelname)s: %(message)s")
model_id = 'amazon.titan-text-express-v1'
prompt = """Meeting transcript: Miguel: Hi Brant, I want to discuss the workstream
for our new product launch Brant: Sure Miguel, is there anything in particular you want
to discuss? Miguel: Yes, I want to talk about how users enter into the product.
Brant: Ok, in that case let me add in Namita. Namita: Hey everyone
Brant: Hi Namita, Miguel wants to discuss how users enter into the product.
Miguel: its too complicated and we should remove friction.
for example, why do I need to fill out additional forms?
I also find it difficult to find where to access the product
when I first land on the landing page. Brant: I would also add that
I think there are too many steps. Namita: Ok, I can work on the
landing page to make the product more discoverable but brant
can you work on the additonal forms? Brant: Yes but I would need
to work with James from another team as he needs to unblock the sign up workflow.
Miguel can you document any other concerns so that I can discuss with James only once?
Miguel: Sure.
From the meeting transcript above, Create a list of action items for each person. """
body = json.dumps({
"inputText": prompt,
"textGenerationConfig": {
"maxTokenCount": 4096,
"stopSequences": [],
"temperature": 0,
"topP": 1
}
})
response_body = generate_text(model_id, body)
print(f"Input token count: {response_body['inputTextTokenCount']}")
for result in response_body['results']:
print(f"Token count: {result['tokenCount']}")
print(f"Output text: {result['outputText']}")
print(f"Completion reason: {result['completionReason']}")
except ClientError as err:
message = err.response["Error"]["Message"]
logger.error("A client error occurred: %s", message)
print("A client error occured: " +
format(message))
except ImageError as err:
logger.error(err.message)
print(err.message)
else:
print(
f"Finished generating text with the Amazon &titan-text-express; model {model_id}.")
if __name__ == "__main__":
main()
```