跳到主要內容
Open In ColabOpen on GitHub

Cogniswitch Toolkit

Cogniswitch 用於建置可投入生產的應用程式，這些應用程式可以順暢地使用、組織和檢索知識。Cogniswitch 使用您選擇的框架（在本例中為 Langchain），有助於減輕在選擇正確的儲存和檢索格式時的決策壓力。它還可以消除在產生的回應方面的可靠性問題和幻覺。

設定​

訪問此頁面註冊 Cogniswitch 帳戶。

  • 使用您的電子郵件註冊並驗證您的註冊

  • 您將收到一封郵件，其中包含用於服務的平台令牌和 oauth 令牌。

%pip install -qU langchain-community

導入必要的庫​

import warnings

warnings.filterwarnings("ignore")

import os

from langchain.agents.agent_toolkits import create_conversational_retrieval_agent
from langchain_community.agent_toolkits import CogniswitchToolkit
from langchain_openai import ChatOpenAI

Cogniswitch 平台令牌、OAuth 令牌和 OpenAI API 金鑰​

cs_token = "Your CogniSwitch token"
OAI_token = "Your OpenAI API token"
oauth_token = "Your CogniSwitch authentication token"

os.environ["OPENAI_API_KEY"] = OAI_token

使用憑證實例化 cogniswitch 工具套件​

cogniswitch_toolkit = CogniswitchToolkit(
    cs_token=cs_token, OAI_token=OAI_token, apiKey=oauth_token
)

取得 cogniswitch 工具列表​

tool_lst = cogniswitch_toolkit.get_tools()

實例化 LLM​

llm = ChatOpenAI(
    temperature=0,
    openai_api_key=OAI_token,
    max_tokens=1500,
    model_name="gpt-3.5-turbo-0613",
)

將 LLM 與工具套件一起使用​

使用 LLM 和工具套件建立代理​

agent_executor = create_conversational_retrieval_agent(llm, tool_lst, verbose=False)

調用代理以發布 URL​

response = agent_executor.invoke("upload this url https://cogniswitch.ai/developer")

print(response["output"])
The URL https://cogniswitch.ai/developer has been uploaded successfully. The status of the document is currently being processed. You will receive an email notification once the processing is complete.

調用代理以發布檔案​

response = agent_executor.invoke("upload this file example_file.txt")

print(response["output"])
The file example_file.txt has been uploaded successfully. The status of the document is currently being processed. You will receive an email notification once the processing is complete.

調用代理以取得文件狀態​

response = agent_executor.invoke("Tell me the status of this document example_file.txt")

print(response["output"])
The status of the document example_file.txt is as follows:

- Created On: 2024-01-22T19:07:42.000+00:00
- Modified On: 2024-01-22T19:07:42.000+00:00
- Document Entry ID: 153
- Status: 0 (Processing)
- Original File Name: example_file.txt
- Saved File Name: 1705950460069example_file29393011.txt

The document is currently being processed.

使用查詢調用代理並取得答案​

response = agent_executor.invoke("How can cogniswitch help develop GenAI applications?")

print(response["output"])
CogniSwitch can help develop GenAI applications in several ways:

1. Knowledge Extraction: CogniSwitch can extract knowledge from various sources such as documents, websites, and databases. It can analyze and store data from these sources, making it easier to access and utilize the information for GenAI applications.

2. Natural Language Processing: CogniSwitch has advanced natural language processing capabilities. It can understand and interpret human language, allowing GenAI applications to interact with users in a more conversational and intuitive manner.

3. Sentiment Analysis: CogniSwitch can analyze the sentiment of text data, such as customer reviews or social media posts. This can be useful in developing GenAI applications that can understand and respond to the emotions and opinions of users.

4. Knowledge Base Integration: CogniSwitch can integrate with existing knowledge bases or create new ones. This allows GenAI applications to access a vast amount of information and provide accurate and relevant responses to user queries.

5. Document Analysis: CogniSwitch can analyze documents and extract key information such as entities, relationships, and concepts. This can be valuable in developing GenAI applications that can understand and process large amounts of textual data.

Overall, CogniSwitch provides a range of AI-powered capabilities that can enhance the development of GenAI applications by enabling knowledge extraction, natural language processing, sentiment analysis, knowledge base integration, and document analysis.

此頁面是否有幫助？