Make Reader¶

我们将演示 LlamaIndex 如何与您的 Make.com 工作流集成，通过将 GPT 索引的响应发送到情景 Webhook。

如果您在 colab 上打开此 Notebook，您可能需要安装 LlamaIndex 🦙。

In [ ]

%pip install llama-index-readers-make-com

%pip install llama-index-readers-make-com

In [ ]

!pip install llama-index

!pip install llama-index

In [ ]

import logging
import sys

logging.basicConfig(stream=sys.stdout, level=logging.INFO)
logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

import logging import sys logging.basicConfig(stream=sys.stdout, level=logging.INFO) logging.getLogger().addHandler(logging.StreamHandler(stream=sys.stdout))

In [ ]

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
from llama_index.readers.make_com import MakeWrapper

from llama_index.core import VectorStoreIndex, SimpleDirectoryReader from llama_index.readers.make_com import MakeWrapper

下载数据

In [ ]

!mkdir -p 'data/paul_graham/'
!wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

!mkdir -p 'data/paul_graham/' !wget 'https://raw.githubusercontent.com/run-llama/llama_index/main/docs/docs/examples/data/paul_graham/paul_graham_essay.txt' -O 'data/paul_graham/paul_graham_essay.txt'

In [ ]

documents = SimpleDirectoryReader("./data/paul_graham/").load_data()
index = VectorStoreIndex.from_documents(documents=documents)

documents = SimpleDirectoryReader("./data/paul_graham/").load_data() index = VectorStoreIndex.from_documents(documents=documents)

In [ ]

# set Logging to DEBUG for more detailed outputs
# query index
query_str = "What did the author do growing up?"
query_engine = index.as_query_engine()
response = query_engine.query(query_str)

# set Logging to DEBUG for more detailed outputs # query index query_str = "What did the author do growing up?" query_engine = index.as_query_engine() response = query_engine.query(query_str)

In [ ]

# Send response to Make.com webhook
wrapper = MakeWrapper()
wrapper.pass_response_to_webhook("<webhook_url>", response, query_str)

# Send response to Make.com webhook wrapper = MakeWrapper() wrapper.pass_response_to_webhook("", response, query_str)