Name | llama-index-readers-wordlift JSON |
Version |
0.1.1
JSON |
| download |
home_page | |
Summary | llama-index readers wordlift integration |
upload_time | 2024-02-12 23:47:54 |
maintainer | |
docs_url | None |
author | Your Name |
requires_python | >=3.8.1,<3.12 |
license | MIT |
keywords |
|
VCS |
|
bugtrack_url |
|
requirements |
No requirements were recorded.
|
Travis-CI |
No Travis.
|
coveralls test coverage |
No coveralls.
|
# WordLift Reader
The WordLift GraphQL Reader is a connector to fetch and transform data from a WordLift Knowledge Graph using your the WordLift Key. The connector provides a convenient way to load data from WordLift using a GraphQL query and transform it into a list of documents for further processing.
## Usage
To use the WordLift GraphQL Reader, follow the steps below:
1. Set up the necessary configuration options, such as the API endpoint, headers, query, fields, and configuration options (make sure you have with you the [Wordlift Key](https://docs.wordlift.io/pages/key-concepts/#wordlift-key)).
2. Create an instance of the `WordLiftLoader` class, passing in the configuration options.
3. Use the `load_data` method to fetch and transform the data.
4. Process the loaded documents as needed.
Here's an example of how to use the WordLift GraphQL Reader:
```python
import json
from llama_index import VectorStoreIndex
from llama_index.readers.schema import Document
from langchain.llms import OpenAI
from llama_hub.wordlift import WordLiftLoader
# Set up the necessary configuration options
endpoint = "https://api.wordlift.io/graphql"
headers = {
"Authorization": "<YOUR_WORDLIFT_KEY>",
"Content-Type": "application/json",
}
query = """
# Your GraphQL query here
"""
fields = "<YOUR_FIELDS>"
config_options = {
"text_fields": ["<YOUR_TEXT_FIELDS>"],
"metadata_fields": ["<YOUR_METADATA_FIELDS>"],
}
# Create an instance of the WordLiftLoader
reader = WordLiftLoader(endpoint, headers, query, fields, config_options)
# Load the data
documents = reader.load_data()
# Convert the documents
converted_doc = []
for doc in documents:
converted_doc_id = json.dumps(doc.doc_id)
converted_doc.append(
Document(
text=doc.text,
doc_id=converted_doc_id,
embedding=doc.embedding,
doc_hash=doc.doc_hash,
extra_info=doc.extra_info,
)
)
# Create the index and query engine
index = VectorStoreIndex.from_documents(converted_doc)
query_engine = index.as_query_engine()
# Perform a query
result = query_engine.query("<YOUR_QUERY>")
# Process the result as needed
logging.info("Result: %s", result)
```
This loader is designed to be used as a way to load data from WordLift KGs into [LlamaIndex](https://github.com/emptycrown/llama-hub/tree/main/llama_hub/apify/actor#:~:text=load%20data%20into-,LlamaIndex,-and/or%20subsequently) and/or subsequently used as a Tool in a [LangChain](https://github.com/hwchase17/langchain) Agent.
Raw data
{
"_id": null,
"home_page": "",
"name": "llama-index-readers-wordlift",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8.1,<3.12",
"maintainer_email": "",
"keywords": "",
"author": "Your Name",
"author_email": "you@example.com",
"download_url": "https://files.pythonhosted.org/packages/87/57/6ea2331f8317bddb6fbd2da917ba84c7f55283d1ffe0bf03920f3a294973/llama_index_readers_wordlift-0.1.1.tar.gz",
"platform": null,
"description": "# WordLift Reader\n\nThe WordLift GraphQL Reader is a connector to fetch and transform data from a WordLift Knowledge Graph using your the WordLift Key. The connector provides a convenient way to load data from WordLift using a GraphQL query and transform it into a list of documents for further processing.\n\n## Usage\n\nTo use the WordLift GraphQL Reader, follow the steps below:\n\n1. Set up the necessary configuration options, such as the API endpoint, headers, query, fields, and configuration options (make sure you have with you the [Wordlift Key](https://docs.wordlift.io/pages/key-concepts/#wordlift-key)).\n2. Create an instance of the `WordLiftLoader` class, passing in the configuration options.\n3. Use the `load_data` method to fetch and transform the data.\n4. Process the loaded documents as needed.\n\nHere's an example of how to use the WordLift GraphQL Reader:\n\n```python\nimport json\nfrom llama_index import VectorStoreIndex\nfrom llama_index.readers.schema import Document\nfrom langchain.llms import OpenAI\nfrom llama_hub.wordlift import WordLiftLoader\n\n# Set up the necessary configuration options\nendpoint = \"https://api.wordlift.io/graphql\"\nheaders = {\n \"Authorization\": \"<YOUR_WORDLIFT_KEY>\",\n \"Content-Type\": \"application/json\",\n}\n\nquery = \"\"\"\n# Your GraphQL query here\n\"\"\"\nfields = \"<YOUR_FIELDS>\"\nconfig_options = {\n \"text_fields\": [\"<YOUR_TEXT_FIELDS>\"],\n \"metadata_fields\": [\"<YOUR_METADATA_FIELDS>\"],\n}\n# Create an instance of the WordLiftLoader\nreader = WordLiftLoader(endpoint, headers, query, fields, config_options)\n\n# Load the data\ndocuments = reader.load_data()\n\n# Convert the documents\nconverted_doc = []\nfor doc in documents:\n converted_doc_id = json.dumps(doc.doc_id)\n converted_doc.append(\n Document(\n text=doc.text,\n doc_id=converted_doc_id,\n embedding=doc.embedding,\n doc_hash=doc.doc_hash,\n extra_info=doc.extra_info,\n )\n )\n\n# Create the index and query engine\nindex = VectorStoreIndex.from_documents(converted_doc)\nquery_engine = index.as_query_engine()\n\n# Perform a query\nresult = query_engine.query(\"<YOUR_QUERY>\")\n\n# Process the result as needed\nlogging.info(\"Result: %s\", result)\n```\n\nThis loader is designed to be used as a way to load data from WordLift KGs into [LlamaIndex](https://github.com/emptycrown/llama-hub/tree/main/llama_hub/apify/actor#:~:text=load%20data%20into-,LlamaIndex,-and/or%20subsequently) and/or subsequently used as a Tool in a [LangChain](https://github.com/hwchase17/langchain) Agent.\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "llama-index readers wordlift integration",
"version": "0.1.1",
"project_urls": null,
"split_keywords": [],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "23265a3d4ddaaa51000943ada232bcbb36336df240f7f0e8199e3782aca11d3f",
"md5": "98690eccc8aa360561974c316d00f090",
"sha256": "776a93382209143819cf7bdd6c5a087d272f525a82727cec1326516f2526545e"
},
"downloads": -1,
"filename": "llama_index_readers_wordlift-0.1.1-py3-none-any.whl",
"has_sig": false,
"md5_digest": "98690eccc8aa360561974c316d00f090",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8.1,<3.12",
"size": 5514,
"upload_time": "2024-02-12T23:47:53",
"upload_time_iso_8601": "2024-02-12T23:47:53.256846Z",
"url": "https://files.pythonhosted.org/packages/23/26/5a3d4ddaaa51000943ada232bcbb36336df240f7f0e8199e3782aca11d3f/llama_index_readers_wordlift-0.1.1-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "87576ea2331f8317bddb6fbd2da917ba84c7f55283d1ffe0bf03920f3a294973",
"md5": "92875f1975f8754d7e6509ffe2396601",
"sha256": "42225e23200745faeed33dcd946100cd6538fb1a06a4551893795fec15144dd2"
},
"downloads": -1,
"filename": "llama_index_readers_wordlift-0.1.1.tar.gz",
"has_sig": false,
"md5_digest": "92875f1975f8754d7e6509ffe2396601",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8.1,<3.12",
"size": 5016,
"upload_time": "2024-02-12T23:47:54",
"upload_time_iso_8601": "2024-02-12T23:47:54.727901Z",
"url": "https://files.pythonhosted.org/packages/87/57/6ea2331f8317bddb6fbd2da917ba84c7f55283d1ffe0bf03920f3a294973/llama_index_readers_wordlift-0.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-02-12 23:47:54",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-readers-wordlift"
}