Python SDK for Exa API.
Project description
Exa
Exa (formerly Metaphor) API in Python
Note: This API is basically the same as metaphor-python but reflects new
features associated with Metaphor's rename to Exa. New site is https://exa.ai
Installation
pip install exa_py
Usage
Import the package and initialize the Exa client with your API key:
from exa_py import Exa
exa = Exa(api_key="your-api-key")
Common requests
# basic search
results = exa.search("This is a Exa query:")
# keyword search (non-neural)
results = exa.search("Google-style query", type="keyword")
# search with date filters
results = exa.search("This is a Exa query:", start_published_date="2019-01-01", end_published_date="2019-01-31")
# search with domain filters
results = exa.search("This is a Exa query:", include_domains=["www.cnn.com", "www.nytimes.com"])
# search and get text contents
results = exa.search_and_contents("This is a Exa query:")
# search and get contents with contents options
results = exa.search_and_contents("This is a Exa query:",
text={"include_html_tags": True, "max_characters": 1000})
# find similar documents
results = exa.find_similar("https://example.com")
# find similar excluding source domain
results = exa.find_similar("https://example.com", exclude_source_domain=True)
# find similar with contents
results = exa.find_similar_and_contents("https://example.com", text=True)
# get text contents
results = exa.get_contents(["tesla.com"])
# get contents with contents options
results = exa.get_contents(["urls"],
text={"include_html_tags": True, "max_characters": 1000})
# basic answer
response = exa.answer("This is a query to answer a question")
# answer with full text, using the exa-pro model (sends 2 expanded quries to exa search)
response = exa.answer("This is a query to answer a question", text=True, model="exa-pro")
# answer with streaming
response = exa.stream_answer("This is a query to answer:")
# Print each chunk as it arrives when using the stream_answer method
for chunk in response:
print(chunk, end='', flush=True)
# research task example – answer a question with citations
# Example prompt & schema inspired by the TypeScript example.
QUESTION = (
"Summarize the history of San Francisco highlighting one or two major events "
"for each decade from 1850 to 1950"
)
OUTPUT_SCHEMA: Dict[str, Any] = {
"type": "object",
"required": ["timeline"],
"properties": {
"timeline": {
"type": "array",
"items": {
"type": "object",
"required": ["decade", "notableEvents"],
"properties": {
"decade": {
"type": "string",
"description": 'Decade label e.g. "1850s"',
},
"notableEvents": {
"type": "string",
"description": "A summary of notable events.",
},
},
},
},
},
}
resp = exa.research.create_task(
instructions=QUESTION,
model="exa-research",
output_schema=OUTPUT_SCHEMA,
)
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
exa_py-1.14.0.tar.gz
(28.4 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
exa_py-1.14.0-py3-none-any.whl
(35.7 kB
view details)
File details
Details for the file exa_py-1.14.0.tar.gz.
File metadata
- Download URL: exa_py-1.14.0.tar.gz
- Upload date:
- Size: 28.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
c85acf5486b6155f7c19b2f55d94d9e17e10349c96f2e62f1278ff1a824acd12
|
|
| MD5 |
437f93d10f43fba1fe8085bce33bd9b3
|
|
| BLAKE2b-256 |
05283803e552164c64743c16bad602dbf5ee1afd4316fa31287cc61d22b01ed1
|
File details
Details for the file exa_py-1.14.0-py3-none-any.whl.
File metadata
- Download URL: exa_py-1.14.0-py3-none-any.whl
- Upload date:
- Size: 35.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.13.3
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
4cdf57ff1dbbb97e979edb822bc1021dd653e35aac95ecf2586e128ec2e16d3b
|
|
| MD5 |
ff05a5a9e45738fa3c604167b096c1f3
|
|
| BLAKE2b-256 |
bb2876999e175e14910b52e4f60074af1494cb830d2868ff80cff5bd5f4322eb
|
