build-with-exa

Name: build-with-exa
Author: MoizIbnYousaf

27stars5forks

How to install build-with-exa?

moizibnyousaf/marketing-cli/build-with-exa

$npx -y skills add MoizIbnYousaf/marketing-cli --skill build-with-exa

Installs into the current project.

Summary

Build applications and agents with Exa's API Platform: search, contents, answer, context, Agent API, monitors, websets, OpenAI-compatible endpoints, and exa-py / exa-js. Use when choosing Exa endpoints, writing Exa API calls, integrating semantic web search or research into produ

Files · 1

View on GitHub

SKILL.md

1	## On Activation
2
3	1. Confirm `EXA_API_KEY` is available for any live API call. SDK examples assume the key is set.
4	2. Default new integrations to `POST /search` with `type: "auto"` and `contents.highlights: true`. Escalate to Agent API only for multi-step research / list-building.
5	3. Load only the `references/*.md` file needed for the current endpoint - do not dump the whole tree into context.
6	4. For agent-native marketing research inside mktg projects, prefer `exa-search`, `company-research`, or `lead-generation` over inventing a custom integration.
7
8	# Build with Exa
9
10	## Scope
11
12	Included by default:
13
14	- Core retrieval APIs: search endpoint, contents endpoint, answer endpoint, context endpoint
15	- Long-running research workflows: Agent API (`/agent`)
16	- Async and recurring workflows: Monitors API, Websets API
17	- SDK guidance: Python `exa-py`, TypeScript `exa-js`
18
19	> Note on data retention: `/search`, `/answer`, and deep research are Zero Data Retention (ZDR). The Agent API (`/agent`), Websets, and Monitors are not ZDR. If a use case requires ZDR, stay on the ZDR surfaces or contact Exa.
20
21	## Installation
22
23	```bash
24	# Python
25	pip install exa-py
26
27	# TypeScript / JavaScript
28	npm install exa-js
29	```
30
31	## Authentication
32
33	```bash
34	export EXA_API_KEY="your_api_key_here"
35	```
36
37	Exa accepts either the `x-api-key` header or `Authorization: Bearer <key>`.
38
39	## API Decision Workflow
40
41	Before picking an endpoint, decide which workflow shape fits:
42
43	- Raw web content for your own LLM or agent: start with `/search` using `type: "auto"` and `contents: { highlights: true }`
44	- Synthesized structured output: start with `/search` using the search type that fits your latency and reasoning needs, then add `outputSchema` and `systemPrompt`
45	- Long-running multi-step research, list-building, or enrichment with structured output: use the Agent API (`/agent`)
46
47	Default to the search endpoint. Use the search endpoint (`/search`) for most new integrations, then move to a more specialized Exa surface only when the task shape clearly calls for it.
48
49	1. Need general semantic web retrieval, synthesized output, filters, or content extraction from search results: use the search endpoint (`/search`)
50	2. Already know the URLs and need clean page extraction or freshness controls: use the contents endpoint (`/contents`)
51	3. Need pages related to a known seed URL: use the search endpoint (`/search`) with a query derived from the page (for example title, topic, or text from `/contents`)
52	4. Need a grounded answer with citations from Exa-managed search: use the answer endpoint (`/answer`)
53	5. Need code-focused retrieval from repos, docs, and Stack Overflow: use the context endpoint (`/context`)
54	6. Need OpenAI SDK drop-in compatibility for chat or responses clients: use the OpenAI-compatible endpoints (`/chat/completions`, `/responses`)
55	7. Need asynchronous multi-step research, list-building, enrichment, or follow-up questions over prior research: use the Agent API (`/agent`)
56	8. Need scheduled recurring search with webhook delivery: use the Monitors API (`/monitors`)
57	9. Need async verified and enriched entity collection workflows: use the Websets API (`/websets/v0`)
58
59	## Quick Start
60
61	For more complete examples, see the relevant reference file in the table below.
62
63	Python (`/search`):
64
65	```python
66	from exa_py import Exa
67
68	exa = Exa(api_key="YOUR_EXA_API_KEY")
69	result = exa.search(
70	"latest developments in LLMs",
71	type="auto",
72	contents={"highlights": True}
73	)
74
75	for item in result.results:
76	print(item.title, item.url)
77	```
78
79	TypeScript (`/search`):
80
81	```typescript
82	import Exa from "exa-js";
83
84	const exa = new Exa();
85	const result = await exa.search("latest developments in LLMs", {
86	type: "auto",
87	contents: { highlights: true }
88	});
89
90	for (const item of result.results) {
91	console.log(item.title, item.url);
92	}
93	```
94
95	Raw HTTP (`/search`):
96
97	```bash
98	curl -X POST "https://api.exa.ai/search" \
99	-H "Content-Type: application/json" \
100	-H "x-api-key: $EXA_API_KEY" \
101	-d '{
102	"query": "latest developments in LLMs",
103	"type": "auto",
104	"contents": {
105	"highlights": true
106	}
107	}'
108	```
109
110	## Anti-Patterns
111	- On the search endpoint, `text`, `highlights`, and `summary` belong inside `contents`, not at the top level.
112	- On the contents endpoint, `text`, `highlights`, and `summary` are top-level fields, not nested inside `contents`.
113	- Pick one of `highlights`, `text`, or `summary` b

People who liked this also viewed

6 picks

Type

build-with-exa

27stars5forks

View on GitHub

How to install build-with-exa?

moizibnyousaf/marketing-cli/build-with-exa

$npx -y skills add MoizIbnYousaf/marketing-cli --skill build-with-exa

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	## On Activation
2
3	1. Confirm `EXA_API_KEY` is available for any live API call. SDK examples assume the key is set.
4	2. Default new integrations to `POST /search` with `type: "auto"` and `contents.highlights: true`. Escalate to Agent API only for multi-step research / list-building.
5	3. Load only the `references/*.md` file needed for the current endpoint - do not dump the whole tree into context.
6	4. For agent-native marketing research inside mktg projects, prefer `exa-search`, `company-research`, or `lead-generation` over inventing a custom integration.
7
8	# Build with Exa
9
10	## Scope
11
12	Included by default:
13
14	- Core retrieval APIs: search endpoint, contents endpoint, answer endpoint, context endpoint
15	- Long-running research workflows: Agent API (`/agent`)
16	- Async and recurring workflows: Monitors API, Websets API
17	- SDK guidance: Python `exa-py`, TypeScript `exa-js`
18
19	> Note on data retention: `/search`, `/answer`, and deep research are Zero Data Retention (ZDR). The Agent API (`/agent`), Websets, and Monitors are not ZDR. If a use case requires ZDR, stay on the ZDR surfaces or contact Exa.
20
21	## Installation
22
23	```bash
24	# Python
25	pip install exa-py
26
27	# TypeScript / JavaScript
28	npm install exa-js
29	```
30
31	## Authentication
32
33	```bash
34	export EXA_API_KEY="your_api_key_here"
35	```
36
37	Exa accepts either the `x-api-key` header or `Authorization: Bearer <key>`.
38
39	## API Decision Workflow
40
41	Before picking an endpoint, decide which workflow shape fits:
42
43	- Raw web content for your own LLM or agent: start with `/search` using `type: "auto"` and `contents: { highlights: true }`
44	- Synthesized structured output: start with `/search` using the search type that fits your latency and reasoning needs, then add `outputSchema` and `systemPrompt`
45	- Long-running multi-step research, list-building, or enrichment with structured output: use the Agent API (`/agent`)
46
47	Default to the search endpoint. Use the search endpoint (`/search`) for most new integrations, then move to a more specialized Exa surface only when the task shape clearly calls for it.
48
49	1. Need general semantic web retrieval, synthesized output, filters, or content extraction from search results: use the search endpoint (`/search`)
50	2. Already know the URLs and need clean page extraction or freshness controls: use the contents endpoint (`/contents`)
51	3. Need pages related to a known seed URL: use the search endpoint (`/search`) with a query derived from the page (for example title, topic, or text from `/contents`)
52	4. Need a grounded answer with citations from Exa-managed search: use the answer endpoint (`/answer`)
53	5. Need code-focused retrieval from repos, docs, and Stack Overflow: use the context endpoint (`/context`)
54	6. Need OpenAI SDK drop-in compatibility for chat or responses clients: use the OpenAI-compatible endpoints (`/chat/completions`, `/responses`)
55	7. Need asynchronous multi-step research, list-building, enrichment, or follow-up questions over prior research: use the Agent API (`/agent`)
56	8. Need scheduled recurring search with webhook delivery: use the Monitors API (`/monitors`)
57	9. Need async verified and enriched entity collection workflows: use the Websets API (`/websets/v0`)
58
59	## Quick Start
60
61	For more complete examples, see the relevant reference file in the table below.
62
63	Python (`/search`):
64
65	```python
66	from exa_py import Exa
67
68	exa = Exa(api_key="YOUR_EXA_API_KEY")
69	result = exa.search(
70	"latest developments in LLMs",
71	type="auto",
72	contents={"highlights": True}
73	)
74
75	for item in result.results:
76	print(item.title, item.url)
77	```
78
79	TypeScript (`/search`):
80
81	```typescript
82	import Exa from "exa-js";
83
84	const exa = new Exa();
85	const result = await exa.search("latest developments in LLMs", {
86	type: "auto",
87	contents: { highlights: true }
88	});
89
90	for (const item of result.results) {
91	console.log(item.title, item.url);
92	}
93	```
94
95	Raw HTTP (`/search`):
96
97	```bash
98	curl -X POST "https://api.exa.ai/search" \
99	-H "Content-Type: application/json" \
100	-H "x-api-key: $EXA_API_KEY" \
101	-d '{
102	"query": "latest developments in LLMs",
103	"type": "auto",
104	"contents": {
105	"highlights": true
106	}
107	}'
108	```
109
110	## Anti-Patterns
111	- On the search endpoint, `text`, `highlights`, and `summary` belong inside `contents`, not at the top level.
112	- On the contents endpoint, `text`, `highlights`, and `summary` are top-level fields, not nested inside `contents`.
113	- Pick one of `highlights`, `text`, or `summary` b

People who liked this also viewed

6 picks

Type