80b1badf74
* fix(security): address all Dependabot vulnerability alerts Python (uv.lock, pyproject.toml): - authlib 1.6.6 → 1.6.9 (JWS header injection, OIDC hash binding, Bleichenbacher padding oracle) - pyasn1 0.6.2 → 0.6.3 (unbounded recursion DoS) - pyjwt 2.10.1 → 2.12.1 (unknown crit header extensions - also in integration-tests and crewai) - orjson 3.11.4 → 3.11.7 (deeply nested JSON recursion DoS) - tornado 6.5.2 → 6.5.5 (multipart DoS, incomplete cookie validation) npm (package.json, package-lock.json): - next ^16.1.6 → ^16.1.7 (HTTP smuggling, CSRF bypass, cache DoS, null origin bypass) - fast-xml-parser override updated to >=5.5.6 (numeric entity expansion bypass) - undici override added >=7.24.0 (WebSocket overflow, smuggling, CRLF injection, DoS) - flatted override added >=3.4.0 (unbounded recursion DoS) - svgo override added >=3.3.3 (DOCTYPE entity expansion DoS) - dompurify override added >=3.3.2 (XSS vulnerability) * feat(docs): add Integrations Hub and unified page hero - Add /integrations page with search, type filter, and card grid - Integrations defined in a single JSON file (src/data/integrations.json) supporting official and community entries with icon, author, and link - Scrolling integrations banner moved from global navbar to /integrations only - Remove IntegrationsGrid component; replace all usages with link to hub - Add PageHero component with full-bleed gradient background, shared across Cookbook, FAQ, Best Practices, Changelog, and Blog index pages - Remove FAQ from top navbar (already in Resources dropdown) - Move integration changelogs table to bottom of changelog page
128 lines
3.2 KiB
Text
128 lines
3.2 KiB
Text
---
|
|
sidebar_position: 0
|
|
---
|
|
|
|
# Quick Start
|
|
|
|
Get up and running with Hindsight in 60 seconds.
|
|
|
|
import Tabs from '@theme/Tabs';
|
|
import TabItem from '@theme/TabItem';
|
|
import CodeSnippet from '@site/src/components/CodeSnippet';
|
|
import {ClientsGrid} from '@site/src/components/SupportedGrids';
|
|
|
|
{/* Import raw source files */}
|
|
import quickstartPy from '!!raw-loader!@site/examples/api/quickstart.py';
|
|
import quickstartMjs from '!!raw-loader!@site/examples/api/quickstart.mjs';
|
|
import quickstartSh from '!!raw-loader!@site/examples/api/quickstart.sh';
|
|
import quickstartGo from '!!raw-loader!@site/examples/api/quickstart.go';
|
|
|
|
## Clients
|
|
|
|
<ClientsGrid />
|
|
|
|
## Start the API Server
|
|
|
|
<Tabs>
|
|
<TabItem value="pip" label="pip (API only)">
|
|
|
|
```bash
|
|
pip install hindsight-api
|
|
export OPENAI_API_KEY=sk-xxx
|
|
export HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY
|
|
|
|
hindsight-api
|
|
```
|
|
|
|
API available at [http://localhost:8888](http://localhost:8888/docs)
|
|
|
|
</TabItem>
|
|
<TabItem value="docker" label="Docker (Full Experience)">
|
|
|
|
```bash
|
|
|
|
export OPENAI_API_KEY=sk-xxx
|
|
|
|
docker run --rm -it --pull always -p 8888:8888 -p 9999:9999 \
|
|
-e HINDSIGHT_API_LLM_API_KEY=$OPENAI_API_KEY \
|
|
-v $HOME/.hindsight-docker:/home/hindsight/.pg0 \
|
|
ghcr.io/vectorize-io/hindsight:latest
|
|
```
|
|
|
|
- **API**: http://localhost:8888
|
|
- **Control Plane** (Web UI): http://localhost:9999
|
|
|
|
</TabItem>
|
|
</Tabs>
|
|
|
|
:::tip LLM Provider
|
|
Hindsight requires an LLM with structured output support. Recommended: **Groq** with `gpt-oss-20b` for fast, cost-effective inference.
|
|
See [LLM Providers](/developer/models#llm) for more details.
|
|
:::
|
|
|
|
---
|
|
|
|
## Use the Client
|
|
|
|
<Tabs>
|
|
<TabItem value="python" label="Python">
|
|
|
|
```bash
|
|
pip install hindsight-client
|
|
```
|
|
|
|
<CodeSnippet code={quickstartPy} section="quickstart-full" language="python" />
|
|
|
|
</TabItem>
|
|
<TabItem value="node" label="Node.js">
|
|
|
|
```bash
|
|
npm install @vectorize-io/hindsight-client
|
|
```
|
|
|
|
<CodeSnippet code={quickstartMjs} section="quickstart-full" language="javascript" />
|
|
|
|
</TabItem>
|
|
<TabItem value="cli" label="CLI">
|
|
|
|
```bash
|
|
curl -fsSL https://hindsight.vectorize.io/get-cli | bash
|
|
```
|
|
|
|
<CodeSnippet code={quickstartSh} section="quickstart-full" language="bash" />
|
|
|
|
</TabItem>
|
|
<TabItem value="go" label="Go">
|
|
|
|
```bash
|
|
go get github.com/vectorize-io/hindsight/hindsight-clients/go
|
|
```
|
|
|
|
<CodeSnippet code={quickstartGo} section="quickstart-full" language="go" />
|
|
|
|
</TabItem>
|
|
</Tabs>
|
|
|
|
---
|
|
|
|
## What's Happening
|
|
|
|
| Operation | What it does |
|
|
|-----------|--------------|
|
|
| **Retain** | Content is processed, facts are extracted, entities are identified and linked in a knowledge graph |
|
|
| **Recall** | Four search strategies (semantic, keyword, graph, temporal) run in parallel to find relevant memories |
|
|
| **Reflect** | Retrieved memories are used to generate a disposition-aware response |
|
|
|
|
---
|
|
|
|
## Integrations
|
|
|
|
Browse all supported integrations in the [Integrations Hub](/integrations).
|
|
|
|
## Next Steps
|
|
|
|
- [**Retain**](./retain) — Advanced options for storing memories
|
|
- [**Recall**](./recall) — Search and retrieval strategies
|
|
- [**Reflect**](./reflect) — Disposition-aware reasoning
|
|
- [**Memory Banks**](./memory-banks) — Configure disposition and mission
|
|
- [**Server Deployment**](/developer/installation) — Docker Compose, Helm, and production setup
|