diff --git a/fern/docs.yml b/fern/docs.yml index 17a1fef..2a4dfa6 100644 --- a/fern/docs.yml +++ b/fern/docs.yml @@ -20,7 +20,7 @@ navigation: - page: Welcome path: ./docs/pages/welcome.mdx - page: Quick Start - path: ./docs/pages/gettingstarted.mdx + path: ./docs/pages/quickstart.mdx - page: SDKs path: ./docs/pages/sdks.mdx - section: Input Requirements diff --git a/fern/docs/pages/gettingstarted.mdx b/fern/docs/pages/quickstart.mdx similarity index 86% rename from fern/docs/pages/gettingstarted.mdx rename to fern/docs/pages/quickstart.mdx index 093d5cc..1f77900 100644 --- a/fern/docs/pages/gettingstarted.mdx +++ b/fern/docs/pages/quickstart.mdx @@ -3,28 +3,43 @@ title: Quick Start description: Reliable, future proof AI predictions --- -Technical teams need to figure out how to integrate the latest Large Language Models (LLMs), but: +Technical teams need to figure out how to integrate the latest Large Language +Models (LLMs), but: - You can’t build robust systems with inconsistent, unvalidated outputs; and -- LLM integrations scare corporate lawyers, finance departments, and security professionals due to hallucinations, cost, lack of compliance (e.g., HIPAA), leaked IP/PII, and “injection” vulnerabilities. +- LLM integrations scare corporate lawyers, finance departments, and security +professionals due to hallucinations, cost, lack of compliance (e.g., HIPAA), +leaked IP/PII, and “injection” vulnerabilities. -Some companies are moving forward anyway by investing tons of engineering time/money in their own wrappers around LLMs and expensive hosting with OpenAI/Azure. Others are ignoring these issues and pressing forward with fragile and risky LLM integrations. +Some companies are moving forward anyway by investing tons of engineering time/money +in their own wrappers around LLMs and expensive hosting with OpenAI/Azure. Others +are ignoring these issues and pressing forward with fragile and risky LLM integrations. -At Prediction Guard, we think that you should get useful output from compliant AI systems (without crazy implementation/ hosting costs), so our solution lets you: +At Prediction Guard, we think that you should get useful output from compliant +AI systems (without crazy implementation/ hosting costs), so our solution lets you: 1. **De-risk LLM inputs** to remove PII and prompt injections; -2. **Validate and check LLM outputs** to guard against hallucination, toxicity and inconsistencies; and -3. **Implement private and compliant LLM systems** (HIPAA and self-hosted) that give your legal counsel warm fuzzy feeling while still delighting your customers with AI features. +2. **Validate and check LLM outputs** to guard against hallucination, toxicity and +inconsistencies; and +3. **Implement private and compliant LLM systems** (HIPAA and self-hosted) that +give your legal counsel warm fuzzy feeling while still delighting your customers +with AI features. -Sounds pretty great right? Follow the steps below to starting leveraging trustworthy LLMs: +Sounds pretty great right? Follow the steps below to starting leveraging +trustworthy LLMs: ## 1. Get access to Prediction Guard Enterprise -We host and control the latest LLMs for you in our secure and privacy-conserving enterprise platform, so you can focus on your prompts and chains. To access the hosted LLMs, contact us [here](https://mailchi.mp/predictionguard/getting-started) to get an enterprise access token. You will need this access token to continue. +We host and control the latest LLMs for you in our secure and privacy-conserving +enterprise platform, so you can focus on your prompts and chains. To access the +hosted LLMs, contact us [here](https://mailchi.mp/predictionguard/getting-started) +to get an enterprise access token. You will need this access token to continue. ## 2. Start using one of our LLMs! -Suppose you want to prompt an LLM to answer a user query from a chat application. You can setup a message thread, which includes a system prompt (that instructs the LLM how to behave in responding) as follows: +Suppose you want to prompt an LLM to answer a user query from a chat application. +You can setup a message thread, which includes a system prompt (that instructs +the LLM how to behave in responding) as follows: ``` [ diff --git a/fern/docs/pages/sdks.mdx b/fern/docs/pages/sdks.mdx index 784c23e..c8aa32a 100644 --- a/fern/docs/pages/sdks.mdx +++ b/fern/docs/pages/sdks.mdx @@ -1,5 +1,5 @@ -We provide official open-source SDKs (client libraries) for your favorite platforms. These clients make connecting to our API faster and help avoid errors. - +We provide official open-source SDKs (client libraries) for your favorite platforms. +These clients make connecting to our API faster and help avoid errors. ## Official SDK Documentation @@ -10,16 +10,16 @@ We provide official open-source SDKs (client libraries) for your favorite platfo - ## Request a New SDK -If you'd like to request an SDK for a language that we don't currently support, please reach out to us on [Discord](https://discord.gg/TFHgnhAFKd). We prioritize languages based on demand. - +If you'd like to request an SDK for a language that we don't currently support, +please reach out to us on [Discord](https://discord.gg/TFHgnhAFKd). We prioritize +languages based on demand. ## Access Tokens -To access the API, contact us [here](https://mailchi.mp/predictionguard/getting-started) to get an access token. - +To access the API, contact us [here](https://mailchi.mp/predictionguard/getting-started) +to get an access token. ## SDK Quick Start @@ -72,7 +72,8 @@ print(json.dumps( #### More Python Examples -Take a look at the [examples](https://github.com/predictionguard/python-client/tree/master/examples) directory for more Python examples. +Take a look at the [examples](https://github.com/predictionguard/python-client/tree/master/examples) +directory for more Python examples. --- @@ -123,7 +124,8 @@ Chat(); #### More JS Examples -Take a look at the [examples](https://github.com/predictionguard/js-client/tree/main/examples) directory for more JS examples. +Take a look at the [examples](https://github.com/predictionguard/js-client/tree/main/examples) +directory for more JS examples. --- @@ -203,7 +205,8 @@ func run() error { #### More Go Examples -Take a look at the [examples](https://github.com/predictionguard/go-client/tree/main/examples) directory for more Go examples. +Take a look at the [examples](https://github.com/predictionguard/go-client/tree/main/examples) +directory for more Go examples. --- @@ -246,4 +249,5 @@ async fn main() { #### More Rust Examples -Take a look at the [examples](https://github.com/predictionguard/rust-client/tree/main/examples) directory for more Rust examples. +Take a look at the [examples](https://github.com/predictionguard/rust-client/tree/main/examples) +directory for more Rust examples. diff --git a/fern/docs/pages/usingllms/accessing.mdx b/fern/docs/pages/usingllms/accessing.mdx index 5c7b1e5..0a7268f 100644 --- a/fern/docs/pages/usingllms/accessing.mdx +++ b/fern/docs/pages/usingllms/accessing.mdx @@ -33,13 +33,13 @@ os.environ["PREDICTIONGUARD_API_KEY"] = "" client = PredictionGuard() ``` -You can find out more about the models available via the Prediction Guard API [in the docs](https://docs.predictionguard.com/models), and you can list out the model names via this command: +You can find out more about the models available via the Prediction Guard API [in the docs](https://docs.predictionguard.com/options/enumerations), and you can list out the model names via this command: ```python copy print(client.completions.list_models()) ``` -Generating text with one of these models is then just single request for a "Completion" (note, we also support chat completions). Here we will call the `Notus-7B` model and try to have it autocomplete a joke. +Generating text with one of these models is then just single request for a "Completion" (note, we also support chat completions). Here we will call the `Neural-Chat-7B"` model and try to have it autocomplete a joke. ```python copy response = client.completions.create(model="Neural-Chat-7B",