Working with LLM APIs & SDKs

121 lessons in AI Engineering / Working with LLMs

• Synchronous API Calls vs Web UI InteractionSlides / Video
• Basic Error Handling for LLM APIsSlides / Video
• Token Usage and Cost in API ResponsesSlides / Video
• Extracting Generated Text from a ResponseSlides / Video
• Understanding the API Response StructureSlides / Video
• Common Request Parameters ExplainedSlides / Video
• Selecting a Model in the API RequestSlides / Video
• Structuring Request Messages with RolesSlides / Video
• Installing and Setting Up a Provider SDKSlides / Video
• API Keys and Authentication BasicsSlides / Video
• What an LLM API Is and How It WorksSlides / Video
• REST API vs SDK ApproachesSlides / Video
• Synchronous vs Asynchronous API CallsSlides / Video
• API Pricing and Cost BasicsSlides / Video
• Rate Limits and QuotasSlides / Video
• Basic API Error HandlingSlides / Video
• Common Sampling ParametersQuiz
• Extracting the Completion TextQuiz
• Structure of a Chat Messages ArrayQuiz
• Token Usage in the ResponseQuiz
• Multi-Turn ConversationsQuiz
• Message RolesQuiz
• Rate LimitsQuiz
• API Keys and AuthenticationQuiz
• Setting Max TokensQuiz
• Streaming vs Non-StreamingQuiz
• API Cost and Pricing BasicsQuiz
• Handling API ErrorsQuiz
• Making a Basic API RequestQuiz
• Streaming vs Non-Streaming ResponsesSlides / Video
• Reading Token Usage from the ResponseSlides / Video
• Extracting Text from a ResponseSlides / Video
• Understanding the API Response ObjectSlides / Video
• Common Request ParametersSlides / Video
• Selecting a Model in the API CallSlides / Video
• Iterating a streaming responseCode Quiz
• Message roles structureCode Quiz
• Reading the API key from envCode Quiz
• Specifying the model parameterCode Quiz
• Importing the OpenAI clientCode Quiz
• Passing conversation historyCode Quiz
• Avoiding hardcoded keysCode Quiz
• Structuring the Messages Array (roles)Quiz
• Extracting Generated Text from a ResponseQuiz
• Synchronous vs Asynchronous RequestsQuiz
• Reading the API Response ObjectQuiz
• API Pricing and Token-Based CostQuiz
• Setting max_tokens / Output LengthQuiz
• Rate Limits and QuotasQuiz
• Authenticating SDK RequestsQuiz
• Understanding Token Usage in ResponsesQuiz
• Handling API Errors and Status CodesQuiz
• Selecting a Model in an API CallQuiz
• Obtaining and Using API KeysQuiz
• REST/HTTP Requests vs SDK WrappersQuiz
• Common Request ParametersQuiz
• Making a Basic Chat Completion RequestQuiz
• Keeping API Keys SecureQuiz
• What an LLM API IsQuiz
• Setting the Temperature ParameterQuiz
• Streaming vs Non-Streaming ResponsesQuiz
• Installing and Importing an LLM SDKQuiz
• Messages Array and Role FieldsSlides / Video
• Structure of a Chat Completion RequestSlides / Video
• Making Your First API CallSlides / Video
• Token Usage FieldFlashcard
• Keeping API Keys SecretFlashcard
• Extracting the Generated TextFlashcard
• What an SDK IsFlashcard
• Installing a Provider SDKFlashcard
• Retries and TimeoutsFlashcard
• Pricing and Cost per TokenFlashcard
• Setting the System MessageFlashcard
• API Response Object StructureFlashcard
• Synchronous vs Streaming CallsFlashcard
• Making Your First API CallFlashcard
• Chat vs Legacy CompletionsFlashcard
• Latency ConsiderationsFlashcard
• Provider and Model SelectionFlashcard
• REST API vs SDKFlashcard
• Streaming Responses BasicsFlashcard
• Rate LimitsFlashcard
• Handling API errorsCode Quiz
• Limiting output lengthCode Quiz
• Sending conversation historyCode Quiz
• Sync vs async client methodsCode Quiz
• Reading the key from envCode Quiz
• Extracting the response textCode Quiz
• Reading token usageCode Quiz
• Initializing the clientCode Quiz
• Consuming a streaming responseCode Quiz
• Structuring the messages arrayCode Quiz
• Importing the OpenAI SDKCode Quiz
• Specifying the modelCode Quiz
• Basic chat completion callCode Quiz
• Installing and Setting Up an LLM SDKSlides / Video
• Keeping API Keys Secure with Env VarsSlides / Video
• API Keys and AuthenticationSlides / Video
• Top-p and Sampling ParametersFlashcard
• REST API vs Official SDKFlashcard
• Stop SequencesFlashcard
• API Pricing and Cost per TokenFlashcard
• System Prompt via APIFlashcard
• Sync vs Async API CallsFlashcard
• Completion vs Chat EndpointsFlashcard
• API Keys and AuthenticationFlashcard
• Multi-Turn ConversationsFlashcard
• Retries and Exponential BackoffFlashcard
• Provider-Specific DifferencesFlashcard
• Token Usage in ResponsesFlashcard
• Specifying the Model ParameterFlashcard
• Securing Keys with Env VariablesFlashcard
• Installing an LLM SDKFlashcard
• Parsing the Response ObjectFlashcard
• Streaming ResponsesFlashcard
• Basic Chat Completion RequestFlashcard
• Rate Limits and QuotasFlashcard
• max_tokens ParameterFlashcard
• Handling API ErrorsFlashcard
• What an LLM API IsFlashcard
• What an LLM API IsSlides / Video