Skip to content

Parakeet examples & Recipes

Of this repository: https://github.com/parakeet-nest/parakeet/tree/main/examples

Item Details
01-generate generate completion
02-generate-stream generate completion with stream
03-chat chat completion
04-chat-stream chat completion with stream
05-context chat with context
06-summary summarize a content
07-explain explain a piece of code
08-embeddings-memory create embeddings in a memory vector store
09-embeddings-bbolt create embeddings in a bbolt vector store
10-chat-conversational-memory chat completion + conversational memory
11-chat-conversational-bbolt persist the conversation of the chat
12-json-output the LLM generates a json output
13-simple-fake-function-calling kind of function calling
14-mistral-function-calling use the tools support of Mistral
15-mistral-function-calling use the tools support of Mistral
16-fake-function-calling make function calling without the tools support
17-fake-function-calling make function calling without the tools support
18-call-functions-for-real call wasm functions with tools
19-mistral-function-calling-tool-support use the new tools support with Mistral
20-play-with-granite generate source code
21-analysis-with-granite analyse source code
22-dockerizing generate a Dockerfile and a Compose file
23-rag-with-chunker rag demo
24-rag-with-splitter rag demo
25-rag-with-regex rag demo
26-docker-cmd teach the docker commands to the LLM
27-generate-token use an authentication token
28-generate-stream-token use an authentication token
29-chat-token use an authentication token
30-chat-stream-token use an authentication token
31-embeddings-memory-token use an authentication token
32-rag-with-redis rag demo with Redis as the vector store
33-rag-with-elastic rag demo with Elasticsearch as the vector store
34-rag-with-bbolt rag demo with Bbolt as the vector store
35-rag-with-bbolt rag demo with Bbolt as the vector store
36-rag-with-asciidoc rag demo with Asciidoc document
37-rag-with-html rag demo with HTML document
38-rag-with-markdown rag demo with Markdown document
39-rag-with-elastic-markdown rag demo with Markdown and Elasticsearch
40-rag-with-elastic-markdown rag demo with Markdown and Elasticsearch
41-prompt-from-repo 🚧
42-make-a-slm-smarter experiments to make a SLM an expert on a specific topic
43-function-calling tools demos with SLMs
44-chat-openai chat completion with OpenAI
45-chat-stream-openai chat stream completion with OpenAI
46-create-an-expert 🚧
47-function-calling-xp call tools several times with the same prompt
48-testing-models testing various models
49-embeddings-memory-openai create embeddings with OpenAI
50-llm-information get information about LLMs
51-genai-webapp GenAI web application demo
52-constraints Preventing an LLM from talking about certain things
53-constraints Preventing an LLM from talking about certain things
54-constraints-webapp Preventing an LLM from talking about certain things
55-create-npc Create a NPC with nemotron-mini and chat with him
56-jean-luc-picard Chat with Jean-Luc Picard
57-jean-luc-picard-rag Chat with Jean-Luc Picard + RAG
58-michael-burnham Chat with Michael Burnham
59-jean-luc-picard-contextual-retrieval Chat with Jean-Luc Picard + Contextual Retrieval
60-safety-models Safety Models fine-tuned for content safety classification of LLM inputs and responses
61-agents Basic Flock Agent
62-agents-chat Conversational Flock Agents
63-agents-chat-stream Conversational Flock Agents
64-agents-with-tools Function Calling Flock Agent example