Skip to content

elephantscale/OpenAI-labs

BranchesTags

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

575 Commits
.vs
.vs
 
 
01-install
01-install
 
 
02-Fine-Tuning
02-Fine-Tuning
 
 
03-embeddings
03-embeddings
 
 
04-speech-to-text
04-speech-to-text
 
 
05-prompt-engineering
05-prompt-engineering
 
 
07-langchain
07-langchain
 
 
08-building-systems
08-building-systems
 
 
10-pizza-order-bot
10-pizza-order-bot
 
 
11-wandb
11-wandb
 
 
12-google-palm
12-google-palm
 
 
14-pinecone-apps
14-pinecone-apps
 
 
15-aws-bedrock
15-aws-bedrock
 
 
16-Llama
16-Llama
 
 
17-Neo4J-RAG
17-Neo4J-RAG
 
 
18-JavaScript-RAG
18-JavaScript-RAG
 
 
19-Red-Teaming-LLM-Applications
19-Red-Teaming-LLM-Applications
 
 
20-Quantization-Fundamentals
20-Quantization-Fundamentals
 
 
21-JavaScript-RAG
21-JavaScript-RAG
 
 
22-Mistral
22-Mistral
 
 
23-Comet
23-Comet
 
 
24-Weaviate
24-Weaviate
 
 
25-OnDevice
25-OnDevice
 
 
26-agentic
26-agentic
 
 
27-database-agent
27-database-agent
 
 
28-function-calling
28-function-calling
 
 
29-pinecone
29-pinecone
 
 
30-advanced_retrieval_for_AI_with_chroma
30-advanced_retrieval_for_AI_with_chroma
 
 
31-reinforcement -learning-from-human-feedback
31-reinforcement -learning-from-human-feedback
 
 
32-diffusion-model
32-diffusion-model
 
 
33-prompt-compression-and-query-optimization
33-prompt-compression-and-query-optimization
 
 
34-langchain-chat-with-your-own-data
34-langchain-chat-with-your-own-data
 
 
35_LLM_With_Semantic_Search
35_LLM_With_Semantic_Search
 
 
36-Functions-Tool-Agents-Langchain
36-Functions-Tool-Agents-Langchain
 
 
37-pretraining-llm
37-pretraining-llm
 
 
38-AI-Agentic-Design-Patterns-with-AutoGen
38-AI-Agentic-Design-Patterns-with-AutoGen
 
 
39-Embedding-Models
39-Embedding-Models
 
 
40-Vector-Databases-from-Embeddings-to-Applications
40-Vector-Databases-from-Embeddings-to-Applications
 
 
41-building-genAI-app-with-gradio
41-building-genAI-app-with-gradio
 
 
43-AI-Python-for-Beginners
43-AI-Python-for-Beginners
 
 
44-Building-Agentic-RAG-with-Llamaindex
44-Building-Agentic-RAG-with-Llamaindex
 
 
45-Multi-AI-Agent-Systems-with-crewAI
45-Multi-AI-Agent-Systems-with-crewAI
 
 
46-Improving-Accuracy-of-LLMs
46-Improving-Accuracy-of-LLMs
 
 
47-Pair-Programming-with-a-Large-Language-Model
47-Pair-Programming-with-a-Large-Language-Model
 
 
48-Finetuning-Large-Language-Models
48-Finetuning-Large-Language-Models
 
 
49-Building-AI-Applications-with-Haystack
49-Building-AI-Applications-with-Haystack
 
 
50-AI-Python-for-Beginners
50-AI-Python-for-Beginners
 
 
51-Qdrant-intro
51-Qdrant-intro
 
 
52-Agentic-on-Bedrock
52-Agentic-on-Bedrock
 
 
53-Serverless-LLM-Bedrock
53-Serverless-LLM-Bedrock
 
 
54-LLM-as-OS
54-LLM-as-OS
 
 
55-Guardrails
55-Guardrails
 
 
56-AI-Powered-Games
56-AI-Powered-Games
 
 
57-Reasoning-with-o1
57-Reasoning-with-o1
 
 
58-Canvas
58-Canvas
 
 
59-Agentic-AI-for-Leaders
59-Agentic-AI-for-Leaders
 
 
60-Jamba
60-Jamba
 
 
61-Anthropic-Computer-Use
61-Anthropic-Computer-Use
 
 
62-gen-AI-privacy-security
62-gen-AI-privacy-security
 
 
63-how-llm-transformers-work
63-how-llm-transformers-work
 
 
64-attention-in-transformers
64-attention-in-transformers
 
 
65-evaluating-ai-agents
65-evaluating-ai-agents
 
 
66-windsurf
66-windsurf
 
 
67-llama-index
67-llama-index
 
 
68-replit
68-replit
 
 
69-dottxt
69-dottxt
 
 
70-smolagents
70-smolagents
 
 
71-voiceagents
71-voiceagents
 
 
72-anthropic-mcp
72-anthropic-mcp
 
 
73-Agentic-Java
73-Agentic-Java
 
 
74-predibase/slides
74-predibase/slides
 
 
75-dspy
75-dspy
 
 
76-airflow
76-airflow
 
 
77-llama4
77-llama4
 
 
78-acp
78-acp
 
 
79-posttraining-llm
79-posttraining-llm
 
 
80-claude-code
80-claude-code
 
 
81-elisya-ai
81-elisya-ai
 
 
82-agentic-knowledge-graphs
82-agentic-knowledge-graphs
 
 
83-agentic-langgraph
83-agentic-langgraph
 
 
84-knowledge-graph-sap
84-knowledge-graph-sap
 
 
85-Box
85-Box
 
 
86-snowflake
86-snowflake
 
 
87-agentic-ai
87-agentic-ai
 
 
88-voice-agents
88-voice-agents
 
 
89-claude-code-white
89-claude-code-white
 
 
90-governing-ai-agents
90-governing-ai-agents
 
 
91-jupyter-ai
91-jupyter-ai
 
 
92-multi-agent-crewai
92-multi-agent-crewai
 
 
93-semantic-cache-redis
93-semantic-cache-redis
 
 
94-building-ai-agents-with-tools
94-building-ai-agents-with-tools
 
 
95-qdrant
95-qdrant
 
 
96-NeMo
96-NeMo
 
 
97-docproc
97-docproc
 
 
98-google-gemini
98-google-gemini
 
 
99-agentic-anthropic
99-agentic-anthropic
 
 
data
data
 
 
doc
doc
 
 
images
images
 
 
mp3
mp3
 
 

Repository files navigation

OpenAI labs

Workflow (per lab)

  1. From the repo root, run the lab setup:

    • ./setup.sh <lab-path>
    • Example: ./setup.sh labs/python-rag

  2. Change into the lab directory:

    • cd <lab-path>

  3. Activate the lab’s virtual environment (optional, but convenient for CLI work):

    • source .venv/bin/activate

  4. Run the notebooks in that lab.

    • In Jupyter, make sure the notebook kernel is set to the lab kernel:
      • Kernel → Change Kernel → Lab: <lab-name>

  5. When you’re done (optional):

    • deactivate

About

No description, website, or topics provided.

Resources

Readme
Activity
Custom properties

Stars

7 stars

Watchers

4 watching

Forks

4 forks
Report repository

Releases

1 tags

Packages

No packages published

Contributors 7

Languages