- Mermaid flowchart based on the coding inference
- Gemini to generate prompts where I upload my flochart
- Paste the prompt to Claude and tell it to generate mp4. And Claude outputs mp4.
🔄 In a Training Loop
Tarun Jain
lucifertrj
AI & ML interests
Deep Learning, FPGA, and ML
Recent Activity
repliedto their post 3 days ago
You can now automate EDD (eval-driven development) with Coding Harness Agents
> build a baseline LLM-based application
> score every change with judge evals
> keep what improves, reject what regresses
I made a tutorial on what EDD is, how it works, and how to use eval scores across experiments to improve an LLM app. It builds on Jeffrey's (Confident AI) article on EDD and Eugene Yan's write-up on product evals.
> Setup: a baseline RAG app using Qdrant and Gemini that every experiment starts from
> Step 1: a binary-labelled dataset with critiques
> Step 2: aligning the LLM-as-a-judge evaluator with Opik evals
> Step 3: a harness loop that runs each experiment and scores it against the baseline.
Tracing and experiment comparison then show what improved, what regressed, and what to tweak next.
Source code is open source.
Full guide (source code linked in the description): https://www.youtube.com/watch?v=e6akw_fKWPk liked a model 4 days ago
kaividlabs/LFM2.5-2.6B-litertlm updated a model 4 days ago
kaividlabs/LFM2.5-2.6B-litertlmOrganizations
replied to their post 3 days ago
reacted to their post with 🔥 4 days ago
Post
1368
You can now automate EDD (eval-driven development) with Coding Harness Agents
> build a baseline LLM-based application
> score every change with judge evals
> keep what improves, reject what regresses
I made a tutorial on what EDD is, how it works, and how to use eval scores across experiments to improve an LLM app. It builds on Jeffrey's (Confident AI) article on EDD and Eugene Yan's write-up on product evals.
> Setup: a baseline RAG app using Qdrant and Gemini that every experiment starts from
> Step 1: a binary-labelled dataset with critiques
> Step 2: aligning the LLM-as-a-judge evaluator with Opik evals
> Step 3: a harness loop that runs each experiment and scores it against the baseline.
Tracing and experiment comparison then show what improved, what regressed, and what to tweak next.
Source code is open source.
Full guide (source code linked in the description): https://www.youtube.com/watch?v=e6akw_fKWPk
> build a baseline LLM-based application
> score every change with judge evals
> keep what improves, reject what regresses
I made a tutorial on what EDD is, how it works, and how to use eval scores across experiments to improve an LLM app. It builds on Jeffrey's (Confident AI) article on EDD and Eugene Yan's write-up on product evals.
> Setup: a baseline RAG app using Qdrant and Gemini that every experiment starts from
> Step 1: a binary-labelled dataset with critiques
> Step 2: aligning the LLM-as-a-judge evaluator with Opik evals
> Step 3: a harness loop that runs each experiment and scores it against the baseline.
Tracing and experiment comparison then show what improved, what regressed, and what to tweak next.
Source code is open source.
Full guide (source code linked in the description): https://www.youtube.com/watch?v=e6akw_fKWPk
- 4 replies
posted an update 6 days ago
Post
1368
You can now automate EDD (eval-driven development) with Coding Harness Agents
> build a baseline LLM-based application
> score every change with judge evals
> keep what improves, reject what regresses
I made a tutorial on what EDD is, how it works, and how to use eval scores across experiments to improve an LLM app. It builds on Jeffrey's (Confident AI) article on EDD and Eugene Yan's write-up on product evals.
> Setup: a baseline RAG app using Qdrant and Gemini that every experiment starts from
> Step 1: a binary-labelled dataset with critiques
> Step 2: aligning the LLM-as-a-judge evaluator with Opik evals
> Step 3: a harness loop that runs each experiment and scores it against the baseline.
Tracing and experiment comparison then show what improved, what regressed, and what to tweak next.
Source code is open source.
Full guide (source code linked in the description): https://www.youtube.com/watch?v=e6akw_fKWPk
> build a baseline LLM-based application
> score every change with judge evals
> keep what improves, reject what regresses
I made a tutorial on what EDD is, how it works, and how to use eval scores across experiments to improve an LLM app. It builds on Jeffrey's (Confident AI) article on EDD and Eugene Yan's write-up on product evals.
> Setup: a baseline RAG app using Qdrant and Gemini that every experiment starts from
> Step 1: a binary-labelled dataset with critiques
> Step 2: aligning the LLM-as-a-judge evaluator with Opik evals
> Step 3: a harness loop that runs each experiment and scores it against the baseline.
Tracing and experiment comparison then show what improved, what regressed, and what to tweak next.
Source code is open source.
Full guide (source code linked in the description): https://www.youtube.com/watch?v=e6akw_fKWPk
- 4 replies
reacted to their post with 🔥 17 days ago
Post
2948
Published a guide to TurboQuant quantization: how the algorithm works and what Qdrant adds on top of it.
It also includes a benchmark comparing float32, scalar, binary and TurboQuant across BEIR's SciFact, ArguAna and NFCorpus, measured with recall@10, precision@10 and nDCG@10.
🔗 HF article: https://huggingface.co/blog/lucifertrj/turboquant-quantization-explained
It also includes a benchmark comparing float32, scalar, binary and TurboQuant across BEIR's SciFact, ArguAna and NFCorpus, measured with recall@10, precision@10 and nDCG@10.
🔗 HF article: https://huggingface.co/blog/lucifertrj/turboquant-quantization-explained
posted an update 19 days ago
Post
2948
Published a guide to TurboQuant quantization: how the algorithm works and what Qdrant adds on top of it.
It also includes a benchmark comparing float32, scalar, binary and TurboQuant across BEIR's SciFact, ArguAna and NFCorpus, measured with recall@10, precision@10 and nDCG@10.
🔗 HF article: https://huggingface.co/blog/lucifertrj/turboquant-quantization-explained
It also includes a benchmark comparing float32, scalar, binary and TurboQuant across BEIR's SciFact, ArguAna and NFCorpus, measured with recall@10, precision@10 and nDCG@10.
🔗 HF article: https://huggingface.co/blog/lucifertrj/turboquant-quantization-explained
posted an update over 1 year ago
Post
759
Bhagavad Gita GPT assistant - Build fast RAG pipeline to index 1000+ pages using Binary Optimization
DeepSeek R-1 and Qdrant Binary Quantization
Check out the latest tutorial where we build a Bhagavad Gita GPT assistant—covering:
- DeepSeek R1 vs OpenAI O1
- Using Qdrant client with Binary Quantization
- Building the RAG pipeline with LlamaIndex
- Running inference with DeepSeek R1 Distill model on Groq
- Develop Streamlit app for the chatbot inference
Watch the full implementation here: https://www.youtube.com/watch?v=NK1wp3YVY4Q
DeepSeek R-1 and Qdrant Binary Quantization
Check out the latest tutorial where we build a Bhagavad Gita GPT assistant—covering:
- DeepSeek R1 vs OpenAI O1
- Using Qdrant client with Binary Quantization
- Building the RAG pipeline with LlamaIndex
- Running inference with DeepSeek R1 Distill model on Groq
- Develop Streamlit app for the chatbot inference
Watch the full implementation here: https://www.youtube.com/watch?v=NK1wp3YVY4Q
- 1 reply
posted an update almost 2 years ago
Post
597
Image Prompt Engineering Guide:
➡️ Artistic styling for Image generation
➡️ Prompt weighting using the parentheses method to generate realistic images.
➡️ Advanced features like style and positioning control[experimental].
➡️ Image placement on the generated AI image using Recraft V3 Mockup.
Watch: https://www.youtube.com/watch?v=d3nUG28-jIc
➡️ Artistic styling for Image generation
➡️ Prompt weighting using the parentheses method to generate realistic images.
➡️ Advanced features like style and positioning control[experimental].
➡️ Image placement on the generated AI image using Recraft V3 Mockup.
Watch: https://www.youtube.com/watch?v=d3nUG28-jIc
posted an update almost 2 years ago
Post
1580
AI Agents LlamaIndex in 40 minutes
The video covers code and workflow explanations for:
- Function Calling
- Function Calling Agents + Agent Runner
- Agentic RAG
- REAcT Agent: Build your own Search Assistant Agent
Watch: https://youtu.be/bHn4dLJYIqE
The video covers code and workflow explanations for:
- Function Calling
- Function Calling Agents + Agent Runner
- Agentic RAG
- REAcT Agent: Build your own Search Assistant Agent
Watch: https://youtu.be/bHn4dLJYIqE
posted an update over 2 years ago
Post
1721
Observability and Retrieval Augmented Generation in 10 lines of Code
Tutorial: https://www.youtube.com/watch?v=VCQ0Cw-GF2U
This video covers:
- Why we need observability?
- Implementation of RAG using BeyondLLM
- Monitor and Track LLM Observability using Phoenix
Tutorial: https://www.youtube.com/watch?v=VCQ0Cw-GF2U
This video covers:
- Why we need observability?
- Implementation of RAG using BeyondLLM
- Monitor and Track LLM Observability using Phoenix
reacted to their post with 👀 over 2 years ago
Post
2351
Advanced RAG - Hybrid Search using HuggingFace Models
Chat with PDF in 10 lines of code:
Cookbook: https://github.com/aiplanethub/beyondllm/blob/main/cookbook/Implementing_Hybrid_Search.ipynb
Support the project by giving a ⭐️ to the repo
Chat with PDF in 10 lines of code:
# pip install beyondllm
# pip install llama-index-embeddings-fastembed
from beyondllm import source,retrieve,embeddings,llms,generator
import os
from getpass import getpass
os.environ['HUGGINGFACE_ACCESS_TOKEN'] = getpass("Enter your HF API token:")
data = source.fit("sample.pdf", dtype="pdf")
embed_model = embeddings.FastEmbedEmbeddings()
retriever = auto_retriever(
data=data, embed_model=embed_model,
type="hybrid", top_k=5, mode="OR"
)
llm = HuggingFaceHubModel(model="mistralai/Mistral-7B-Instruct-v0.2")
pipeline = generator.Generate(question="<replace-with-your-query>",llm=llm,retriever=retriever)
print(pipeline.call())Cookbook: https://github.com/aiplanethub/beyondllm/blob/main/cookbook/Implementing_Hybrid_Search.ipynb
Support the project by giving a ⭐️ to the repo
posted an update over 2 years ago
Post
2351
Advanced RAG - Hybrid Search using HuggingFace Models
Chat with PDF in 10 lines of code:
Cookbook: https://github.com/aiplanethub/beyondllm/blob/main/cookbook/Implementing_Hybrid_Search.ipynb
Support the project by giving a ⭐️ to the repo
Chat with PDF in 10 lines of code:
# pip install beyondllm
# pip install llama-index-embeddings-fastembed
from beyondllm import source,retrieve,embeddings,llms,generator
import os
from getpass import getpass
os.environ['HUGGINGFACE_ACCESS_TOKEN'] = getpass("Enter your HF API token:")
data = source.fit("sample.pdf", dtype="pdf")
embed_model = embeddings.FastEmbedEmbeddings()
retriever = auto_retriever(
data=data, embed_model=embed_model,
type="hybrid", top_k=5, mode="OR"
)
llm = HuggingFaceHubModel(model="mistralai/Mistral-7B-Instruct-v0.2")
pipeline = generator.Generate(question="<replace-with-your-query>",llm=llm,retriever=retriever)
print(pipeline.call())Cookbook: https://github.com/aiplanethub/beyondllm/blob/main/cookbook/Implementing_Hybrid_Search.ipynb
Support the project by giving a ⭐️ to the repo
replied to their post over 2 years ago
Thanks
replied to their post over 2 years ago
This is not using beyondllm
posted an update over 2 years ago
Post
1883
Evaluate RAG using Open Source from HuggingFace using BeyondLLM
GitHub: https://github.com/aiplanethub/beyondllm
Don't forget to ⭐️ the repo
# pip install beyondllm
# pip install huggingface_hub
# pip install llama-index-embeddings-fastembed
from beyondllm.source import fit
from beyondllm.embeddings import FastEmbedEmbeddings
from beyondllm.retrieve import auto_retriever
from beyondllm.llms import HuggingFaceHubModel
from beyondllm.generator import Generate
import os
from getpass import getpass
os.environ['HUGGINGFACE_ACCESS_TOKEN'] = getpass("Enter your HF API token:")
data = fit("RedHenLab_GSoC_Tarun.pdf",dtype="pdf")
embed_model = FastEmbedEmbeddings()
retriever = auto_retriever(data=data,embed_model=embed_model,type="normal",top_k=3)
llm = HuggingFaceHubModel(model="mistralai/Mistral-7B-Instruct-v0.2")
pipeline = Generate(question="what models has Tarun fine-tuned?",llm=llm,retriever=retriever)
print(pipeline.call()) # Return the AI response
print(pipeline.get_rag_triad_evals())GitHub: https://github.com/aiplanethub/beyondllm
Don't forget to ⭐️ the repo
- 4 replies