Advanced RAG: Fine-Tune Embeddings from HuggingFace for RAG
โข
3
# 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())
# 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())
Thanks
This is not using beyondllm
# 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())