Skip to content

removed the secret #38

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
pavanjava merged 1 commit into from
Sep 30, 2024
Merged

removed the secret #38

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions bootstraprag/templates/llamaindex/simple_rag/.env
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,9 +1,10 @@
DB_URL='http://localhost:6333'
DB_API_KEY='th3s3cr3tk3y'
COLLECTION_NAME='YOUR_COLLECTION'
COLLECTION_NAME='YOUR_TEST_COLLECTION'

OPENAI_API_KEY=''
OPENAI_EMBED_MODEL=''
OPENAI_EMBED_MODEL='text-embedding-3-small'
OPENAI_MODEL='gpt-4o'

# use this incase you are prefering to experiment with local models.
OLLAMA_BASE_URL='http://localhost:11434'
Expand Down
3 changes: 2 additions & 1 deletion bootstraprag/templates/llamaindex/simple_rag/requirements.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,4 +7,5 @@ llama-index-embeddings-ollama==0.3.0
llama-index-vector-stores-qdrant==0.3.0
qdrant-client==1.11.1
pydantic==2.9.0
litserve==0.2.2
litserve==0.2.2
ragas==0.1.20
7 changes: 7 additions & 0 deletions bootstraprag/templates/llamaindex/simple_rag/simple_rag.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@
from llama_index.llms.ollama import Ollama
from llama_index.core.base.response.schema import Response, StreamingResponse, AsyncStreamingResponse, PydanticResponse
from dotenv import load_dotenv, find_dotenv
from test_set_generator import TestSetGenerator
from typing import Union
import qdrant_client
import logging
Expand Down Expand Up @@ -37,6 +38,8 @@ def __init__(self, input_dir: str, similarity_top_k: int = 3, chunk_size: int =
self.query_engine_tools = []
self.show_progress = show_progress

self.test_set_generator = TestSetGenerator()

# use your prefered vector embeddings model
logger.info("initializing the OllamaEmbedding")
embed_model = OllamaEmbedding(model_name=os.environ['OLLAMA_EMBED_MODEL'],
Expand All @@ -63,6 +66,10 @@ def __init__(self, input_dir: str, similarity_top_k: int = 3, chunk_size: int =
self._create_index()

def _create_index(self):

# create an evaluation test set
self.test_set_generator.generate_test_set(input_dir=self.input_dir) # leaving defaults as is.

if self.client.collection_exists(collection_name=os.environ['COLLECTION_NAME']):
try:
self._index = VectorStoreIndex.from_vector_store(vector_store=self.vector_store)
Expand Down
48 changes: 48 additions & 0 deletions bootstraprag/templates/llamaindex/simple_rag/test_set_generator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,48 @@
from llama_index.core import SimpleDirectoryReader
from ragas.testset.generator import TestsetGenerator
from ragas.testset.evolutions import simple, reasoning, multi_context
from llama_index.llms.ollama import Ollama
from llama_index.llms.openai import OpenAI
from llama_index.embeddings.ollama import OllamaEmbedding
from llama_index.embeddings.openai import OpenAIEmbedding
from dotenv import load_dotenv, find_dotenv
import logging
import os

_ = load_dotenv(find_dotenv())
logging.basicConfig(level=int(os.environ['INFO']))
logger = logging.getLogger(__name__)


class TestSetGenerator:
def __init__(self):
# generator with ollama models
# generator_llm = Ollama(model=os.environ.get('OLLAMA_LLM_MODEL'), request_timeout=300)
# critic_llm = Ollama(model=os.environ.get('OLLAMA_LLM_MODEL'), request_timeout=300)
# embeddings = OllamaEmbedding(model_name=os.environ.get('OLLAMA_EMBED_MODEL'), request_timeout=300)

# generator with openai models
generator_llm = OpenAI(model=os.environ.get('OPENAI_MODEL'), timeout=300)
critic_llm = OpenAI(model=os.environ.get('OPENAI_MODEL'), timeout=300)
embeddings = OpenAIEmbedding(model=os.environ.get('OPENAI_EMBED_MODEL'), timeout=300)

self.generator = TestsetGenerator.from_llama_index(
generator_llm=generator_llm,
critic_llm=critic_llm,
embeddings=embeddings,
)

def generate_test_set(self, input_dir, test_size: int = 5, simple_dist: float = 0.5, reasoning_dist: float = 0.25,
multi_context_dist: float = 0.25, show_progress: bool = True):
logger.info('loading docs..')
_docs = SimpleDirectoryReader(input_dir=input_dir).load_data(show_progress=show_progress)
# generate test set
logger.info('test set generation started..')
test_set = self.generator.generate_with_llamaindex_docs(
documents=_docs,
test_size=test_size,
distributions={simple: simple_dist, reasoning: reasoning_dist, multi_context: multi_context_dist},
)
logger.info('test set generation ended..filename: testset.csv')
df = test_set.to_pandas()
df.to_csv(filename="testset.csv")