LangChain RAG Pipeline

from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI
from opentelemetry.exporter.otlp.proto.http.trace_exporter import OTLPSpanExporter
from opentelemetry.sdk import trace as trace_sdk
from opentelemetry.sdk.trace.export import ConsoleSpanExporter, SimpleSpanProcessor

from openinference.instrumentation.langchain import LangChainInstrumentor

# Configure OpenTelemetry
endpoint = "http://127.0.0.1:6006/v1/traces"
tracer_provider = trace_sdk.TracerProvider()
tracer_provider.add_span_processor(SimpleSpanProcessor(OTLPSpanExporter(endpoint)))
tracer_provider.add_span_processor(SimpleSpanProcessor(ConsoleSpanExporter()))

# Instrument LangChain
LangChainInstrumentor().instrument(tracer_provider=tracer_provider)

# Create a prompt template with partial variables
prompt = ChatPromptTemplate.from_template("{x} {y} {z}?").partial(x="why is", z="blue")

# Create a chain with LangChain Expression Language (LCEL)
chain = prompt | ChatOpenAI(model_name="gpt-3.5-turbo")

if __name__ == "__main__":
    # Invoke the chain
    response = chain.invoke(dict(y="sky"))
    print(response.content)

from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain.vectorstores import FAISS
from langchain.chains import create_retrieval_chain
from langchain.chains.combine_documents import create_stuff_documents_chain
from langchain_core.documents import Document

# Sample documents
docs = [
    Document(page_content="LangChain is a framework for developing applications powered by language models."),
    Document(page_content="OpenInference provides OpenTelemetry-native instrumentation for LLM applications."),
    Document(page_content="Phoenix is an open-source observability platform for LLMs."),
]

# Create vector store
embeddings = OpenAIEmbeddings()
vectorstore = FAISS.from_documents(docs, embeddings)
retriever = vectorstore.as_retriever()

# Create prompt
system_prompt = (
    "You are an assistant for question-answering tasks. "
    "Use the following pieces of retrieved context to answer the question. "
    "If you don't know the answer, say that you don't know. "
    "\n\n{context}"
)

prompt = ChatPromptTemplate.from_messages([
    ("system", system_prompt),
    ("human", "{input}"),
])

# Create LLM and chains
llm = ChatOpenAI(model_name="gpt-3.5-turbo")
question_answer_chain = create_stuff_documents_chain(llm, prompt)
rag_chain = create_retrieval_chain(retriever, question_answer_chain)

# Query the RAG chain
response = rag_chain.invoke({"input": "What is OpenInference?"})
print(response["answer"])