Create app.py

app.py

@@ -0,0 +1,164 @@
+import json
+import os
+import warnings
+from typing import List
+from operator import itemgetter
+from dotenv import load_dotenv
+
+from langfuse.callback import CallbackHandler
+langfuse_handler = CallbackHandler(
+    public_key="pk-lf-b5beeffa-b30f-4390-b850-5a1628c7bc5e",
+    secret_key="sk-lf-a3e49606-e293-4d32-b451-21627a02556e",
+    host="https://cloud.langfuse.com"
+)
+
+import gradio as gr
+
+from langchain_openai import OpenAIEmbeddings
+from langchain_openai import ChatOpenAI
+
+from langchain.docstore.document import Document
+
+from langchain.prompts import PromptTemplate
+from langchain.prompts import ChatPromptTemplate
+
+from langchain.chains import RetrievalQA
+
+from langchain_core.output_parsers import StrOutputParser, CommaSeparatedListOutputParser
+from pydantic import BaseModel, Field
+from langchain_core.runnables import RunnablePassthrough
+from langchain_core.runnables import RunnableParallel
+
+from langchain_community.vectorstores import FAISS
+from langchain_community.document_transformers import EmbeddingsRedundantFilter
+
+from langchain.retrievers import EnsembleRetriever
+from langchain.retrievers.merger_retriever import MergerRetriever
+from langchain.retrievers.document_compressors import DocumentCompressorPipeline
+from langchain.retrievers import ContextualCompressionRetriever
+
+#from langchain_cohere import  CohereEmbeddings, CohereRerank
+
+#from langchain_groq import ChatGroq
+
+load_dotenv()
+
+os.getenv("COHERE_API_KEY")
+#os.getenv("GROQ_API_KEY")
+#os.getenv("OPENAI_API_KEY")
+
+embeddings = OpenAIEmbeddings(model="text-embedding-3-large")
+#embeddings_cohere = CohereEmbeddings(model="embed-multilingual-v3.0")
+
+def load_vectorstore(index_name, embeddings, k=100):
+    return FAISS.load_local(index_name, embeddings, allow_dangerous_deserialization=True).as_retriever(
+                            search_kwargs={ "k": k}
+    )
+
+retriever_names = ['large']
+
+retrievers = {}
+retrievers_docs = {}
+
+for name in retriever_names:
+    retrievers[name] = load_vectorstore(f"{name}", embeddings)
+    retrievers_docs[name] = (lambda x: x["input"]) | retrievers[name]
+
+
+def format_docs_with_id(docs: List[Document]) -> str:
+    """
+    Formatte les documents fournis avec des informations pertinentes sur chaque source.
+    Inclut XINumber, Book Number, Raw Material Cost RMC, Fragrance Formula Name et Fragrance Formula Descriptors.
+    Args:
+        docs (List[Document]): Liste des documents ou articles à formater.
+    Returns:
+        str: Représentation formatée des documents.
+    """
+    formatted = [
+        (
+            f"XINumber: {doc.metadata.get('XINumber', 'Missing')}\n"
+            f"Book Number: {doc.metadata.get('Book Number', 'Missing')}\n"
+            f"Raw Material Cost: {doc.metadata.get('RMC', 'Missing')}\n"
+            f"Fragrance Formula Name: {doc.metadata.get('Formula Name', 'Missing')}\n"
+            f"Date Evaluated: {doc.metadata.get('Date Evaluated', 'Missing')}\n"
+            f"Application Product: {doc.metadata.get('Application', 'Missing')}\n"
+            f"Fragrance Type: {doc.metadata.get('Fragrance Type', 'Missing')}\n"
+            f"Fragrance Formula Notes: {doc.page_content}\n"
+        )
+        for doc in docs
+    ]
+    return "\n\n" + "\n\n".join(formatted)
+
+
+def prompt_fn(criteria):
+
+    return (
+            "You are fragrance formula design expert and you have to chose all formulas from context that fits most the client brief."
+            "Return formulas with all their details: XINumber, Book Number, Raw Material Cost RMC, Application Product, Fragrance Formula Name, Fragrance Formula and Descriptors"
+            "Return 15 formulas at least that fits. Reorder the returned formulas according to the matching criterias."
+            "Return only the Formulas with all their details without any additional comments."
+        
+            f"Here are additional criterias to respect and to filter for from context: {criteria}"
+            "\n\nHere is the context: "
+            "{context}"
+            )
+
+llm = ChatOpenAI(temperature=0, model="gpt-4o")
+structured_llm = llm.with_structured_output(CitedAnswer_fr)
+
+retrieve_docs = {name: (lambda x: x["input"]) | retrievers[name] for name in retriever_names}
+
+def legal(question, criteria='select from all context'):
+
+    prompt = ChatPromptTemplate.from_messages([
+    ("system", prompt_fn(criteria)),
+    ("human", "{input}"),
+    ])
+
+
+    rag_chain_from_docs = (
+        RunnablePassthrough.assign(context=(lambda x: format_docs_with_id(x["context"])))
+        | prompt
+        | llm
+    )
+          
+    chains = {
+        name: RunnablePassthrough.assign(context=retrieve_docs[name]).assign(answer=rag_chain_from_docs)
+        for name in retriever_names
+    }
+
+    name = "large"
+    
+    if name not in chains:
+        raise ValueError(f"Invalid typologie: {name}")
+    #try:
+    #result = chains[name].invoke({"input": question})
+    result = chains[name].invoke({"input": question}, config={"callbacks": [langfuse_handler]})
+    return result["answer"].content #result["answer"].articles, result["answer"].citations
+    #except Exception as e:
+    #    return "Je ne sais pa#| "", ""
+        
+
+with gr.Blocks() as demo:
+    gr.Markdown("## OnScent Fragrance Intelligent Library Search")
+    #gr.Markdown("Developed by ScentGenie")
+    gr.Markdown("### Client Brief or Description")
+    
+    with gr.Row():
+        input1 = gr.Textbox(label="Brief", placeholder="Wrapped in a blanket by the fireplace")
+    gr.Markdown("### Additional Criterias")
+    gr.Markdown("Criterias like Application area, RMC, Notes to exclude etc")
+    with gr.Row():
+        input2 = gr.Textbox(label="Additional Criterias (can be left empy)", placeholder=" for hair products with RMC under 15$ and without vanilla note")
+    #with gr.Row():
+    #    input3 = gr.Dropdown(["Advanced", "Fast"], label="Mode", value="Advanced")
+        
+    gr.Markdown("## Recommended Formulas")
+    output1 = gr.Text(label="Recommendations ranked by Relevance")
+    #output2 = gr.Text(label="Documents Sources")
+    #output3 = gr.Text(label="Documents IDs")
+
+    btn = gr.Button("Submit")
+    btn.click(legal, inputs=[input1, input2], outputs=[output1])
+
+demo.launch(debug=True)