Duplicate from NicolasGaudemet/LongTextQuestioner

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: LongTextQuestioner
+emoji: 🌖
+colorFrom: gray
+colorTo: blue
+sdk: gradio
+sdk_version: 3.28.0
+app_file: document_questioner_app.py
+pinned: false
+duplicated_from: NicolasGaudemet/LongTextQuestioner
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

document_questioner_app.py

@@ -0,0 +1,50 @@
+import openai
+import os
+import gradio as gr
+from langchain.document_loaders import DirectoryLoader, TextLoader, UnstructuredFileLoader
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.vectorstores import Chroma
+from langchain.chains import RetrievalQA
+from langchain.chat_models import ChatOpenAI
+
+os.environ["OPENAI_API_KEY"] = "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"
+
+def question_document(Document, Question):
+    # Load documents with DirectoryLoader 
+
+    if not Document.name.endswith('.txt'):
+        return ("Le document doit être un fichier texte (.txt)")
+    
+    loader = TextLoader(Document.name, encoding = "ISO-8859-1")
+
+    #loader = DirectoryLoader("", glob="*.txt", loader_kwargs = {"encoding" : "ISO-8859-1"})
+    txt_docs = loader.load_and_split()
+
+    # Create embeddings
+    embeddings = OpenAIEmbeddings()
+    # Write in DB
+    txt_docsearch = Chroma.from_documents(txt_docs, embeddings)
+
+    # Define LLM
+    llm = ChatOpenAI(model_name="gpt-3.5-turbo", temperature=0.3)
+
+    # Create Retriever
+    qa_txt = RetrievalQA.from_chain_type(llm=llm, 
+                                        chain_type="map_reduce",
+                                        retriever=txt_docsearch.as_retriever()
+                                        )
+
+    answer = qa_txt.run(Question) #+ "If you don't find the answer in the document, don't answer, say you don't know, in the language of the question." )
+    return answer 
+
+#Définition de l'interface
+
+iface = gr.Interface(
+    fn = question_document, 
+    inputs= ["file","text"],
+    outputs = gr.outputs.Textbox(label="Réponse"), 
+    title="Long Text Questioner",
+    description="par Nicolas \nPermet d'interroger un document texte",
+    allow_flagging = "never")
+
+iface.launch()

requirements.txt

@@ -0,0 +1,5 @@
+openai
+langchain
+unstructured
+chromadb
+tiktoken