Upload 4 files

app.py

@@ -1,63 +1,104 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-
-if __name__ == "__main__":
-    demo.launch()
+import os
+import fitz  # PyMuPDF
+from docx import Document
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+import pickle
+from langchain_community.llms import HuggingFaceEndpoint
+from langchain_community.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from fastapi import FastAPI, UploadFile, File
+from typing import List
+
+app = FastAPI()
+
+# Function to extract text from a PDF file
+def extract_text_from_pdf(pdf_path):
+    text = ""
+    doc = fitz.open(pdf_path)
+    for page_num in range(len(doc)):
+        page = doc.load_page(page_num)
+        text += page.get_text()
+    return text
+
+# Function to extract text from a Word document
+def extract_text_from_docx(docx_path):
+    doc = Document(docx_path)
+    text = "\n".join([para.text for para in doc.paragraphs])
+    return text
+
+# Initialize the embedding model
+embedding_model = SentenceTransformer('all-MiniLM-L6-v2')
+
+# Hugging Face API token
+api_token = os.getenv('HUGGINGFACEHUB_API_TOKEN')
+if not api_token:
+    raise ValueError("HUGGINGFACEHUB_API_TOKEN environment variable is not set")
+
+print(f"API Token: {api_token[:5]}...")
+
+# Initialize the HuggingFace LLM
+llm = HuggingFaceEndpoint(
+    endpoint_url="https://api-inference.huggingface.co/models/gpt2",
+    model_kwargs={"api_key": api_token}
+)
+
+# Initialize the HuggingFace embeddings
+embedding = HuggingFaceEmbeddings()
+
+# Load or create FAISS index
+index_path = "faiss_index.pkl"
+if os.path.exists(index_path):
+    with open(index_path, "rb") as f:
+        index = pickle.load(f)
+else:
+    # Create a new FAISS index if it doesn't exist
+    index = faiss.IndexFlatL2(embedding_model.get_sentence_embedding_dimension())
+    with open(index_path, "wb") as f:
+        pickle.dump(index, f)
+
+@app.post("/upload/")
+async def upload_file(files: List[UploadFile] = File(...)):
+    for file in files:
+        content = await file.read()
+        if file.filename.endswith('.pdf'):
+            with open("temp.pdf", "wb") as f:
+                f.write(content)
+            text = extract_text_from_pdf("temp.pdf")
+        elif file.filename.endswith('.docx'):
+            with open("temp.docx", "wb") as f:
+                f.write(content)
+            text = extract_text_from_docx("temp.docx")
+        else:
+            return {"error": "Unsupported file format"}
+
+        # Process the text and update FAISS index
+        sentences = text.split("\n")
+        embeddings = embedding_model.encode(sentences)
+        index.add(np.array(embeddings))
+
+    # Save the updated index
+    with open(index_path, "wb") as f:
+        pickle.dump(index, f)
+
+    return {"message": "Files processed successfully"}
+
+@app.post("/query/")
+async def query(text: str):
+    # Encode the query text
+    query_embedding = embedding_model.encode([text])
+    
+    # Search the FAISS index
+    D, I = index.search(np.array(query_embedding), k=5)
+    
+    top_documents = []
+    for idx in I[0]:
+        if idx != -1:  # Ensure that a valid index is found
+            top_documents.append(f"Document {idx}")
+
+    return {"top_documents": top_documents}
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

faiss_index.pkl

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ad23da459429f29dfd33e3b9cbf1852c2a31bcc85a7c6ca28ebbe2b597bcb0
+size 46191

requirements.txt

@@ -1 +1,12 @@
-huggingface_hub==0.22.2
+python=3.8
+fastapi
+uvicorn
+pydantic
+fitz
+python-docx
+sentence-transformers
+faiss-cpu
+langchain
+langchain_community
+huggingface-hub
+transformers