Upload 4 files

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+llama-2-7b-chat.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text

LoadLLM.py

@@ -0,0 +1,24 @@
+from langchain_community.llms import LlamaCpp
+from langchain.callbacks.manager import CallbackManager
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+
+model_path = 'llama-2-7b-chat.Q5_K_M.gguf'
+
+
+class Loadllm:
+    @staticmethod
+    def load_llm():
+        callback_manager = CallbackManager([StreamingStdOutCallbackHandler()])
+        # Prepare the LLM
+
+        llm = LlamaCpp(
+            model_path=model_path,
+            n_gpu_layers=40,
+            n_batch=512,
+            n_ctx=2048,
+            f16_kv=True,  # MUST set to True, otherwise you will run into problem after a couple of calls
+            callback_manager=callback_manager,
+            verbose=True,
+        )
+
+        return llm

app.py

@@ -0,0 +1,49 @@
+from ctransformers import AutoModelForCausalLM
+from flask import Flask, request, jsonify
+import os
+from langchain_community.document_loaders import PyMuPDFLoader
+from LoadLLM import Loadllm
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+from langchain.chains import ConversationalRetrievalChain
+
+DB_FAISS_PATH = 'vectorstore/db_faiss'
+
+app = Flask(__name__)
+
+@app.route('/')
+def home():
+    return "API Server Running"
+
+
+@app.route('/PromptBuddy', methods=['GET', 'POST'])
+def PromptLLM():
+    pdf_file = request.files['file']
+    pdf_name = pdf_file.filename
+    user_prompt = request.form.get('query')
+    pdf_file.save(pdf_name)
+
+
+    loader = PyMuPDFLoader(file_path=pdf_name)
+    data = loader.load()
+
+
+    # Create embeddings using Sentence Transformers
+    embeddings = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
+
+    # Create a FAISS vector store and save embeddings
+    db = FAISS.from_documents(data, embeddings)
+    db.save_local(DB_FAISS_PATH)
+
+    # Load the language model
+    llm = Loadllm.load_llm()
+
+    # Create a conversational chain
+    chain = ConversationalRetrievalChain.from_llm(llm=llm, retriever=db.as_retriever())
+
+    result = chain({"question": user_prompt, "chat_history":''})
+    return result["answer"]
+
+
+if __name__ == '__main__':
+    app.run(debug=True)

llama-2-7b-chat.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0b99920cf47b94c78d2fb06a1eceb9ed795176dfa3f7feac64629f1b52b997f
+size 4783156928