Upload RagBotAssignment.py

RagBotAssignment.py

@@ -0,0 +1,87 @@
+# -*- coding: utf-8 -*-
+"""RagBot (2).ipynb
+
+Automatically generated by Colab.
+
+Original file is located at
+    https://colab.research.google.com/drive/1pDSwQZ5XyUQf_efd7Y1dJsLE_L8JmEda
+"""
+
+!pip install pypdf
+
+!pip install -q transformers einops accelerate langchain bitsandbytes
+
+!pip install sentence_transformers
+
+!pip install llama_index
+!pip install llama-index-llms-huggingface
+!pip install llama-index-readers-web
+!pip install llama-index-embeddings-langchain
+
+from llama_index.core import VectorStoreIndex,SimpleDirectoryReader,ServiceContext
+from llama_index.llms.huggingface import HuggingFaceLLM
+from llama_index.core.prompts.prompts import SimpleInputPrompt
+
+documents = SimpleDirectoryReader('/content/data').load_data()
+documents
+
+system_prompts = """
+You are a Q&A assistant. Your goal is to answer questions as
+accurately as possible based on the instructions and context provided.
+"""
+## Default format supportable by LLama2
+query_wrapper_prompt = SimpleInputPrompt("<|USER|>{query_str}<|ASSISTANT|>")
+
+!!huggingface-cli login
+
+
+
+import torch
+
+llm = HuggingFaceLLM(
+    context_window=4096,
+    max_new_tokens=256,
+    generate_kwargs={"temperature": 0.0, "do_sample": False},
+    system_prompt=system_prompts,
+    query_wrapper_prompt=query_wrapper_prompt,
+    tokenizer_name="meta-llama/Llama-2-7b-chat-hf",
+    model_name="meta-llama/Llama-2-7b-chat-hf",
+    device_map="auto",
+    # uncomment this if using CUDA to reduce memory usage
+    model_kwargs={"torch_dtype": torch.float16 , "load_in_8bit":True}
+)
+
+from langchain.embeddings.huggingface import HuggingFaceEmbeddings
+from llama_index.core import ServiceContext
+from llama_index.embeddings.langchain import LangchainEmbedding
+
+embed_model=LangchainEmbedding(
+    HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2"))
+
+service_context=ServiceContext.from_defaults(
+    chunk_size=1024,
+    llm=llm,
+    embed_model=embed_model
+)
+
+index=VectorStoreIndex.from_documents(documents,service_context=service_context)
+
+query_engine=index.as_query_engine()
+
+response=query_engine.query("who is ceo of i2e")
+print(response)
+
+response=query_engine.query("who is ceo of google")
+print(response)
+
+response=query_engine.query("who is vishal, give a short discription of him")
+print(response)
+
+response=query_engine.query("who is vishal, give a long discription of him")
+print(response)
+
+response=query_engine.query("what is i2e")
+print(response)
+
+response=query_engine.query("about home page")
+print(response)