Duplicate from fengtc/langchain-text-local-glm-faiss

.gitattributes

@@ -0,0 +1,36 @@
+*.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
+*.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
+ANSYS_Fluent_Text_Command_List.pdf filter=lfs diff=lfs merge=lfs -text

ANSYS_Fluent_Text_Command_List.pdf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dd5c52133e79300143e09f32410d9d0372ff27d0ef8371ea9800eb76fa5cb44
+size 4218442

README.md

@@ -0,0 +1,14 @@
+---
+title: Langchain Pdf Openai Faiss
+emoji: ⚡
+colorFrom: indigo
+colorTo: purple
+sdk: gradio
+sdk_version: 3.39.0
+app_file: app.py
+pinned: false
+license: openrail
+duplicated_from: fengtc/langchain-text-local-glm-faiss
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,62 @@
+from langchain.embeddings.openai import OpenAIEmbeddings
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.chains.question_answering import load_qa_chain
+from langchain.llms import OpenAI
+from gradio import gradio as gr
+from langchain.chat_models import ChatOpenAI
+#from langchain.memory import ConversationBufferMemor
+from langchain.schema import AIMessage, HumanMessage
+from langchain import PromptTemplate, LLMChain
+from langchain.llms import TextGen
+
+
+
+import os
+OPENAI_API_KEY=os.getenv('OPENAI_API_KEY')
+
+#分割文档
+text_splitter = CharacterTextSplitter(
+     separator="\n",
+     chunk_size=1000,
+     chunk_overlap=200,
+     length_function=len
+ )
+
+texts = text_splitter.split_text("./output_1.txt")
+
+# 嵌入模型
+#embeddings = OpenAIEmbeddings()
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+
+# 加载数据
+docsearch = FAISS.from_texts(texts, embeddings)
+
+model_url = "http://36.103.234.50:5000"
+
+llm = TextGen(model_url=model_url)
+
+chain = load_qa_chain(llm)
+
+def predict(message, history):
+    history_langchain_format = []
+    for human, ai in history:
+        history_langchain_format.append(HumanMessage(content=human))
+        history_langchain_format.append(AIMessage(content=ai))
+    history_langchain_format.append(HumanMessage(content=message))
+    docs = docsearch.similarity_search(message)
+    response = chain.run(input_documents=docs, question=message)
+    
+
+    partial_message = ""
+    for chunk in response:
+        if len(chunk) != 0:
+            partial_message = partial_message + chunk
+            yield partial_message 
+
+    
+    return response
+
+gr.ChatInterface(predict).queue().launch()
+

requirements.txt

@@ -0,0 +1,7 @@
+langchain
+openai
+docsearch
+tiktoken
+texts
+faiss-cpu
+sentence_transformers