Initial commit

README.md

@@ -1,12 +1,12 @@
+
 ---
-title: RAG Interface To Hub
-emoji: 👁
-colorFrom: green
-colorTo: pink
+title: RAG-Interface-to-Hub
+emoji: 🔥
+colorFrom: indigo
+colorTo: indigo
 sdk: gradio
-sdk_version: 4.12.0
-app_file: app.py
+sdk_version: 3.47.1
+app_file: run.py
 pinned: false
+hf_oauth: false
 ---
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

requirements.txt

@@ -0,0 +1,3 @@
+llama-cpp-python[server]
+chromadb
+sentence_transformers

run.py

@@ -0,0 +1,117 @@
+#########################################################################################
+# Title:  Gradio Interface to LLM-chatbot with RAG-funcionality and ChromaDB on HF-Hub 
+# Author: Andreas Fischer
+# Date:   December 29th, 2023
+# Last update: December 29th, 2023
+##########################################################################################
+
+
+# Chroma-DB
+#-----------
+import os
+import chromadb
+dbPath="/home/af/Schreibtisch/gradio/Chroma/db" 
+if(os.path.exists(dbPath)==False): 
+  dbPath="/home/user/app/db"
+print(dbPath)
+#client = chromadb.Client()
+path=dbPath
+client = chromadb.PersistentClient(path=path)
+print(client.heartbeat()) 
+print(client.get_version())  
+print(client.list_collections()) 
+from chromadb.utils import embedding_functions
+default_ef = embedding_functions.DefaultEmbeddingFunction()
+sentence_transformer_ef = embedding_functions.SentenceTransformerEmbeddingFunction(model_name="T-Systems-onsite/cross-en-de-roberta-sentence-transformer")
+#instructor_ef = embedding_functions.InstructorEmbeddingFunction(model_name="hkunlp/instructor-large", device="cuda")
+print(str(client.list_collections()))
+
+global collection
+if("name=ChromaDB1" in str(client.list_collections())):
+  print("ChromaDB1 found!")
+  collection = client.get_collection(name="ChromaDB1", embedding_function=sentence_transformer_ef)
+else:
+  print("ChromaDB1 created!")
+  collection = client.create_collection(
+    "ChromaDB1",
+    embedding_function=sentence_transformer_ef,
+    metadata={"hnsw:space": "cosine"})
+  
+  collection.add(
+    documents=["The meaning of life is to love.", "This is a sentence", "This is a sentence too"], 
+    metadatas=[{"source": "notion"}, {"source": "google-docs"}, {"source": "google-docs"}], 
+    ids=["doc1", "doc2", "doc3"], 
+  )
+
+print("Database ready!")
+print(collection.count()) 
+
+
+# Model
+#-------
+
+from huggingface_hub import InferenceClient
+import gradio as gr
+
+client = InferenceClient(
+    "mistralai/Mixtral-8x7B-Instruct-v0.1"
+    #"mistralai/Mistral-7B-Instruct-v0.1"
+)
+
+
+# Gradio-GUI
+#------------
+
+import gradio as gr
+import json
+
+def format_prompt(message, history):
+  prompt = "<s>"
+  for user_prompt, bot_response in history:
+    prompt += f"[INST] {user_prompt} [/INST]"
+    prompt += f" {bot_response}</s> "
+  prompt += f"[INST] {message} [/INST]"
+  return prompt
+
+def response(
+    prompt, history, temperature=0.9, max_new_tokens=500, top_p=0.95, repetition_penalty=1.0,
+):
+    temperature = float(temperature)
+    if temperature < 1e-2: temperature = 1e-2
+    top_p = float(top_p)
+    generate_kwargs = dict(
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_p=top_p,
+        repetition_penalty=repetition_penalty,
+        do_sample=True,
+        seed=42,
+    )
+    addon=""
+    results=collection.query(
+      query_texts=[prompt],
+      n_results=2,
+      #where={"source": "google-docs"}
+      #where_document={"$contains":"search_string"}
+    )
+    dists=["<small>(relevance: "+str(round((1-d)*100/100))+";" for d in results['distances'][0]]
+    sources=["source: "+s["source"]+")</small>" for s in results['metadatas'][0]]
+    results=results['documents'][0]
+    combination = zip(results,dists,sources)
+    combination = [' '.join(triplets) for triplets in combination]
+    print(combination)
+    if(len(results)>1):
+      addon=" Bitte berücksichtige bei deiner Antwort ggf. folgende Auszüge aus unserer Datenbank, sofern sie für die Antwort erforderlich sind. Beantworte die Frage knapp und präzise. Ignoriere unpassende Datenbank-Auszüge OHNE sie zu kommentieren, zu erwähnen oder aufzulisten:\n"+"\n".join(results)
+    system="Du bist ein KI-basiertes Assistenzsystem."+addon+"\n\nUser-Anliegen:"   
+    #body={"prompt":system+"### Instruktion:\n"+message+"\n\n### Antwort:","max_tokens":500, "echo":"False","stream":"True"} #e.g. SauerkrautLM
+    formatted_prompt = format_prompt(system+"\n"+prompt, history)
+    stream = client.text_generation(formatted_prompt, **generate_kwargs, stream=True, details=True, return_full_text=False)
+    output = ""
+    for response in stream:
+        output += response.token.text
+        yield output
+    output=output+"\n\n<br><details open><summary><strong>Sources</strong></summary><br><ul>"+ "".join(["<li>" + s + "</li>" for s in combination])+"</ul></details>"
+    yield output
+
+gr.ChatInterface(response, chatbot=gr.Chatbot(render_markdown=True),title="RAG-Interface").queue().launch(share=True) #False, server_name="0.0.0.0", server_port=7864)
+print("Interface up and running!")