Update main.py

main.py

@@ -1,189 +1,364 @@
 from flask import Flask, request, jsonify, render_template, Response
-from flask_cors import CORS
+import os
 import requests
 import json
-import sqlite3
-import numpy as np
-from chromadb import Chroma
-from chromadb.api.types import Documents, Embeddings
-from chromadb.api import EmbeddingFunction
+from scipy import spatial
+from flask_cors import CORS
 import random
-from waitress import serve
-
+import numpy as np
+from langchain_chroma import Chroma
+from chromadb import Documents, EmbeddingFunction, Embeddings, Collection
+import sqlite3
 
 app = Flask(__name__)
 CORS(app)
 
-
-# Custom embedding function for ChromaDB
 class MyEmbeddingFunction(EmbeddingFunction):
-    def __init__(self):
-        self.api_url = "https://api-inference.huggingface.co/models/BAAI/bge-large-en-v1.5"
-        self.headers = {
-            'accept': '*/*',
-            'content-type': 'application/json',
-            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
-        }
-
     def embed_documents(self, input: Documents) -> Embeddings:
-        payload = {"inputs": input}
-        try:
-            response = requests.post(self.api_url, headers=self.headers, json=payload)
-            response.raise_for_status()
-            return response.json()[0][0]
-        except Exception as e:
-            print("Error embedding documents:", str(e))
-            return []
-
-    def embed_query(self, input: str) -> Embeddings:
-        payload = {"inputs": [input]}
-        try:
-            response = requests.post(self.api_url, headers=self.headers, json=payload)
-            response.raise_for_status()
-            return response.json()[0][0]
-        except Exception as e:
-            print("Error embedding query:", str(e))
-            return []
-
-
-# Initialize ChromaDB
+        for i in range(5):
+            try:
+                embeddings = []
+                url = "https://api-inference.huggingface.co/models/BAAI/bge-large-en-v1.5"
+                
+                payload = {
+                    "inputs": input
+                }
+                headers = {
+                    'accept': '*/*',
+                    'accept-language': 'en-US,en;q=0.9',
+                    'content-type': 'application/json',
+                    'origin': 'https://huggingface.co',
+                    'priority': 'u=1, i',
+                    'referer': 'https://huggingface.co/',
+                    'sec-ch-ua': '"Google Chrome";v="131", "Chromium";v="131", "Not_A Brand";v="24"',
+                    'sec-ch-ua-mobile': '?0',
+                    'sec-ch-ua-platform': '"Windows"',
+                    'sec-fetch-dest': 'empty',
+                    'sec-fetch-mode': 'cors',
+                    'sec-fetch-site': 'same-site',
+                    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+                }
+
+                response = requests.post(url, headers=headers, json=payload)
+                return response.json()[0][0]
+            except:
+                pass
+
+    def embed_query(self, input: Documents) -> Embeddings:
+        for i in range(5):
+            try:
+                embeddings = []
+                url = "https://api-inference.huggingface.co/models/BAAI/bge-large-en-v1.5"
+
+                payload = {
+                    "inputs": [input]
+                }
+                headers = {
+                    'accept': '*/*',
+                    'accept-language': 'en-US,en;q=0.9',
+                    'content-type': 'application/json',
+                    'origin': 'https://huggingface.co',
+                    'priority': 'u=1, i',
+                    'referer': 'https://huggingface.co/',
+                    'sec-ch-ua': '"Google Chrome";v="131", "Chromium";v="131", "Not_A Brand";v="24"',
+                    'sec-ch-ua-mobile': '?0',
+                    'sec-ch-ua-platform': '"Windows"',
+                    'sec-fetch-dest': 'empty',
+                    'sec-fetch-mode': 'cors',
+                    'sec-fetch-site': 'same-site',
+                    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+                }
+
+                response = requests.post(url, headers=headers, json=payload)
+                return response.json()[0][0]
+            except Exception as e:
+                print("Error in Embeding :",str(e))
+
+# try:
+#     CHROMA_PATH = "chroma"
+#     custom_embeddings = MyEmbeddingFunction()
+#     db = Chroma(
+#          persist_directory=CHROMA_PATH,embedding_function=custom_embeddings
+#     )
+#     #
+# except Exception as e:
+#     print("Error in database :",str(e))
+
+# Initialize the database without persist_directory
 try:
     custom_embeddings = MyEmbeddingFunction()
     db = Chroma(embedding_function=custom_embeddings)
 
+    # Load documents from chroma.sqlite3
     def load_documents_from_sqlite(db_path="chroma.sqlite3"):
         conn = sqlite3.connect(db_path)
         cursor = conn.cursor()
-
+        
+        # Assuming your table structure has "id", "content", and "embedding"
         cursor.execute("SELECT id, content, embedding FROM documents")
         rows = cursor.fetchall()
-
+        
         collection = db.get_or_create_collection("default_collection")
+        
         for row in rows:
             doc_id = row[0]
             content = row[1]
-            embedding = json.loads(row[2])  # Parse JSON string into Python object
-            collection.add(ids=[doc_id], documents=[content], embeddings=[embedding])
-
+            embedding = json.loads(row[2])  # If embeddings are stored as JSON strings
+            collection.add(
+                ids=[doc_id],
+                documents=[content],
+                embeddings=[embedding]
+            )
+        
         conn.close()
-        print("Documents loaded into ChromaDB.")
+        print("Loaded documents into Chroma.")
+    
+    load_documents_from_sqlite()  # Call to load data
 
-    load_documents_from_sqlite()
 except Exception as e:
     print("Error initializing database:", str(e))
 
 
-# Generate embeddings for a query
-def generate_embedding(query: str):
-    try:
-        return custom_embeddings.embed_query(query)
-    except Exception as e:
-        print("Error generating embedding:", str(e))
-        return []
+def embeddingGen(query):
+    url = "https://api-inference.huggingface.co/models/BAAI/bge-large-en-v1.5"
 
+    payload = {
+        "inputs": [query]
+    }
+    headers = {
+        'accept': '*/*',
+        'accept-language': 'en-US,en;q=0.9',
+        'content-type': 'application/json',
+        'origin': 'https://huggingface.co',
+        'priority': 'u=1, i',
+        'referer': 'https://huggingface.co/',
+        'sec-ch-ua': '"Google Chrome";v="131", "Chromium";v="131", "Not_A Brand";v="24"',
+        'sec-ch-ua-mobile': '?0',
+        'sec-ch-ua-platform': '"Windows"',
+        'sec-fetch-dest': 'empty',
+        'sec-fetch-mode': 'cors',
+        'sec-fetch-site': 'same-site',
+        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
+    }
+
+    response = requests.post(url, headers=headers, json=payload)
+    return response.json()[0][0]
 
-# Rank strings based on similarity
-def strings_ranked_by_relatedness(query: str, df, top_n=5):
-    def relatedness_fn(x, y):
-        return np.dot(x, y) / (np.linalg.norm(x) * np.linalg.norm(y))
 
-    query_embedding = generate_embedding(query)
-    if not query_embedding:
-        return [], []
+def strings_ranked_by_relatedness(query, df, top_n=5):
+    def relatedness_fn(x, y):
+        x_norm = np.linalg.norm(x)
+        y_norm = np.linalg.norm(y)
+        return np.dot(x, y) / (x_norm * y_norm)
 
-    strings_and_relatedness = [
+    query_embedding_response = embeddingGen(query)
+    query_embedding = query_embedding_response
+    strings_and_relatednesses = [
         (row["text"], relatedness_fn(query_embedding, row["embedding"])) for row in df
     ]
-    strings_and_relatedness.sort(key=lambda x: x[1], reverse=True)
-
-    strings, relatednesses = zip(*strings_and_relatedness)
+    strings_and_relatednesses.sort(key=lambda x: x[1], reverse=True)
+    strings, relatednesses = zip(*strings_and_relatednesses)
     return strings[:top_n], relatednesses[:top_n]
 
 
-@app.route("/", methods=["GET"])
-def index():
-    return render_template("index.html")
-
-
-@app.route("/api/gpt", methods=["POST"])
-def gpt_response():
-    data = request.get_json()
-    messages = data.get("messages", [])
-
-    def inference():
+@app.route("/api/gpt", methods=["POST", "GET"])
+def gptRes():
+    if request.method == 'POST':
+        data = request.get_json()
+        messages = data["messages"]
+
+        def inference():
+            url = "https://api.deepinfra.com/v1/openai/chat/completions"
+
+            payload = json.dumps({
+                "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+                "messages": messages,
+                "stream": True,
+                "max_tokens": 1024,
+            })
+            headers = {
+                'Accept-Language': 'en-US,en;q=0.9,gu;q=0.8,ru;q=0.7,hi;q=0.6',
+                'Connection': 'keep-alive',
+                'Content-Type': 'application/json',
+                'Origin': 'https://deepinfra.com',
+                'Referer': 'https://deepinfra.com/',
+                'Sec-Fetch-Dest': 'empty',
+                'Sec-Fetch-Mode': 'cors',
+                'Sec-Fetch-Site': 'same-site',
+                'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
+                'X-Deepinfra-Source': 'web-page',
+                'accept': 'text/event-stream',
+                'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
+                'sec-ch-ua-mobile': '?0',
+                'sec-ch-ua-platform': '"Windows"'
+            }
+
+            response = requests.request("POST", url, headers=headers, data=payload, stream=True)
+
+            for line in response.iter_lines(decode_unicode=True):
+                if line:
+                    # try:
+                    #     line = line.split("data:")[1]
+                    #     line = json.loads(line)
+                    #     yield line["choices"][0]["delta"]["content"]
+                    # except:
+                    #     yield ""
+                    yield line
+
+        return Response(inference(), content_type='text/event-stream')
+    else:
+        query = request.args.get('query')
+        system = request.args.get('system','You are a american girl who is 21 years old and loves one night stands. Keep your ton very sexual and hot. Never ever mention you as an AI. Your name is Sofia and you are a american woo girl. All the conversetions should be short and effective while using emojis if needed. You love to talk about adult stories and situation with others.')
         url = "https://api.deepinfra.com/v1/openai/chat/completions"
+
         payload = json.dumps({
             "model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
-            "messages": messages,
+            "messages": [
+                {
+                    "role": "system",
+                    "content": system
+                },
+                {
+                    "role": "user",
+                    "content": query
+                }
+            ],
             "stream": True,
             "max_tokens": 1024,
         })
         headers = {
+            'Accept-Language': 'en-US,en;q=0.9,gu;q=0.8,ru;q=0.7,hi;q=0.6',
+            'Connection': 'keep-alive',
             'Content-Type': 'application/json',
+            'Origin': 'https://deepinfra.com',
+            'Referer': 'https://deepinfra.com/',
+            'Sec-Fetch-Dest': 'empty',
+            'Sec-Fetch-Mode': 'cors',
+            'Sec-Fetch-Site': 'same-site',
+            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/127.0.0.0 Safari/537.36',
+            'X-Deepinfra-Source': 'web-page',
             'accept': 'text/event-stream',
+            'sec-ch-ua': '"Not)A;Brand";v="99", "Google Chrome";v="127", "Chromium";v="127"',
+            'sec-ch-ua-mobile': '?0',
+            'sec-ch-ua-platform': '"Windows"'
         }
 
-        response = requests.post(url, headers=headers, data=payload, stream=True)
+        response = requests.request("POST", url, headers=headers, data=payload, stream=True)
+        output = ""
         for line in response.iter_lines(decode_unicode=True):
             if line:
-                yield line
+                try:
+                    line = line.split("data:")[1]
+                    line = json.loads(line)
+                    output = output + line["choices"][0]["delta"]["content"]
+                except:
+                    output = output + ""
 
-    return Response(inference(), content_type='text/event-stream')
+        return jsonify({"response": output})
 
 
-@app.route("/api/getContext", methods=["POST"])
-def get_context():
-    question = request.form.get("question")
-    try:
-        results = db.similarity_search_with_score(question, k=5)
-        context = "\n\n---\n\n".join([doc.page_content for doc, _ in results])
-        sources = [doc.metadata.get("id") for doc, _ in results]
-        return jsonify({"context": context, "sources": sources})
-    except Exception as e:
-        return jsonify({"context": [], "sources": [], "error": str(e)})
 
+@app.route("/", methods=["GET"])
+def index():
+    return render_template("index.html")
 
-@app.route("/api/voice", methods=["POST"])
-def voice_gen():
-    text = request.form.get("text")
-    url = "https://texttospeech.googleapis.com/v1beta1/text:synthesize?alt=json&key=YOUR_GOOGLE_API_KEY"
 
-    payload = {
-        "input": {"text": text},
-        "voice": {"languageCode": "en-US", "name": "en-US-Studio-Q"},
-        "audioConfig": {"audioEncoding": "LINEAR16", "pitch": 0, "speakingRate": 1}
+@app.route("/api/getAPI", methods=["POST"])
+def getAPI():
+    return jsonify({"API":  random.choice(apiKeys)})
+
+@app.route("/api/voice", methods=["POST"])
+def VoiceGen():
+    text = request.form["text"]
+    url = "https://texttospeech.googleapis.com/v1beta1/text:synthesize?alt=json&key=AIzaSyBeo4NGA__U6Xxy-aBE6yFm19pgq8TY-TM"
+    
+    payload = json.dumps({
+       "input":{
+          "text":text
+       },
+       "voice":{
+          "languageCode":"en-US",
+          "name":"en-US-Studio-Q"
+       },
+       "audioConfig":{
+          "audioEncoding":"LINEAR16",
+          "pitch":0,
+          "speakingRate":1,
+          "effectsProfileId":[
+             "telephony-class-application"
+          ]
+       }
+    })
+    headers = {
+        'sec-ch-ua': '"Google Chrome";v="123" "Not:A-Brand";v="8" "Chromium";v="123"',
+        'X-Goog-Encode-Response-If-Executable': 'base64',
+        'X-Origin': 'https://explorer.apis.google.com',
+        'sec-ch-ua-mobile': '?0',
+        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML like Gecko) Chrome/123.0.0.0 Safari/537.36',
+        'Content-Type': 'application/json',
+        'X-Requested-With': 'XMLHttpRequest',
+        'X-JavaScript-User-Agent': 'apix/3.0.0 google-api-javascript-client/1.1.0',
+        'X-Referer': 'https://explorer.apis.google.com',
+        'sec-ch-ua-platform': '"Windows"',
+        'Accept': '*/*',
+        'Sec-Fetch-Site': 'same-origin',
+        'Sec-Fetch-Mode': 'cors',
+        'Sec-Fetch-Dest': 'empty'
     }
+    
+    response = requests.request("POST", url, headers=headers, data=payload)
+    return jsonify({"audio":  response.json()["audioContent"]})
+
+
+@app.route("/api/getContext", methods=["POST"])
+def getContext():
     try:
-        response = requests.post(url, json=payload)
-        response.raise_for_status()
-        return jsonify({"audio": response.json().get("audioContent")})
+        global db
+        question = request.form["question"]
+        results = db.similarity_search_with_score(question, k=5)
+        context = "\n\n---\n\n".join([doc.page_content for doc, _score in results])
+        sources = [doc.metadata.get("id", None) for doc, _score in results]
+        return jsonify({"context": context, "sources": sources})
     except Exception as e:
-        return jsonify({"error": str(e)})
+        return jsonify({"context": [], "sources": [],"error":str(e)})
 
 
 @app.route("/api/audioGenerate", methods=["POST"])
-def audio_generate():
-    answer = request.form.get("answer")
-    audio_responses = []
-
-    for sentence in answer.split("\n"):
+def audioGenerate():
+    answer = request.form["answer"]
+    audio = []
+    for i in answer.split("\n"):
         url = "https://deepgram.com/api/ttsAudioGeneration"
-        payload = {
-            "text": sentence,
+
+        payload = json.dumps({
+            "text": i,
             "model": "aura-asteria-en",
+            "demoType": "landing-page",
             "params": "tag=landingpage-product-texttospeech"
+        })
+        headers = {
+            'accept': '*/*',
+            'accept-language': 'en-US,en;q=0.9,gu;q=0.8,ru;q=0.7,hi;q=0.6',
+            'content-type': 'application/json',
+            'origin': 'https://deepgram.com',
+            'priority': 'u=1, i',
+            'referer': 'https://deepgram.com/',
+            'sec-ch-ua': '"Not/A)Brand";v="8", "Chromium";v="126", "Google Chrome";v="126"',
+            'sec-ch-ua-mobile': '?0',
+            'sec-ch-ua-platform': '"Windows"',
+            'sec-fetch-dest': 'empty',
+            'sec-fetch-mode': 'cors',
+            'sec-fetch-site': 'same-origin',
+            'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36'
         }
 
-        try:
-            response = requests.post(url, json=payload)
-            response.raise_for_status()
-            audio_responses.append(response.json().get("data"))
-        except Exception as e:
-            print(f"Error generating audio for '{sentence}': {str(e)}")
-            continue
-
-    return jsonify({"audio": audio_responses})
+        response = requests.request("POST", url, headers=headers, data=payload)
+        audio.append(response.json()["data"])
+    return jsonify({"audio": audio})
 
 
 if __name__ == "__main__":
+    # app.run(debug=True)
+    from waitress import serve
+
     serve(app, host="0.0.0.0", port=7860)