data push

Dockerfile

@@ -0,0 +1,11 @@
+FROM python:3.10-slim
+
+WORKDIR /app
+
+COPY ./ /app
+
+RUN pip install -r requirements.txt
+
+
+CMD fastapi run --reload --host=0.0.0.0 --port=7860
+

README.md

@@ -0,0 +1,12 @@
+---
+
+title: test-api
+emoji: 🐳
+colorFrom: purple
+colorTo: gray
+sdk: docker
+app_port: 7860
+---
+
+# test_api  
+

app.py

@@ -0,0 +1,33 @@
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+from deep_translator import GoogleTranslator
+from fastapi.responses import JSONResponse
+from main import process
+# Create the FastAPI app instance
+app = FastAPI()
+
+# Root endpoint
+@app.get("/")
+async def home():
+    return {"message": "Welcome to my FastAPI API on Hugging Face Spaces!"}
+
+# Translate endpoint that accepts a query parameter 'text'
+@app.get("/translate")
+async def translate(text: str = ""):
+    if not text:
+        raise HTTPException(status_code=400, detail="No text provided")
+    
+    # Perform translation using deep_translator
+    translator = GoogleTranslator(source="auto", target="mr")
+    result = translator.translate(text)
+    
+    return {"result": result}
+
+@app.get("/chatbot")
+async def chatbot(text: str = ""):
+    if not text:
+        raise HTTPException(status_code=400, detail="No text provided")
+    # Perform translation using deep_translator
+    result = process(query=text)
+    return {"result": result}
+

main.py

@@ -0,0 +1,50 @@
+import numpy as np
+from sklearn.metrics.pairwise import cosine_similarity
+from utils.convert_embedding import GetEmbedding
+import random
+import pickle
+import os 
+
+
+
+user_query = "hi"
+def dump_user_question(query):
+    try:
+        if os.path.exists:
+            with open(r"data\question_data.pkl","rb") as f:
+                que = pickle.load(f)
+        else:
+            que = []
+        que.append(query)
+        with open(r"data\question_data.pkl","wb") as f:
+                que = pickle.dump(que,f)
+    except:
+        with open(r"data\question_data.pkl","wb") as f:
+            pickle.dump([],f)
+
+def process(user_query):
+    dump_user_question(user_query)
+    user_embedding = GetEmbedding([user_query]).user_query_emb()
+    with open(r"data\question_embedding_latest.pkl","rb") as f:
+        load_embedding = pickle.load(f)
+
+    with open(r"data\answer.pkl","rb") as f:
+        ans = pickle.load(f)
+    similarity_scores = cosine_similarity(user_embedding, load_embedding)
+    index = np.argmax(similarity_scores)
+    answer = ans[index]
+
+    return random.choice(answer)
+
+
+
+if __name__ == "__main__":
+    pass
+    # for _ in range(3):
+    #     user = input("How can i help you :? \n")
+    #     result = process(user)
+    #     print(result)
+
+    # with open(r"data\question_data.pkl","rb") as f:
+    #     que = pickle.load(f)
+    # print(que)

requirements.txt

@@ -0,0 +1,4 @@
+deep-translator
+fastapi[standard]
+gunicorn
+sentence_transformers

utils/convert_embedding.py

@@ -0,0 +1,24 @@
+from sentence_transformers import SentenceTransformer
+
+class GetEmbedding:
+    def __init__(self,data:list):
+        self.data = data
+    def user_query_emb(self,model_name:str = 'paraphrase-MiniLM-L6-v2'):
+        try:
+            model = SentenceTransformer(model_name_or_path=model_name)
+            embedding = model.encode(self.data)
+            return embedding
+        except Exception as e:
+            print(e)
+
+    def convert_data(self,model_name:str = 'paraphrase-MiniLM-L6-v2'):
+        try:
+            model = SentenceTransformer(model_name)
+            embeddings = model.encode(self.data)
+            return embeddings
+        except Exception as e:
+            print(e)
+
+if __name__ == "__main__":
+    emb = GetEmbedding("lalit")
+    print( emb)

utils/vector_store.py

@@ -0,0 +1,50 @@
+from faiss import IndexFlatL2,write_index,read_index
+import numpy as np
+from utils.convert_embedding import GetEmbedding
+
+
+class VectorStore:
+    def __init__(self):
+        pass
+
+    def store_vectors(self,data:list,embedding_space_name:str = 'faiss_index.index',numpy_emb_space:str = 'embeddings.npy' ):
+        try:
+            embeddings = GetEmbedding(data=data).convert_emb()
+            diamension = embeddings.shape[1]
+            print("Diamension",diamension)
+            # Create L2 distance index
+            index = IndexFlatL2(diamension)
+
+            index.add(embeddings)
+
+            write_index(index, embedding_space_name)
+
+            # Save embeddings to file
+            np.save(numpy_emb_space, embeddings)
+            return True
+        except Exception as e:
+            print(e)
+            return False
+
+    def get_similary_search(self,query,embedding_space_name:str = 'faiss_index.index',numpy_emb_space:str = 'embeddings.npy',K:int= 1):
+        # Load the FAISS index
+        index = read_index('faiss_index.index')
+
+        # Load the embeddings
+        embeddings_np = np.load('embeddings.npy')
+
+        # Now you can perform similarity searches on the index
+        query = "What is photosynthesis?"
+        query_embedding = GetEmbedding([query]).convert_emb()
+        query_embedding = query_embedding.detach().numpy()
+        # query_embedding = np.array(query_embedding)  # Convert to numpy array
+        # query_embedding = query_embedding.reshape(1, -1)
+        # print("shape")
+        # print(query_embedding.shape)
+        # Perform search
+        distances, indices = index.search(query_embedding, k = K)
+
+        return indices
+
+
+