Update app.py

app.py

@@ -1,12 +1,12 @@
 import os
 import sys
+import requests
 from langchain.chains import ConversationalRetrievalChain
 from langchain.document_loaders import PyPDFLoader, Docx2txtLoader, TextLoader
 from langchain.text_splitter import CharacterTextSplitter
 from langchain.vectorstores import Chroma
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.llms.base import LLM
-from huggingface_hub import InferenceClient
 import gradio as gr
 
 # workaround for sqlite in HF spaces
@@ -44,36 +44,43 @@ vectorstore = Chroma(
 vectorstore.add_texts(texts=texts, metadatas=metadatas)
 vectorstore.persist()
 
-# 🔐 Get HF token from env variable
-HF_API_KEY = os.getenv("HF_API_KEY")
-if HF_API_KEY is None:
-    raise ValueError("HF_API_KEY environment variable is not set.")
+# 🔐 Get DeepSeek API key from env
+DEEPSEEK_API_KEY = os.getenv("DEEPSEEK_API_KEY")
+if DEEPSEEK_API_KEY is None:
+    raise ValueError("DEEPSEEK_API_KEY environment variable is not set.")
 
-HF_MODEL = "google/flan-t5-large"
+# 🌟 DeepSeek API endpoint
+DEEPSEEK_API_URL = "https://api.deepseek.com/v1/chat/completions"
 
-# 🤖 Create InferenceClient bound to model
-client = InferenceClient(model=HF_MODEL, token=HF_API_KEY)
-
-# 🔷 Wrap HF client into LangChain LLM interface
-class HuggingFaceInferenceLLM(LLM):
-    """LLM that queries HuggingFace Inference API."""
-
-    client: InferenceClient = client
+# 🔷 Wrap DeepSeek API into LangChain LLM
+class DeepSeekLLM(LLM):
+    """LLM that queries DeepSeek's API."""
+    api_key: str = DEEPSEEK_API_KEY
 
     def _call(self, prompt, stop=None, run_manager=None, **kwargs):
-        response = self.client.text_generation(
-            prompt,
-            max_new_tokens=512,
-            temperature=0.7,
-            do_sample=True,
-        )
-        return response
+        headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json"
+        }
+        payload = {
+            "model": "deepseek-chat",   # adjust if you have a specific model name
+            "messages": [
+                {"role": "system", "content": "You are a helpful assistant."},
+                {"role": "user", "content": prompt}
+            ],
+            "temperature": 0.7,
+            "max_tokens": 512
+        }
+        response = requests.post(DEEPSEEK_API_URL, headers=headers, json=payload)
+        response.raise_for_status()
+        data = response.json()
+        return data["choices"][0]["message"]["content"].strip()
 
     @property
     def _llm_type(self) -> str:
-        return "huggingface_inference_api"
+        return "deepseek_api"
 
-llm = HuggingFaceInferenceLLM()
+llm = DeepSeekLLM()
 
 # 🔗 Conversational chain
 chain = ConversationalRetrievalChain.from_llm(