Update tools.py

tools.py

@@ -1,41 +1,41 @@
-import os
-from dotenv import load_dotenv
-from langchain.chat_models import ChatOpenAI
-from langchain.document_loaders import PyPDFLoader
-from langchain.text_splitter import CharacterTextSplitter
-from langchain.vectorstores import FAISS
-from langchain.embeddings import HuggingFaceEmbeddings
-import serpapi
-
-load_dotenv()
-
-# LLM (Groq + LLaMA3)
-llm = ChatOpenAI(
-    model="llama3-8b-8192",
-    openai_api_base="https://api.groq.com/openai/v1",
-    openai_api_key=os.environ["GROQ_API_KEY"]
-)
-
-# Embeddings (HuggingFace)
-embeddings = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
-
-# Load PDFs and create FAISS vectorstore
-def load_vectorstore(pdf_dir="pdfs/"):
-    docs = []
-    for file in os.listdir(pdf_dir):
-        if file.endswith(".pdf"):
-            loader = PyPDFLoader(os.path.join(pdf_dir, file))
-            docs.extend(loader.load())
-    splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    chunks = splitter.split_documents(docs)
-    return FAISS.from_documents(chunks, embedding=embeddings)
-
-# Custom Web Search tool using SerpAPI
-def search_tool(query: str):
-    client = serpapi.Client(api_key=os.getenv("SERPAPI_API_KEY"))
-    search = client.search({
-        "engine": "google",
-        "q": query,
-    })
-    results = dict(search)
-    return results["organic_results"][0]["snippet"]  # Return the snippet or any part of the result
+import os
+from dotenv import load_dotenv
+from langchain.chat_models import ChatOpenAI
+from langchain.document_loaders import PyPDFLoader
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+import serpapi
+
+load_dotenv()
+
+# LLM (Groq + LLaMA3)
+llm = ChatOpenAI(
+    model="llama3-8b-8192",
+    openai_api_base="https://api.groq.com/openai/v1",
+    openai_api_key=os.environ["GROQ_API_KEY"]
+)
+
+# Embeddings (HuggingFace)
+embeddings = HuggingFaceEmbeddings(model_name="llama")
+
+# Load PDFs and create FAISS vectorstore
+def load_vectorstore(pdf_dir="pdfs/"):
+    docs = []
+    for file in os.listdir(pdf_dir):
+        if file.endswith(".pdf"):
+            loader = PyPDFLoader(os.path.join(pdf_dir, file))
+            docs.extend(loader.load())
+    splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+    chunks = splitter.split_documents(docs)
+    return FAISS.from_documents(chunks, embedding=embeddings)
+
+# Custom Web Search tool using SerpAPI
+def search_tool(query: str):
+    client = serpapi.Client(api_key=os.getenv("SERPAPI_API_KEY"))
+    search = client.search({
+        "engine": "google",
+        "q": query,
+    })
+    results = dict(search)
+    return results["organic_results"][0]["snippet"]  # Return the snippet or any part of the result