Merge pull request #641 from langchain-ai/rlm/update-nomic-embd

Update Nomic embeddings

examples/rag/langgraph_adaptive_rag_local.ipynb

@@ -46,7 +46,7 @@
    "outputs": [],
    "source": [
     "%capture --no-stderr\n",
-    "%pip install -U langchain-nomic langchain_community tiktoken langchainhub chromadb langchain langgraph tavily-python"
+    "%pip install -U langchain-nomic langchain_community tiktoken langchainhub chromadb langchain langgraph tavily-python nomic[local]"
    ]
   },
   {
@@ -125,8 +125,8 @@
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.embeddings import GPT4AllEmbeddings\n",
     "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_nomic.embeddings import NomicEmbeddings\n",
     "\n",
     "urls = [\n",
     "    \"https://lilianweng.github.io/posts/2023-06-23-agent/\",\n",
@@ -146,7 +146,8 @@
     "vectorstore = Chroma.from_documents(\n",
     "    documents=doc_splits,\n",
     "    collection_name=\"rag-chroma\",\n",
-    "    embedding=GPT4AllEmbeddings(),\n",
+    "    embedding=NomicEmbeddings(model=\"nomic-embed-text-v1.5\",\n",
+    "                              inference_mode='local'),\n",
     ")\n",
     "retriever = vectorstore.as_retriever()"
    ]

examples/rag/langgraph_crag_local.ipynb

@@ -186,9 +186,9 @@
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.embeddings import GPT4AllEmbeddings\n",
     "from langchain_community.vectorstores import Chroma\n",
     "from langchain_mistralai import MistralAIEmbeddings\n",
+    "from langchain_nomic.embeddings import NomicEmbeddings\n",
     "\n",
     "# Load\n",
     "url = \"https://lilianweng.github.io/posts/2023-06-23-agent/\"\n",
@@ -203,7 +203,8 @@
     "\n",
     "# Embed and index\n",
     "if run_local == \"Yes\":\n",
-    "    embedding = GPT4AllEmbeddings()\n",
+    "    embedding=NomicEmbeddings(model=\"nomic-embed-text-v1.5\",\n",
+    "                              inference_mode='local',)\n",
     "else:\n",
     "    embedding = MistralAIEmbeddings(mistral_api_key=mistral_api_key)\n",
     "\n",

examples/rag/langgraph_rag_agent_llama3_local.ipynb

@@ -51,7 +51,7 @@
    "outputs": [],
    "source": [
     "%%capture --no-stderr\n",
-    "%pip install -U langchain-nomic langchain_community tiktoken langchainhub chromadb langchain langgraph tavily-python gpt4all langchain-text-splitters"
+    "%pip install -U langchain-nomic langchain_community tiktoken langchainhub chromadb langchain langgraph tavily-python nomic[local] langchain-text-splitters"
    ]
   },
   {
@@ -78,7 +78,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 4,
    "id": "2096d49c-d3dc-4329-ada7-aff56d210198",
    "metadata": {},
    "outputs": [],
@@ -90,7 +90,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 5,
    "id": "267c63e1-4c2f-439d-8d95-4c6aa01f41cf",
    "metadata": {},
    "outputs": [],
@@ -98,8 +98,8 @@
     "### Index\n",
     "\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.embeddings import GPT4AllEmbeddings\n",
     "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_nomic.embeddings import NomicEmbeddings\n",
     "from langchain_text_splitters import RecursiveCharacterTextSplitter\n",
     "\n",
     "urls = [\n",
@@ -120,7 +120,8 @@
     "vectorstore = Chroma.from_documents(\n",
     "    documents=doc_splits,\n",
     "    collection_name=\"rag-chroma\",\n",
-    "    embedding=GPT4AllEmbeddings(),\n",
+    "    embedding=NomicEmbeddings(model=\"nomic-embed-text-v1.5\",\n",
+    "                             inference_mode='local'),\n",
     ")\n",
     "retriever = vectorstore.as_retriever()"
    ]

examples/rag/langgraph_self_rag_local.ipynb

@@ -61,7 +61,7 @@
    "outputs": [],
    "source": [
     "%capture --no-stderr\n",
-    "%pip install -U langchain-nomic langchain_community tiktoken langchainhub chromadb langchain langgraph"
+    "%pip install -U langchain-nomic langchain_community tiktoken langchainhub chromadb langchain langgraph nomic[local]"
    ]
   },
   {
@@ -135,15 +135,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "id": "c3bb9060-ad74-4470-9991-2ba167b6b8d8",
    "metadata": {},
    "outputs": [],
    "source": [
     "from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
     "from langchain_community.document_loaders import WebBaseLoader\n",
-    "from langchain_community.embeddings import GPT4AllEmbeddings\n",
     "from langchain_community.vectorstores import Chroma\n",
+    "from langchain_nomic.embeddings import NomicEmbeddings\n",
     "\n",
     "urls = [\n",
     "    \"https://lilianweng.github.io/posts/2023-06-23-agent/\",\n",
@@ -163,7 +163,8 @@
     "vectorstore = Chroma.from_documents(\n",
     "    documents=doc_splits,\n",
     "    collection_name=\"rag-chroma\",\n",
-    "    embedding=GPT4AllEmbeddings(),\n",
+    "    embedding=NomicEmbeddings(model=\"nomic-embed-text-v1.5\",\n",
+    "                             inference_mode='local'),\n",
     ")\n",
     "retriever = vectorstore.as_retriever()"
    ]