2023-11-13 22:26:02 +00:00
{
"cells": [
{
"cell_type": "markdown",
"id": "f1571abe-8e84-44d1-b222-e4121fdbb4be",
"metadata": {},
"source": [
"# Advanced RAG Eval\n",
"\n",
"The cookbook walks through the process of running eval(s) on advanced RAG. \n",
"\n",
"This can be very useful to determine the best RAG approach for your application."
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "0d8415ee-709c-407f-9ac2-f03a9d697aaf",
"metadata": {},
"outputs": [],
"source": [
"! pip install -U langchain openai chromadb langchain-experimental # (newest versions required for multi-modal)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "191f8465-fd6b-4017-8f0e-d284971b45ae",
"metadata": {},
"outputs": [],
"source": [
"# lock to 0.10.19 due to a persistent bug in more recent versions\n",
"! pip install \"unstructured[all-docs]==0.10.19\" pillow pydantic lxml pillow matplotlib tiktoken open_clip_torch torch"
]
},
{
"cell_type": "markdown",
"id": "45949db5-d9b6-44a9-85f8-96d83a288616",
"metadata": {},
"source": [
"## Data Loading\n",
"\n",
"Let's look at an [example whitepaper](https://sgp.fas.org/crs/misc/IF10244.pdf) that provides a mixture of tables, text, and images about Wildfires in the US."
]
},
{
"cell_type": "markdown",
"id": "961a42b9-c16b-472e-b994-3c3f73afbbcb",
"metadata": {},
"source": [
"### Option 1: Load text"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "12f24fc0-c176-4201-982b-8a84b278ff1b",
"metadata": {},
"outputs": [],
"source": [
"# Path\n",
"path = \"/Users/rlm/Desktop/cpi/\"\n",
"\n",
"# Load\n",
"from langchain.document_loaders import PyPDFLoader\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"loader = PyPDFLoader(path + \"cpi.pdf\")\n",
"pdf_pages = loader.load()\n",
"\n",
"# Split\n",
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"text_splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=0)\n",
"all_splits_pypdf = text_splitter.split_documents(pdf_pages)\n",
"all_splits_pypdf_texts = [d.page_content for d in all_splits_pypdf]"
]
},
{
"cell_type": "markdown",
"id": "92fc1870-1836-4bc3-945a-78e2c16ad823",
"metadata": {},
"source": [
"### Option 2: Load text, tables, images \n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "7d863632-f894-4471-b4cc-a1d9aa834d29",
"metadata": {},
"outputs": [],
"source": [
"from unstructured.partition.pdf import partition_pdf\n",
"\n",
"# Extract images, tables, and chunk text\n",
"raw_pdf_elements = partition_pdf(\n",
" filename=path + \"cpi.pdf\",\n",
" extract_images_in_pdf=True,\n",
" infer_table_structure=True,\n",
" chunking_strategy=\"by_title\",\n",
" max_characters=4000,\n",
" new_after_n_chars=3800,\n",
" combine_text_under_n_chars=2000,\n",
" image_output_dir_path=path,\n",
")\n",
"\n",
"# Categorize by type\n",
"tables = []\n",
"texts = []\n",
"for element in raw_pdf_elements:\n",
" if \"unstructured.documents.elements.Table\" in str(type(element)):\n",
" tables.append(str(element))\n",
" elif \"unstructured.documents.elements.CompositeElement\" in str(type(element)):\n",
" texts.append(str(element))"
]
},
{
"cell_type": "markdown",
"id": "65f399c5-bd91-4ed4-89c6-c89d2e17466e",
"metadata": {},
"source": [
"## Store\n",
"\n",
"### Option 1: Embed, store text chunks"
]
},
{
"cell_type": "code",
"execution_count": 3,
"id": "7d7ecdb2-0bb5-46b8-bcff-af8fc272e88e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.embeddings import OpenAIEmbeddings\n",
2023-11-14 22:17:44 +00:00
"from langchain.vectorstores import Chroma\n",
2023-11-14 20:58:22 +00:00
"\n",
"baseline = Chroma.from_texts(\n",
" texts=all_splits_pypdf_texts,\n",
" collection_name=\"baseline\",\n",
" embedding=OpenAIEmbeddings(),\n",
")\n",
"retriever_baseline = baseline.as_retriever()"
2023-11-13 22:26:02 +00:00
]
},
{
"cell_type": "markdown",
"id": "6a0eaefe-5e4b-4853-94c7-5abd6f7fbeac",
"metadata": {},
"source": [
"### Option 2: Multi-vector retriever\n",
"\n",
"#### Text Summary"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "3d4b4b43-e96e-48ab-899d-c39d0430562e",
"metadata": {},
"outputs": [],
"source": [
"from langchain.chat_models import ChatOpenAI\n",
"from langchain.prompts import ChatPromptTemplate\n",
docs[patch], templates[patch]: Import from core (#14575)
Update imports to use core for the low-hanging fruit changes. Ran
following
```bash
git grep -l 'langchain.schema.runnable' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.runnable/langchain_core.runnables/g'
git grep -l 'langchain.schema.output_parser' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.output_parser/langchain_core.output_parsers/g'
git grep -l 'langchain.schema.messages' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.messages/langchain_core.messages/g'
git grep -l 'langchain.schema.chat_histry' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.chat_history/langchain_core.chat_history/g'
git grep -l 'langchain.schema.prompt_template' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.prompt_template/langchain_core.prompts/g'
git grep -l 'from langchain.pydantic_v1' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.pydantic_v1/from langchain_core.pydantic_v1/g'
git grep -l 'from langchain.tools.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.tools\.base/from langchain_core.tools/g'
git grep -l 'from langchain.chat_models.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.chat_models.base/from langchain_core.language_models.chat_models/g'
git grep -l 'from langchain.llms.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.llms\.base\ /from langchain_core.language_models.llms\ /g'
git grep -l 'from langchain.embeddings.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.embeddings\.base/from langchain_core.embeddings/g'
git grep -l 'from langchain.vectorstores.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.vectorstores\.base/from langchain_core.vectorstores/g'
git grep -l 'from langchain.agents.tools' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.agents\.tools/from langchain_core.tools/g'
git grep -l 'from langchain.schema.output' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.output\ /from langchain_core.outputs\ /g'
git grep -l 'from langchain.schema.embeddings' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.embeddings/from langchain_core.embeddings/g'
git grep -l 'from langchain.schema.document' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.document/from langchain_core.documents/g'
git grep -l 'from langchain.schema.agent' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.agent/from langchain_core.agents/g'
git grep -l 'from langchain.schema.prompt ' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.prompt\ /from langchain_core.prompt_values /g'
git grep -l 'from langchain.schema.language_model' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.language_model/from langchain_core.language_models/g'
```
2023-12-12 00:49:10 +00:00
"from langchain_core.output_parsers import StrOutputParser\n",
2023-11-13 22:26:02 +00:00
"\n",
"# Prompt\n",
2023-11-14 20:58:22 +00:00
"prompt_text = \"\"\"You are an assistant tasked with summarizing tables and text for retrieval. \\\n",
2023-11-13 22:26:02 +00:00
"These summaries will be embedded and used to retrieve the raw text or table elements. \\\n",
"Give a concise summary of the table or text that is well optimized for retrieval. Table or text: {element} \"\"\"\n",
"prompt = ChatPromptTemplate.from_template(prompt_text)\n",
"\n",
"# Text summary chain\n",
"model = ChatOpenAI(temperature=0, model=\"gpt-4\")\n",
"summarize_chain = {\"element\": lambda x: x} | prompt | model | StrOutputParser()\n",
"\n",
2023-11-14 20:58:22 +00:00
"# Apply to text\n",
2023-11-13 22:26:02 +00:00
"text_summaries = summarize_chain.batch(texts, {\"max_concurrency\": 5})\n",
"\n",
"# Apply to tables\n",
"table_summaries = summarize_chain.batch(tables, {\"max_concurrency\": 5})"
]
},
{
"cell_type": "markdown",
"id": "bdb5c903-5b4c-4ddb-8f9a-e20f5155dfb9",
"metadata": {},
"source": [
"#### Image Summary"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "4570578c-531b-422c-bedd-cc519d9b7887",
"metadata": {},
"outputs": [],
"source": [
"# Image summary chain\n",
2023-11-14 20:58:22 +00:00
"import base64\n",
"import io\n",
2023-11-14 22:17:44 +00:00
"import os\n",
2023-11-13 22:26:02 +00:00
"from io import BytesIO\n",
2023-11-14 22:17:44 +00:00
"\n",
docs[patch], templates[patch]: Import from core (#14575)
Update imports to use core for the low-hanging fruit changes. Ran
following
```bash
git grep -l 'langchain.schema.runnable' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.runnable/langchain_core.runnables/g'
git grep -l 'langchain.schema.output_parser' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.output_parser/langchain_core.output_parsers/g'
git grep -l 'langchain.schema.messages' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.messages/langchain_core.messages/g'
git grep -l 'langchain.schema.chat_histry' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.chat_history/langchain_core.chat_history/g'
git grep -l 'langchain.schema.prompt_template' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.prompt_template/langchain_core.prompts/g'
git grep -l 'from langchain.pydantic_v1' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.pydantic_v1/from langchain_core.pydantic_v1/g'
git grep -l 'from langchain.tools.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.tools\.base/from langchain_core.tools/g'
git grep -l 'from langchain.chat_models.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.chat_models.base/from langchain_core.language_models.chat_models/g'
git grep -l 'from langchain.llms.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.llms\.base\ /from langchain_core.language_models.llms\ /g'
git grep -l 'from langchain.embeddings.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.embeddings\.base/from langchain_core.embeddings/g'
git grep -l 'from langchain.vectorstores.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.vectorstores\.base/from langchain_core.vectorstores/g'
git grep -l 'from langchain.agents.tools' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.agents\.tools/from langchain_core.tools/g'
git grep -l 'from langchain.schema.output' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.output\ /from langchain_core.outputs\ /g'
git grep -l 'from langchain.schema.embeddings' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.embeddings/from langchain_core.embeddings/g'
git grep -l 'from langchain.schema.document' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.document/from langchain_core.documents/g'
git grep -l 'from langchain.schema.agent' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.agent/from langchain_core.agents/g'
git grep -l 'from langchain.schema.prompt ' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.prompt\ /from langchain_core.prompt_values /g'
git grep -l 'from langchain.schema.language_model' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.language_model/from langchain_core.language_models/g'
```
2023-12-12 00:49:10 +00:00
"from langchain_core.messages import HumanMessage\n",
2023-11-14 22:17:44 +00:00
"from PIL import Image\n",
2023-11-13 22:26:02 +00:00
"\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"def encode_image(image_path):\n",
2023-11-14 20:58:22 +00:00
" \"\"\"Getting the base64 string\"\"\"\n",
2023-11-13 22:26:02 +00:00
" with open(image_path, \"rb\") as image_file:\n",
2023-11-14 20:58:22 +00:00
" return base64.b64encode(image_file.read()).decode(\"utf-8\")\n",
"\n",
"\n",
"def image_summarize(img_base64, prompt):\n",
" \"\"\"Image summary\"\"\"\n",
" chat = ChatOpenAI(model=\"gpt-4-vision-preview\", max_tokens=1024)\n",
2023-11-13 22:26:02 +00:00
"\n",
" msg = chat.invoke(\n",
" [\n",
" HumanMessage(\n",
" content=[\n",
2023-11-14 20:58:22 +00:00
" {\"type\": \"text\", \"text\": prompt},\n",
2023-11-13 22:26:02 +00:00
" {\n",
" \"type\": \"image_url\",\n",
2023-11-14 20:58:22 +00:00
" \"image_url\": {\"url\": f\"data:image/jpeg;base64,{img_base64}\"},\n",
2023-11-13 22:26:02 +00:00
" },\n",
" ]\n",
" )\n",
" ]\n",
" )\n",
" return msg.content\n",
"\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"# Store base64 encoded images\n",
"img_base64_list = []\n",
"\n",
"# Store image summaries\n",
"image_summaries = []\n",
"\n",
"# Prompt\n",
2023-11-14 20:58:22 +00:00
"prompt = \"\"\"You are an assistant tasked with summarizing images for retrieval. \\\n",
2023-11-13 22:26:02 +00:00
"These summaries will be embedded and used to retrieve the raw image. \\\n",
"Give a concise summary of the image that is well optimized for retrieval.\"\"\"\n",
"\n",
"# Apply to images\n",
"for img_file in sorted(os.listdir(path)):\n",
2023-11-14 20:58:22 +00:00
" if img_file.endswith(\".jpg\"):\n",
2023-11-13 22:26:02 +00:00
" img_path = os.path.join(path, img_file)\n",
" base64_image = encode_image(img_path)\n",
" img_base64_list.append(base64_image)\n",
2023-11-14 20:58:22 +00:00
" image_summaries.append(image_summarize(base64_image, prompt))"
2023-11-13 22:26:02 +00:00
]
},
{
"cell_type": "markdown",
"id": "87e03f07-4c82-4743-a3c6-d0597fb55107",
"metadata": {},
"source": [
"### Option 2a: Multi-vector retriever w/ raw images\n",
"\n",
"* Return images to LLM for answer synthesis"
]
},
{
"cell_type": "code",
"execution_count": 11,
"id": "6bf8a07d-203f-4397-8b0b-a84ec4d0adab",
"metadata": {},
"outputs": [],
"source": [
"import uuid\n",
"from base64 import b64decode\n",
2023-11-14 22:17:44 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"from langchain.retrievers.multi_vector import MultiVectorRetriever\n",
2023-11-14 22:17:44 +00:00
"from langchain.storage import InMemoryStore\n",
docs[patch], templates[patch]: Import from core (#14575)
Update imports to use core for the low-hanging fruit changes. Ran
following
```bash
git grep -l 'langchain.schema.runnable' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.runnable/langchain_core.runnables/g'
git grep -l 'langchain.schema.output_parser' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.output_parser/langchain_core.output_parsers/g'
git grep -l 'langchain.schema.messages' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.messages/langchain_core.messages/g'
git grep -l 'langchain.schema.chat_histry' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.chat_history/langchain_core.chat_history/g'
git grep -l 'langchain.schema.prompt_template' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.prompt_template/langchain_core.prompts/g'
git grep -l 'from langchain.pydantic_v1' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.pydantic_v1/from langchain_core.pydantic_v1/g'
git grep -l 'from langchain.tools.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.tools\.base/from langchain_core.tools/g'
git grep -l 'from langchain.chat_models.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.chat_models.base/from langchain_core.language_models.chat_models/g'
git grep -l 'from langchain.llms.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.llms\.base\ /from langchain_core.language_models.llms\ /g'
git grep -l 'from langchain.embeddings.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.embeddings\.base/from langchain_core.embeddings/g'
git grep -l 'from langchain.vectorstores.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.vectorstores\.base/from langchain_core.vectorstores/g'
git grep -l 'from langchain.agents.tools' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.agents\.tools/from langchain_core.tools/g'
git grep -l 'from langchain.schema.output' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.output\ /from langchain_core.outputs\ /g'
git grep -l 'from langchain.schema.embeddings' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.embeddings/from langchain_core.embeddings/g'
git grep -l 'from langchain.schema.document' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.document/from langchain_core.documents/g'
git grep -l 'from langchain.schema.agent' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.agent/from langchain_core.agents/g'
git grep -l 'from langchain.schema.prompt ' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.prompt\ /from langchain_core.prompt_values /g'
git grep -l 'from langchain.schema.language_model' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.language_model/from langchain_core.language_models/g'
```
2023-12-12 00:49:10 +00:00
"from langchain_core.documents import Document\n",
2023-11-13 22:26:02 +00:00
"\n",
2023-11-14 20:58:22 +00:00
"\n",
"def create_multi_vector_retriever(\n",
" vectorstore, text_summaries, texts, table_summaries, tables, image_summaries, images\n",
"):\n",
2023-11-13 22:26:02 +00:00
" # Initialize the storage layer\n",
" store = InMemoryStore()\n",
" id_key = \"doc_id\"\n",
"\n",
" # Create the multi-vector retriever\n",
" retriever = MultiVectorRetriever(\n",
" vectorstore=vectorstore,\n",
" docstore=store,\n",
" id_key=id_key,\n",
" )\n",
"\n",
" # Helper function to add documents to the vectorstore and docstore\n",
" def add_documents(retriever, doc_summaries, doc_contents):\n",
" doc_ids = [str(uuid.uuid4()) for _ in doc_contents]\n",
" summary_docs = [\n",
" Document(page_content=s, metadata={id_key: doc_ids[i]})\n",
" for i, s in enumerate(doc_summaries)\n",
" ]\n",
" retriever.vectorstore.add_documents(summary_docs)\n",
" retriever.docstore.mset(list(zip(doc_ids, doc_contents)))\n",
"\n",
" # Add texts, tables, and images\n",
" # Check that text_summaries is not empty before adding\n",
" if text_summaries:\n",
" add_documents(retriever, text_summaries, texts)\n",
" # Check that table_summaries is not empty before adding\n",
" if table_summaries:\n",
" add_documents(retriever, table_summaries, tables)\n",
" # Check that image_summaries is not empty before adding\n",
" if image_summaries:\n",
" add_documents(retriever, image_summaries, images)\n",
"\n",
" return retriever\n",
"\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"# The vectorstore to use to index the summaries\n",
2023-11-14 20:58:22 +00:00
"multi_vector_img = Chroma(\n",
" collection_name=\"multi_vector_img\", embedding_function=OpenAIEmbeddings()\n",
")\n",
2023-11-13 22:26:02 +00:00
"\n",
"# Create retriever\n",
2023-11-14 20:58:22 +00:00
"retriever_multi_vector_img = create_multi_vector_retriever(\n",
" multi_vector_img,\n",
" text_summaries,\n",
" texts,\n",
" table_summaries,\n",
" tables,\n",
" image_summaries,\n",
" img_base64_list,\n",
")"
2023-11-13 22:26:02 +00:00
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "84d5b4ea-51b8-49cf-8ad1-db8f7a50e3cf",
"metadata": {},
"outputs": [],
"source": [
2023-11-14 20:58:22 +00:00
"# Testing on retrieval\n",
"query = \"What percentage of CPI is dedicated to Housing, and how does it compare to the combined percentage of Medical Care, Apparel, and Other Goods and Services?\"\n",
"suffix_for_images = \" Include any pie charts, graphs, or tables.\"\n",
"docs = retriever_multi_vector_img.get_relevant_documents(query + suffix_for_images)"
2023-11-13 22:26:02 +00:00
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "8db51ac6-ec0c-4c5d-a9a7-0316035e139d",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<img src=\"data:image/jpeg;base64,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
],
"text/plain": [
"<IPython.core.display.HTML object>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
2023-11-14 22:17:44 +00:00
"from IPython.display import HTML, display\n",
2023-11-13 22:26:02 +00:00
"\n",
2023-11-14 20:58:22 +00:00
"\n",
"def plt_img_base64(img_base64):\n",
2023-11-13 22:26:02 +00:00
" # Create an HTML img tag with the base64 string as the source\n",
" image_html = f'<img src=\"data:image/jpeg;base64,{img_base64}\" />'\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
" # Display the image by rendering the HTML\n",
" display(HTML(image_html))\n",
"\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"plt_img_base64(docs[1])"
]
},
{
"cell_type": "markdown",
"id": "48b268ec-db04-4107-9833-ea1615f6dbd1",
"metadata": {},
"source": [
"### Option 2b: Multi-vector retriever w/ image summaries\n",
"\n",
"* Return text summary of images to LLM for answer synthesis"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "ae57c804-0dd1-4806-b761-a913efc4f173",
"metadata": {},
"outputs": [],
"source": [
"# The vectorstore to use to index the summaries\n",
2023-11-14 20:58:22 +00:00
"multi_vector_text = Chroma(\n",
" collection_name=\"multi_vector_text\", embedding_function=OpenAIEmbeddings()\n",
")\n",
2023-11-13 22:26:02 +00:00
"\n",
"# Create retriever\n",
2023-11-14 20:58:22 +00:00
"retriever_multi_vector_img_summary = create_multi_vector_retriever(\n",
" multi_vector_text,\n",
" text_summaries,\n",
" texts,\n",
" table_summaries,\n",
" tables,\n",
" image_summaries,\n",
" image_summaries,\n",
")"
2023-11-13 22:26:02 +00:00
]
},
{
"cell_type": "markdown",
"id": "580a3d55-5025-472d-9c14-cec7a384379f",
"metadata": {},
"source": [
"### Option 3: Multi-modal embeddings"
]
},
{
"cell_type": "code",
"execution_count": 22,
"id": "8dbed5dc-f7a3-4324-9436-1c3ebc24f9fd",
"metadata": {},
"outputs": [],
"source": [
"from langchain_experimental.open_clip import OpenCLIPEmbeddings\n",
"\n",
"# Create chroma w/ multi-modal embeddings\n",
"multimodal_embd = Chroma(\n",
2023-11-14 20:58:22 +00:00
" collection_name=\"multimodal_embd\", embedding_function=OpenCLIPEmbeddings()\n",
2023-11-13 22:26:02 +00:00
")\n",
"\n",
"# Get image URIs\n",
2023-11-14 20:58:22 +00:00
"image_uris = sorted(\n",
" [\n",
" os.path.join(path, image_name)\n",
" for image_name in os.listdir(path)\n",
" if image_name.endswith(\".jpg\")\n",
" ]\n",
")\n",
2023-11-13 22:26:02 +00:00
"\n",
"# Add images and documents\n",
"if image_uris:\n",
" multimodal_embd.add_images(uris=image_uris)\n",
"if texts:\n",
" multimodal_embd.add_texts(texts=texts)\n",
"if tables:\n",
" multimodal_embd.add_texts(texts=tables)\n",
"\n",
2023-11-14 20:58:22 +00:00
"# Make retriever\n",
2023-11-13 22:26:02 +00:00
"retriever_multimodal_embd = multimodal_embd.as_retriever()"
]
},
{
"cell_type": "markdown",
"id": "647abb6c-adf3-4d29-acd2-885c4925fa12",
"metadata": {},
"source": [
"## RAG\n",
"\n",
"### Text Pipeline"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "73440ca0-4330-4c16-9d9d-6f27c249ae58",
"metadata": {},
"outputs": [],
"source": [
"from operator import itemgetter\n",
2023-11-14 22:17:44 +00:00
"\n",
docs[patch], templates[patch]: Import from core (#14575)
Update imports to use core for the low-hanging fruit changes. Ran
following
```bash
git grep -l 'langchain.schema.runnable' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.runnable/langchain_core.runnables/g'
git grep -l 'langchain.schema.output_parser' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.output_parser/langchain_core.output_parsers/g'
git grep -l 'langchain.schema.messages' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.messages/langchain_core.messages/g'
git grep -l 'langchain.schema.chat_histry' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.chat_history/langchain_core.chat_history/g'
git grep -l 'langchain.schema.prompt_template' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.prompt_template/langchain_core.prompts/g'
git grep -l 'from langchain.pydantic_v1' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.pydantic_v1/from langchain_core.pydantic_v1/g'
git grep -l 'from langchain.tools.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.tools\.base/from langchain_core.tools/g'
git grep -l 'from langchain.chat_models.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.chat_models.base/from langchain_core.language_models.chat_models/g'
git grep -l 'from langchain.llms.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.llms\.base\ /from langchain_core.language_models.llms\ /g'
git grep -l 'from langchain.embeddings.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.embeddings\.base/from langchain_core.embeddings/g'
git grep -l 'from langchain.vectorstores.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.vectorstores\.base/from langchain_core.vectorstores/g'
git grep -l 'from langchain.agents.tools' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.agents\.tools/from langchain_core.tools/g'
git grep -l 'from langchain.schema.output' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.output\ /from langchain_core.outputs\ /g'
git grep -l 'from langchain.schema.embeddings' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.embeddings/from langchain_core.embeddings/g'
git grep -l 'from langchain.schema.document' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.document/from langchain_core.documents/g'
git grep -l 'from langchain.schema.agent' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.agent/from langchain_core.agents/g'
git grep -l 'from langchain.schema.prompt ' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.prompt\ /from langchain_core.prompt_values /g'
git grep -l 'from langchain.schema.language_model' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.language_model/from langchain_core.language_models/g'
```
2023-12-12 00:49:10 +00:00
"from langchain_core.runnables import RunnablePassthrough\n",
2023-11-13 22:26:02 +00:00
"\n",
"# Prompt\n",
"template = \"\"\"Answer the question based only on the following context, which can include text and tables:\n",
"{context}\n",
"Question: {question}\n",
"\"\"\"\n",
"rag_prompt_text = ChatPromptTemplate.from_template(template)\n",
"\n",
2023-11-14 20:58:22 +00:00
"\n",
"# Build\n",
2023-11-13 22:26:02 +00:00
"def text_rag_chain(retriever):\n",
2023-11-14 20:58:22 +00:00
" \"\"\"RAG chain\"\"\"\n",
2023-11-13 22:26:02 +00:00
"\n",
" # LLM\n",
" model = ChatOpenAI(temperature=0, model=\"gpt-4\")\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
" # RAG pipeline\n",
" chain = (\n",
" {\"context\": retriever, \"question\": RunnablePassthrough()}\n",
" | rag_prompt_text\n",
" | model\n",
" | StrOutputParser()\n",
" )\n",
"\n",
" return chain"
]
},
{
"cell_type": "markdown",
"id": "14b358ad-42fd-4c6d-b2c0-215dba135707",
"metadata": {},
"source": [
"### Multi-modal Pipeline"
]
},
{
"cell_type": "code",
"execution_count": 24,
"id": "ae89ce84-283e-4634-8169-9ff16f152807",
"metadata": {},
"outputs": [],
"source": [
2023-11-14 20:58:22 +00:00
"import re\n",
2023-11-14 22:17:44 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"from langchain.schema import Document\n",
docs[patch], templates[patch]: Import from core (#14575)
Update imports to use core for the low-hanging fruit changes. Ran
following
```bash
git grep -l 'langchain.schema.runnable' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.runnable/langchain_core.runnables/g'
git grep -l 'langchain.schema.output_parser' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.output_parser/langchain_core.output_parsers/g'
git grep -l 'langchain.schema.messages' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.messages/langchain_core.messages/g'
git grep -l 'langchain.schema.chat_histry' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.chat_history/langchain_core.chat_history/g'
git grep -l 'langchain.schema.prompt_template' {docs,templates,cookbook} | xargs sed -i '' 's/langchain\.schema\.prompt_template/langchain_core.prompts/g'
git grep -l 'from langchain.pydantic_v1' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.pydantic_v1/from langchain_core.pydantic_v1/g'
git grep -l 'from langchain.tools.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.tools\.base/from langchain_core.tools/g'
git grep -l 'from langchain.chat_models.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.chat_models.base/from langchain_core.language_models.chat_models/g'
git grep -l 'from langchain.llms.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.llms\.base\ /from langchain_core.language_models.llms\ /g'
git grep -l 'from langchain.embeddings.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.embeddings\.base/from langchain_core.embeddings/g'
git grep -l 'from langchain.vectorstores.base' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.vectorstores\.base/from langchain_core.vectorstores/g'
git grep -l 'from langchain.agents.tools' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.agents\.tools/from langchain_core.tools/g'
git grep -l 'from langchain.schema.output' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.output\ /from langchain_core.outputs\ /g'
git grep -l 'from langchain.schema.embeddings' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.embeddings/from langchain_core.embeddings/g'
git grep -l 'from langchain.schema.document' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.document/from langchain_core.documents/g'
git grep -l 'from langchain.schema.agent' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.agent/from langchain_core.agents/g'
git grep -l 'from langchain.schema.prompt ' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.prompt\ /from langchain_core.prompt_values /g'
git grep -l 'from langchain.schema.language_model' {docs,templates,cookbook} | xargs sed -i '' 's/from langchain\.schema\.language_model/from langchain_core.language_models/g'
```
2023-12-12 00:49:10 +00:00
"from langchain_core.runnables import RunnableLambda\n",
2023-11-13 22:26:02 +00:00
"\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"def looks_like_base64(sb):\n",
" \"\"\"Check if the string looks like base64.\"\"\"\n",
2023-11-14 20:58:22 +00:00
" return re.match(\"^[A-Za-z0-9+/]+[=]{0,2}$\", sb) is not None\n",
"\n",
2023-11-13 22:26:02 +00:00
"\n",
"def is_image_data(b64data):\n",
" \"\"\"Check if the base64 data is an image by looking at the start of the data.\"\"\"\n",
" image_signatures = {\n",
" b\"\\xFF\\xD8\\xFF\": \"jpg\",\n",
" b\"\\x89\\x50\\x4E\\x47\\x0D\\x0A\\x1A\\x0A\": \"png\",\n",
" b\"\\x47\\x49\\x46\\x38\": \"gif\",\n",
2023-11-14 20:58:22 +00:00
" b\"\\x52\\x49\\x46\\x46\": \"webp\",\n",
2023-11-13 22:26:02 +00:00
" }\n",
" try:\n",
" header = base64.b64decode(b64data)[:8] # Decode and get the first 8 bytes\n",
" for sig, format in image_signatures.items():\n",
" if header.startswith(sig):\n",
" return True\n",
" return False\n",
" except Exception:\n",
" return False\n",
"\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"def split_image_text_types(docs):\n",
" \"\"\"Split base64-encoded images and texts.\"\"\"\n",
" b64_images = []\n",
" texts = []\n",
" for doc in docs:\n",
" # Check if the document is of type Document and extract page_content if so\n",
" if isinstance(doc, Document):\n",
" doc = doc.page_content\n",
" if looks_like_base64(doc) and is_image_data(doc):\n",
" b64_images.append(doc)\n",
" else:\n",
" texts.append(doc)\n",
" return {\"images\": b64_images, \"texts\": texts}\n",
"\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"def img_prompt_func(data_dict):\n",
" # Joining the context texts into a single string\n",
" formatted_texts = \"\\n\".join(data_dict[\"context\"][\"texts\"])\n",
" messages = []\n",
"\n",
" # Adding image(s) to the messages if present\n",
" if data_dict[\"context\"][\"images\"]:\n",
" image_message = {\n",
" \"type\": \"image_url\",\n",
" \"image_url\": {\n",
" \"url\": f\"data:image/jpeg;base64,{data_dict['context']['images'][0]}\"\n",
2023-11-14 20:58:22 +00:00
" },\n",
2023-11-13 22:26:02 +00:00
" }\n",
" messages.append(image_message)\n",
"\n",
" # Adding the text message for analysis\n",
" text_message = {\n",
" \"type\": \"text\",\n",
" \"text\": (\n",
" \"Answer the question based only on the provided context, which can include text, tables, and image(s). \"\n",
" \"If an image is provided, analyze it carefully to help answer the question.\\n\"\n",
" f\"User-provided question / keywords: {data_dict['question']}\\n\\n\"\n",
" \"Text and / or tables:\\n\"\n",
" f\"{formatted_texts}\"\n",
2023-11-14 20:58:22 +00:00
" ),\n",
2023-11-13 22:26:02 +00:00
" }\n",
" messages.append(text_message)\n",
" return [HumanMessage(content=messages)]\n",
"\n",
2023-11-14 20:58:22 +00:00
"\n",
2023-11-13 22:26:02 +00:00
"def multi_modal_rag_chain(retriever):\n",
2023-11-14 20:58:22 +00:00
" \"\"\"Multi-modal RAG chain\"\"\"\n",
2023-11-13 22:26:02 +00:00
"\n",
" # Multi-modal LLM\n",
2023-11-14 20:58:22 +00:00
" model = ChatOpenAI(temperature=0, model=\"gpt-4-vision-preview\", max_tokens=1024)\n",
"\n",
2023-11-13 22:26:02 +00:00
" # RAG pipeline\n",
" chain = (\n",
2023-11-14 20:58:22 +00:00
" {\n",
" \"context\": retriever | RunnableLambda(split_image_text_types),\n",
" \"question\": RunnablePassthrough(),\n",
" }\n",
2023-11-13 22:26:02 +00:00
" | RunnableLambda(img_prompt_func)\n",
" | model\n",
" | StrOutputParser()\n",
" )\n",
"\n",
" return chain"
]
},
{
"cell_type": "markdown",
"id": "5e8b0e26-bb7e-420a-a7bd-8512b7eef92f",
"metadata": {},
"source": [
"### Build RAG Pipelines"
]
},
{
"cell_type": "code",
"execution_count": 25,
"id": "4f1ec8a9-f0fe-4f08-928f-23504803897c",
"metadata": {},
"outputs": [],
"source": [
"# RAG chains\n",
2023-11-14 20:58:22 +00:00
"chain_baseline = text_rag_chain(retriever_baseline)\n",
"chain_mv_text = text_rag_chain(retriever_multi_vector_img_summary)\n",
2023-11-13 22:26:02 +00:00
"\n",
"# Multi-modal RAG chains\n",
2023-11-14 20:58:22 +00:00
"chain_multimodal_mv_img = multi_modal_rag_chain(retriever_multi_vector_img)\n",
"chain_multimodal_embd = multi_modal_rag_chain(retriever_multimodal_embd)"
2023-11-13 22:26:02 +00:00
]
},
{
"cell_type": "markdown",
"id": "448d943c-a1b1-4300-9197-891a03232ee4",
"metadata": {},
"source": [
"## Eval set"
]
},
{
"cell_type": "code",
"execution_count": 34,
"id": "9aabf72f-26be-437f-9372-b06dc2509235",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Question</th>\n",
" <th>Answer</th>\n",
" <th>Source</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>What percentage of CPI is dedicated to Housing?</td>\n",
" <td>Housing occupies 42% of CPI.</td>\n",
" <td>Figure 1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>Medical Care and Transportation account for wh...</td>\n",
" <td>Transportation accounts for 18% of CPI. Medica...</td>\n",
" <td>Figure 1</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>Based on the CPI Owners' Equivalent Rent and t...</td>\n",
" <td>The FHFA Purchase Only Price Index appears to ...</td>\n",
" <td>Figure 2</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Question \\\n",
"0 What percentage of CPI is dedicated to Housing? \n",
"1 Medical Care and Transportation account for wh... \n",
"2 Based on the CPI Owners' Equivalent Rent and t... \n",
"\n",
" Answer Source \n",
"0 Housing occupies 42% of CPI. Figure 1 \n",
"1 Transportation accounts for 18% of CPI. Medica... Figure 1 \n",
"2 The FHFA Purchase Only Price Index appears to ... Figure 2 "
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Read\n",
"import pandas as pd\n",
2023-11-14 20:58:22 +00:00
"\n",
"eval_set = pd.read_csv(path + \"cpi_eval.csv\")\n",
2023-11-13 22:26:02 +00:00
"eval_set.head(3)"
]
},
{
"cell_type": "code",
"execution_count": 35,
"id": "7fdeb77a-e185-47d2-a93f-822f1fc810a2",
"metadata": {},
"outputs": [],
"source": [
"from langsmith import Client\n",
"\n",
"# Dataset\n",
"client = Client()\n",
"dataset_name = f\"CPI Eval {str(uuid.uuid4())}\"\n",
"dataset = client.create_dataset(dataset_name=dataset_name)\n",
"\n",
"# Populate dataset\n",
"for _, row in eval_set.iterrows():\n",
" # Get Q, A\n",
2023-11-14 20:58:22 +00:00
" q = row[\"Question\"]\n",
" a = row[\"Answer\"]\n",
2023-11-13 22:26:02 +00:00
" # Use the values in your function\n",
2023-11-14 20:58:22 +00:00
" client.create_example(\n",
" inputs={\"question\": q}, outputs={\"answer\": a}, dataset_id=dataset.id\n",
" )"
2023-11-13 22:26:02 +00:00
]
},
{
"cell_type": "code",
"execution_count": 36,
"id": "3c4faf4b-f29f-4a42-9cf2-bfbb5158ab59",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"View the evaluation results for project 'CPI Eval 9648e7fe-5ae2-469f-8701-33c63212d126-baseline' at:\n",
"https://smith.langchain.com/o/1fa8b1f4-fcb9-4072-9aa9-983e35ad61b8/projects/p/533846be-d907-4d9c-82db-ce2f1a18fdbf?eval=true\n",
"\n",
"View all tests for Dataset CPI Eval 9648e7fe-5ae2-469f-8701-33c63212d126 at:\n",
"https://smith.langchain.com/datasets/d1762232-5e01-40e7-9978-63002a4c95a3\n",
"[------------------------------------------------->] 4/4View the evaluation results for project 'CPI Eval 9648e7fe-5ae2-469f-8701-33c63212d126-mv_text' at:\n",
"https://smith.langchain.com/o/1fa8b1f4-fcb9-4072-9aa9-983e35ad61b8/projects/p/f5caeede-6f8e-46f7-b4f2-9f23daa31eda?eval=true\n",
"\n",
"View all tests for Dataset CPI Eval 9648e7fe-5ae2-469f-8701-33c63212d126 at:\n",
"https://smith.langchain.com/datasets/d1762232-5e01-40e7-9978-63002a4c95a3\n",
"[------------------------------------------------->] 4/4View the evaluation results for project 'CPI Eval 9648e7fe-5ae2-469f-8701-33c63212d126-mv_img' at:\n",
"https://smith.langchain.com/o/1fa8b1f4-fcb9-4072-9aa9-983e35ad61b8/projects/p/48cf1002-7ae2-451d-a9b1-5bd8088f6a69?eval=true\n",
"\n",
"View all tests for Dataset CPI Eval 9648e7fe-5ae2-469f-8701-33c63212d126 at:\n",
"https://smith.langchain.com/datasets/d1762232-5e01-40e7-9978-63002a4c95a3\n",
"[------------------------------------------------->] 4/4View the evaluation results for project 'CPI Eval 9648e7fe-5ae2-469f-8701-33c63212d126-mm_embd' at:\n",
"https://smith.langchain.com/o/1fa8b1f4-fcb9-4072-9aa9-983e35ad61b8/projects/p/aaa1c2e3-79b0-43e0-b5d5-8e3d00a51d50?eval=true\n",
"\n",
"View all tests for Dataset CPI Eval 9648e7fe-5ae2-469f-8701-33c63212d126 at:\n",
"https://smith.langchain.com/datasets/d1762232-5e01-40e7-9978-63002a4c95a3\n",
"[------------------------------------------------->] 4/4"
]
}
],
"source": [
"from langchain.smith import RunEvalConfig\n",
"\n",
"eval_config = RunEvalConfig(\n",
" evaluators=[\"qa\"],\n",
")\n",
"\n",
2023-11-14 20:58:22 +00:00
"\n",
"def run_eval(chain, run_name, dataset_name):\n",
2023-11-13 22:26:02 +00:00
" _ = client.run_on_dataset(\n",
" dataset_name=dataset_name,\n",
2023-11-14 20:58:22 +00:00
" llm_or_chain_factory=lambda: (lambda x: x[\"question\"] + suffix_for_images)\n",
" | chain,\n",
2023-11-13 22:26:02 +00:00
" evaluation=eval_config,\n",
" project_name=run_name,\n",
" )\n",
"\n",
2023-11-14 20:58:22 +00:00
"\n",
"for chain, run in zip(\n",
" [chain_baseline, chain_mv_text, chain_multimodal_mv_img, chain_multimodal_embd],\n",
" [\"baseline\", \"mv_text\", \"mv_img\", \"mm_embd\"],\n",
"):\n",
" run_eval(chain, dataset_name + \"-\" + run, dataset_name)"
2023-11-13 22:26:02 +00:00
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.16"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
