mirror of
https://github.com/hwchase17/langchain.git
synced 2026-04-21 19:27:58 +00:00
Compare commits
1 Commits
v0.0.286
...
wfh/defaul
| Author | SHA1 | Date | |
|---|---|---|---|
|
840b00ad7c |
@@ -12,7 +12,7 @@ Output parsers are classes that help structure language model responses. There a
|
||||
|
||||
And then one optional one:
|
||||
|
||||
- "Parse with prompt": A method which takes in a string (assumed to be the response from a language model) and a prompt (assumed to be the prompt that generated such a response) and parses it into some structure. The prompt is largely provided in the event the OutputParser wants to retry or fix the output in some way, and needs information from the prompt to do so.
|
||||
- "Parse with prompt": A method which takes in a string (assumed to be the response from a language model) and a prompt (assumed to the prompt that generated such a response) and parses it into some structure. The prompt is largely provided in the event the OutputParser wants to retry or fix the output in some way, and needs information from the prompt to do so.
|
||||
|
||||
## Get started
|
||||
|
||||
|
||||
@@ -1076,10 +1076,6 @@
|
||||
"source": "/docs/modules/agents/tools/integrations/zapier",
|
||||
"destination": "/docs/integrations/tools/zapier"
|
||||
},
|
||||
{
|
||||
"source": "/docs/integrations/tools/sqlite",
|
||||
"destination": "/docs/use_cases/sql/sqlite"
|
||||
},
|
||||
{
|
||||
"source": "/en/latest/modules/callbacks/filecallbackhandler.html",
|
||||
"destination": "/docs/modules/callbacks/how_to/filecallbackhandler"
|
||||
@@ -2220,10 +2216,6 @@
|
||||
"source": "/docs/modules/data_connection/text_embedding/integrations/tensorflowhub",
|
||||
"destination": "/docs/integrations/text_embedding/tensorflowhub"
|
||||
},
|
||||
{
|
||||
"source": "/docs/integrations/text_embedding/Awa",
|
||||
"destination": "/docs/integrations/text_embedding/awadb"
|
||||
},
|
||||
{
|
||||
"source": "/en/latest/modules/indexes/vectorstores/examples/analyticdb.html",
|
||||
"destination": "/docs/integrations/vectorstores/analyticdb"
|
||||
|
||||
1831
docs/extras/expression_language/cookbook.ipynb
Normal file
1831
docs/extras/expression_language/cookbook.ipynb
Normal file
File diff suppressed because it is too large
Load Diff
@@ -1,203 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e89f490d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Agents\n",
|
||||
"\n",
|
||||
"You can pass a Runnable into an agent."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "af4381de",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.agents import XMLAgent, tool, AgentExecutor\n",
|
||||
"from langchain.chat_models import ChatAnthropic"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "24cc8134",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = ChatAnthropic(model=\"claude-2\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "67c0b0e4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"@tool\n",
|
||||
"def search(query: str) -> str:\n",
|
||||
" \"\"\"Search things about current events.\"\"\"\n",
|
||||
" return \"32 degrees\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "7203b101",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"tool_list = [search]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "b68e756d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Get prompt to use\n",
|
||||
"prompt = XMLAgent.get_default_prompt()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "61ab3e9a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Logic for going from intermediate steps to a string to pass into model\n",
|
||||
"# This is pretty tied to the prompt\n",
|
||||
"def convert_intermediate_steps(intermediate_steps):\n",
|
||||
" log = \"\"\n",
|
||||
" for action, observation in intermediate_steps:\n",
|
||||
" log += (\n",
|
||||
" f\"<tool>{action.tool}</tool><tool_input>{action.tool_input}\"\n",
|
||||
" f\"</tool_input><observation>{observation}</observation>\"\n",
|
||||
" )\n",
|
||||
" return log\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"# Logic for converting tools to string to go in prompt\n",
|
||||
"def convert_tools(tools):\n",
|
||||
" return \"\\n\".join([f\"{tool.name}: {tool.description}\" for tool in tools])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "260f5988",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Building an agent from a runnable usually involves a few things:\n",
|
||||
"\n",
|
||||
"1. Data processing for the intermediate steps. These need to represented in a way that the language model can recognize them. This should be pretty tightly coupled to the instructions in the prompt\n",
|
||||
"\n",
|
||||
"2. The prompt itself\n",
|
||||
"\n",
|
||||
"3. The model, complete with stop tokens if needed\n",
|
||||
"\n",
|
||||
"4. The output parser - should be in sync with how the prompt specifies things to be formatted."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "e92f1d6f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent = (\n",
|
||||
" {\n",
|
||||
" \"question\": lambda x: x[\"question\"],\n",
|
||||
" \"intermediate_steps\": lambda x: convert_intermediate_steps(x[\"intermediate_steps\"])\n",
|
||||
" }\n",
|
||||
" | prompt.partial(tools=convert_tools(tool_list))\n",
|
||||
" | model.bind(stop=[\"</tool_input>\", \"</final_answer>\"])\n",
|
||||
" | XMLAgent.get_default_output_parser()\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "6ce6ec7a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"agent_executor = AgentExecutor(agent=agent, tools=tool_list, verbose=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "fb5cb2e3",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n",
|
||||
"\n",
|
||||
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
|
||||
"\u001b[32;1m\u001b[1;3m <tool>search</tool>\n",
|
||||
"<tool_input>weather in new york\u001b[0m\u001b[36;1m\u001b[1;3m32 degrees\u001b[0m\u001b[32;1m\u001b[1;3m\n",
|
||||
"\n",
|
||||
"<final_answer>The weather in New York is 32 degrees\u001b[0m\n",
|
||||
"\n",
|
||||
"\u001b[1m> Finished chain.\u001b[0m\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'question': 'whats the weather in New york?',\n",
|
||||
" 'output': 'The weather in New York is 32 degrees'}"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"agent_executor.invoke({\"question\": \"whats the weather in New york?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bce86dd8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"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": "3.10.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,119 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f09fd305",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Code writing\n",
|
||||
"\n",
|
||||
"Example of how to use LCEL to write Python code."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "bd7c259a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.prompts import ChatPromptTemplate, SystemMessagePromptTemplate, HumanMessagePromptTemplate\n",
|
||||
"from langchain.schema.output_parser import StrOutputParser\n",
|
||||
"from langchain.utilities import PythonREPL"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "73795d2d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"Write some python code to solve the user's problem. \n",
|
||||
"\n",
|
||||
"Return only python code in Markdown format, e.g.:\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"....\n",
|
||||
"```\"\"\"\n",
|
||||
"prompt = ChatPromptTemplate.from_messages(\n",
|
||||
" [(\"system\", template), (\"human\", \"{input}\")]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"model = ChatOpenAI()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "42859e8a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def _sanitize_output(text: str):\n",
|
||||
" _, after = text.split(\"```python\")\n",
|
||||
" return after.split(\"```\")[0]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "5ded1a86",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = prompt | model | StrOutputParser() | _sanitize_output | PythonREPL().run"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "208c2b75",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Python REPL can execute arbitrary code. Use with caution.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'4\\n'"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"input\": \"whats 2 plus 2\"})"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,11 +0,0 @@
|
||||
---
|
||||
sidebar_position: 2
|
||||
---
|
||||
|
||||
# Cookbook
|
||||
|
||||
import DocCardList from "@theme/DocCardList";
|
||||
|
||||
Example code for accomplishing common tasks with the LangChain Expression Language (LCEL). These examples show how to compose different Runnable (the core LCEL interface) components to achieve various tasks. If you're just getting acquainted with LCEL, the [Prompt + LLM](/docs/expression_language/cookbook/prompt_llm_parser) page is a good place to start.
|
||||
|
||||
<DocCardList />
|
||||
@@ -1,180 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5062941a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Adding memory\n",
|
||||
"\n",
|
||||
"This shows how to add memory to an arbitrary chain. Right now, you can use the memory classes but need to hook it up manually"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "7998efd8",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.memory import ConversationBufferMemory\n",
|
||||
"from langchain.schema.runnable import RunnableMap\n",
|
||||
"from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder\n",
|
||||
"\n",
|
||||
"model = ChatOpenAI()\n",
|
||||
"prompt = ChatPromptTemplate.from_messages([\n",
|
||||
" (\"system\", \"You are a helpful chatbot\"),\n",
|
||||
" MessagesPlaceholder(variable_name=\"history\"),\n",
|
||||
" (\"human\", \"{input}\")\n",
|
||||
"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "fa0087f3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"memory = ConversationBufferMemory(return_messages=True)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "06b531ae",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'history': []}"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"memory.load_memory_variables({})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "d9437af6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = RunnableMap({\n",
|
||||
" \"input\": lambda x: x[\"input\"],\n",
|
||||
" \"memory\": memory.load_memory_variables\n",
|
||||
"}) | {\n",
|
||||
" \"input\": lambda x: x[\"input\"],\n",
|
||||
" \"history\": lambda x: x[\"memory\"][\"history\"]\n",
|
||||
"} | prompt | model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "bed1e260",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"inputs = {\"input\": \"hi im bob\"}\n",
|
||||
"response = chain.invoke(inputs)\n",
|
||||
"response"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "890475b4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"memory.save_context(inputs, {\"output\": response.content})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "e8fcb77f",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'history': [HumanMessage(content='hi im bob', additional_kwargs={}, example=False),\n",
|
||||
" AIMessage(content='Hello Bob! How can I assist you today?', additional_kwargs={}, example=False)]}"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"memory.load_memory_variables({})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "d837d5c3",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Your name is Bob.', additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"inputs = {\"input\": \"whats my name\"}\n",
|
||||
"response = chain.invoke(inputs)\n",
|
||||
"response"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,133 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4927a727-b4c8-453c-8c83-bd87b4fcac14",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Adding moderation\n",
|
||||
"\n",
|
||||
"This shows how to add in moderation (or other safeguards) around your LLM application."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"id": "4f5f6449-940a-4f5c-97c0-39b71c3e2a68",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chains import OpenAIModerationChain\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.prompts import ChatPromptTemplate"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "fcb8312b-7e7a-424f-a3ec-76738c9a9d21",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"moderate = OpenAIModerationChain()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"id": "b24b9148-f6b0-4091-8ea8-d3fb281bd950",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"model = OpenAI()\n",
|
||||
"prompt = ChatPromptTemplate.from_messages([\n",
|
||||
" (\"system\", \"repeat after me: {input}\")\n",
|
||||
"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"id": "1c8ed87c-9ca6-4559-bf60-d40e94a0af08",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = prompt | model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"id": "5256b9bd-381a-42b0-bfa8-7e6d18f853cb",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'\\n\\nYou are stupid.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 23,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"input\": \"you are stupid\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"id": "fe6e3b33-dc9a-49d5-b194-ba750c58a628",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"moderated_chain = chain | moderate"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"id": "d8ba0cbd-c739-4d23-be9f-6ae092bd5ffb",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'input': '\\n\\nYou are stupid',\n",
|
||||
" 'output': \"Text was found that violates OpenAI's content policy.\"}"
|
||||
]
|
||||
},
|
||||
"execution_count": 25,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"moderated_chain.invoke({\"input\": \"you are stupid\"})"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,240 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "877102d1-02ea-4fa3-8ec7-a08e242b95b3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_position: 2\n",
|
||||
"title: Multiple chains\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0f2bf8d3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Runnables can easily be used to string together multiple Chains"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "d65d4e9e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'El país donde se encuentra la ciudad de Honolulu, donde nació Barack Obama, el 44º Presidente de los Estados Unidos, es Estados Unidos. Honolulu se encuentra en la isla de Oahu, en el estado de Hawái.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from operator import itemgetter\n",
|
||||
"\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.prompts import ChatPromptTemplate\n",
|
||||
"from langchain.schema import StrOutputParser\n",
|
||||
"\n",
|
||||
"prompt1 = ChatPromptTemplate.from_template(\"what is the city {person} is from?\")\n",
|
||||
"prompt2 = ChatPromptTemplate.from_template(\"what country is the city {city} in? respond in {language}\")\n",
|
||||
"\n",
|
||||
"model = ChatOpenAI()\n",
|
||||
"\n",
|
||||
"chain1 = prompt1 | model | StrOutputParser()\n",
|
||||
"\n",
|
||||
"chain2 = {\"city\": chain1, \"language\": itemgetter(\"language\")} | prompt2 | model | StrOutputParser()\n",
|
||||
"\n",
|
||||
"chain2.invoke({\"person\": \"obama\", \"language\": \"spanish\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "878f8176",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n",
|
||||
"\n",
|
||||
"prompt1 = ChatPromptTemplate.from_template(\"generate a {attribute} color. Return the name of the color and nothing else:\")\n",
|
||||
"prompt2 = ChatPromptTemplate.from_template(\"what is a fruit of color: {color}. Return the name of the fruit and nothing else:\")\n",
|
||||
"prompt3 = ChatPromptTemplate.from_template(\"what is a country with a flag that has the color: {color}. Return the name of the country and nothing else:\")\n",
|
||||
"prompt4 = ChatPromptTemplate.from_template(\"What is the color of {fruit} and the flag of {country}?\")\n",
|
||||
"\n",
|
||||
"model_parser = model | StrOutputParser()\n",
|
||||
"\n",
|
||||
"color_generator = {\"attribute\": RunnablePassthrough()} | prompt1 | {\"color\": model_parser}\n",
|
||||
"color_to_fruit = prompt2 | model_parser\n",
|
||||
"color_to_country = prompt3 | model_parser\n",
|
||||
"question_generator = color_generator | {\"fruit\": color_to_fruit, \"country\": color_to_country} | prompt4"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "d621a870",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"ChatPromptValue(messages=[HumanMessage(content='What is the color of strawberry and the flag of China?', additional_kwargs={}, example=False)])"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"question_generator.invoke({\"warm\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "b4a9812b-bead-4fd9-ae27-0b8be57e5dc1",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='The color of an apple is typically red or green. The flag of China is predominantly red with a large yellow star in the upper left corner and four smaller yellow stars surrounding it.', additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"prompt = question_generator.invoke({\"warm\"})\n",
|
||||
"model.invoke(prompt)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6d75a313-f1c8-4e94-9a17-24e0bf4a2bdc",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Branching and Merging\n",
|
||||
"\n",
|
||||
"You may want the output of one component to be processed by 2 or more other components. [RunnableMaps](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.base.RunnableMap.html) let you split or fork the chain so multiple components can process the input in parallel. Later, other components can join or merge the results to synthesize a final response. This type of chain creates a computation graph that looks like the following:\n",
|
||||
"\n",
|
||||
"```text\n",
|
||||
" Input\n",
|
||||
" / \\\n",
|
||||
" / \\\n",
|
||||
" Branch1 Branch2\n",
|
||||
" \\ /\n",
|
||||
" \\ /\n",
|
||||
" Combine\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "247fa0bd-4596-4063-8cb3-1d7fc119d982",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"planner = (\n",
|
||||
" ChatPromptTemplate.from_template(\n",
|
||||
" \"Generate an argument about: {input}\"\n",
|
||||
" )\n",
|
||||
" | ChatOpenAI()\n",
|
||||
" | StrOutputParser()\n",
|
||||
" | {\"base_response\": RunnablePassthrough()}\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"arguments_for = (\n",
|
||||
" ChatPromptTemplate.from_template(\n",
|
||||
" \"List the pros or positive aspects of {base_response}\"\n",
|
||||
" )\n",
|
||||
" | ChatOpenAI()\n",
|
||||
" | StrOutputParser()\n",
|
||||
")\n",
|
||||
"arguments_against = (\n",
|
||||
" ChatPromptTemplate.from_template(\n",
|
||||
" \"List the cons or negative aspects of {base_response}\"\n",
|
||||
" )\n",
|
||||
" | ChatOpenAI()\n",
|
||||
" | StrOutputParser()\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"final_responder = (\n",
|
||||
" ChatPromptTemplate.from_messages(\n",
|
||||
" [\n",
|
||||
" (\"ai\", \"{original_response}\"),\n",
|
||||
" (\"human\", \"Pros:\\n{results_1}\\n\\nCons:\\n{results_2}\"),\n",
|
||||
" (\"system\", \"Generate a final response given the critique\"),\n",
|
||||
" ]\n",
|
||||
" )\n",
|
||||
" | ChatOpenAI()\n",
|
||||
" | StrOutputParser()\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"chain = (\n",
|
||||
" planner \n",
|
||||
" | {\n",
|
||||
" \"results_1\": arguments_for,\n",
|
||||
" \"results_2\": arguments_against,\n",
|
||||
" \"original_response\": itemgetter(\"base_response\"),\n",
|
||||
" }\n",
|
||||
" | final_responder\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "2564f310-0674-4bb1-9c4e-d7848ca73511",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'While Scrum has its potential cons and challenges, many organizations have successfully embraced and implemented this project management framework to great effect. The cons mentioned above can be mitigated or overcome with proper training, support, and a commitment to continuous improvement. It is also important to note that not all cons may be applicable to every organization or project.\\n\\nFor example, while Scrum may be complex initially, with proper training and guidance, teams can quickly grasp the concepts and practices. The lack of predictability can be mitigated by implementing techniques such as velocity tracking and release planning. The limited documentation can be addressed by maintaining a balance between lightweight documentation and clear communication among team members. The dependency on team collaboration can be improved through effective communication channels and regular team-building activities.\\n\\nScrum can be scaled and adapted to larger projects by using frameworks like Scrum of Scrums or LeSS (Large Scale Scrum). Concerns about speed versus quality can be addressed by incorporating quality assurance practices, such as continuous integration and automated testing, into the Scrum process. Scope creep can be managed by having a well-defined and prioritized product backlog, and a strong product owner can be developed through training and mentorship.\\n\\nResistance to change can be overcome by providing proper education and communication to stakeholders and involving them in the decision-making process. Ultimately, the cons of Scrum can be seen as opportunities for growth and improvement, and with the right mindset and support, they can be effectively managed.\\n\\nIn conclusion, while Scrum may have its challenges and potential cons, the benefits and advantages it offers in terms of collaboration, flexibility, adaptability, transparency, and customer satisfaction make it a widely adopted and successful project management framework. With proper implementation and continuous improvement, organizations can leverage Scrum to drive innovation, efficiency, and project success.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"input\": \"scrum\"})"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "poetry-venv",
|
||||
"language": "python",
|
||||
"name": "poetry-venv"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,431 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "abf7263d-3a62-4016-b5d5-b157f92f2070",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_position: 0\n",
|
||||
"title: Prompt + LLM\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9a434f2b-9405-468c-9dfd-254d456b57a6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The most common and valuable composition is taking:\n",
|
||||
"\n",
|
||||
"``PromptTemplate`` / ``ChatPromptTemplate`` -> ``LLM`` / ``ChatModel`` -> ``OutputParser``\n",
|
||||
"\n",
|
||||
"Almost any other chains you build will use this building block."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "93aa2c87",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## PromptTemplate + LLM\n",
|
||||
"\n",
|
||||
"The simplest composition is just combing a prompt and model to create a chain that takes user input, adds it to a prompt, passes it to a model, and returns the raw model input.\n",
|
||||
"\n",
|
||||
"Note, you can mix and match PromptTemplate/ChatPromptTemplates and LLMs/ChatModels as you like here."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "466b65b3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts import ChatPromptTemplate\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"\n",
|
||||
"prompt = ChatPromptTemplate.from_template(\"tell me a joke about {foo}\")\n",
|
||||
"model = ChatOpenAI()\n",
|
||||
"chain = prompt | model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "e3d0a6cd",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content=\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\", additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"foo\": \"bears\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7eb9ef50",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Often times we want to attach kwargs that'll be passed to each model call. Here's a few examples of that:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0b1d8f88",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Attaching Stop Sequences"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "562a06bf",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = prompt | model.bind(stop=[\"\\n\"])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "43f5d04c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Why did the bear never wear shoes?', additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"foo\": \"bears\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f3eaf88a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Attaching Function Call information"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "f94b71b2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"functions = [\n",
|
||||
" {\n",
|
||||
" \"name\": \"joke\",\n",
|
||||
" \"description\": \"A joke\",\n",
|
||||
" \"parameters\": {\n",
|
||||
" \"type\": \"object\",\n",
|
||||
" \"properties\": {\n",
|
||||
" \"setup\": {\n",
|
||||
" \"type\": \"string\",\n",
|
||||
" \"description\": \"The setup for the joke\"\n",
|
||||
" },\n",
|
||||
" \"punchline\": {\n",
|
||||
" \"type\": \"string\",\n",
|
||||
" \"description\": \"The punchline for the joke\"\n",
|
||||
" }\n",
|
||||
" },\n",
|
||||
" \"required\": [\"setup\", \"punchline\"]\n",
|
||||
" }\n",
|
||||
" }\n",
|
||||
" ]\n",
|
||||
"chain = prompt | model.bind(function_call= {\"name\": \"joke\"}, functions= functions)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "decf7710",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='', additional_kwargs={'function_call': {'name': 'joke', 'arguments': '{\\n \"setup\": \"Why don\\'t bears wear shoes?\",\\n \"punchline\": \"Because they have bear feet!\"\\n}'}}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"foo\": \"bears\"}, config={})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9098c5ed",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## PromptTemplate + LLM + OutputParser\n",
|
||||
"\n",
|
||||
"We can also add in an output parser to easily trasform the raw LLM/ChatModel output into a more workable format"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "cc194c78",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.schema.output_parser import StrOutputParser\n",
|
||||
"\n",
|
||||
"chain = prompt | model | StrOutputParser()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "77acf448",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Notice that this now returns a string - a much more workable format for downstream tasks"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "e3d69a18",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Why don't bears wear shoes?\\n\\nBecause they have bear feet!\""
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"foo\": \"bears\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c01864e5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Functions Output Parser\n",
|
||||
"\n",
|
||||
"When you specify the function to return, you may just want to parse that directly"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "ad0dd88e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.output_parsers.openai_functions import JsonOutputFunctionsParser\n",
|
||||
"\n",
|
||||
"chain = (\n",
|
||||
" prompt \n",
|
||||
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
|
||||
" | JsonOutputFunctionsParser()\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "1e7aa8eb",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'setup': \"Why don't bears like fast food?\",\n",
|
||||
" 'punchline': \"Because they can't catch it!\"}"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"foo\": \"bears\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "d4aa1a01",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.output_parsers.openai_functions import JsonKeyOutputFunctionsParser\n",
|
||||
"\n",
|
||||
"chain = (\n",
|
||||
" prompt \n",
|
||||
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
|
||||
" | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "8b6df9ba",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Why don't bears wear shoes?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"foo\": \"bears\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "023fbccb-ef7d-489e-a9ba-f98e17283d51",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Simplifying input\n",
|
||||
"\n",
|
||||
"To make invocation even simpler, we can add a `RunnableMap` to take care of creating the prompt input dict for us:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "9601c0f0-71f9-4bd4-a672-7bd04084b018",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.schema.runnable import RunnableMap, RunnablePassthrough\n",
|
||||
"\n",
|
||||
"map_ = RunnableMap({\"foo\": RunnablePassthrough()})\n",
|
||||
"chain = (\n",
|
||||
" map_ \n",
|
||||
" | prompt\n",
|
||||
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
|
||||
" | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "7ec4f154-fda5-4847-9220-41aa902fdc33",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Why don't bears wear shoes?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke(\"bears\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "def00bfe-0f83-4805-8c8f-8a53f99fa8ea",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Since we're composing our map with another Runnable, we can even use some syntactic sugar and just use a dict:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"id": "7bf3846a-02ee-41a3-ba1b-a708827d4f3a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = (\n",
|
||||
" {\"foo\": RunnablePassthrough()} \n",
|
||||
" | prompt\n",
|
||||
" | model.bind(function_call= {\"name\": \"joke\"}, functions= functions) \n",
|
||||
" | JsonKeyOutputFunctionsParser(key_name=\"setup\")\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"id": "e566d6a1-538d-4cb5-a210-a63e082e4c74",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"\"Why don't bears like fast food?\""
|
||||
]
|
||||
},
|
||||
"execution_count": 22,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke(\"bears\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,461 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "abe47592-909c-4844-bf44-9e55c2fb4bfa",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_position: 1\n",
|
||||
"title: RAG\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "91c5ef3d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's look at adding in a retrieval step to a prompt and LLM, which adds up to a \"retrieval-augmented generation\" chain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "7f25d9e9-d192-42e9-af50-5660a4bfb0d9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install langchain openai faiss-cpu"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "33be32af",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from operator import itemgetter\n",
|
||||
"\n",
|
||||
"from langchain.prompts import ChatPromptTemplate\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.embeddings import OpenAIEmbeddings\n",
|
||||
"from langchain.schema.output_parser import StrOutputParser\n",
|
||||
"from langchain.schema.runnable import RunnablePassthrough\n",
|
||||
"from langchain.vectorstores import FAISS"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "bfc47ec1",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"vectorstore = FAISS.from_texts([\"harrison worked at kensho\"], embedding=OpenAIEmbeddings())\n",
|
||||
"retriever = vectorstore.as_retriever()\n",
|
||||
"\n",
|
||||
"template = \"\"\"Answer the question based only on the following context:\n",
|
||||
"{context}\n",
|
||||
"\n",
|
||||
"Question: {question}\n",
|
||||
"\"\"\"\n",
|
||||
"prompt = ChatPromptTemplate.from_template(template)\n",
|
||||
"\n",
|
||||
"model = ChatOpenAI()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "eae31755",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = (\n",
|
||||
" {\"context\": retriever, \"question\": RunnablePassthrough()} \n",
|
||||
" | prompt \n",
|
||||
" | model \n",
|
||||
" | StrOutputParser()\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "f3040b0c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Harrison worked at Kensho.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke(\"where did harrison work?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "e1d20c7c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"Answer the question based only on the following context:\n",
|
||||
"{context}\n",
|
||||
"\n",
|
||||
"Question: {question}\n",
|
||||
"\n",
|
||||
"Answer in the following language: {language}\n",
|
||||
"\"\"\"\n",
|
||||
"prompt = ChatPromptTemplate.from_template(template)\n",
|
||||
"\n",
|
||||
"chain = {\n",
|
||||
" \"context\": itemgetter(\"question\") | retriever, \n",
|
||||
" \"question\": itemgetter(\"question\"), \n",
|
||||
" \"language\": itemgetter(\"language\")\n",
|
||||
"} | prompt | model | StrOutputParser()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "7ee8b2d4",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Harrison ha lavorato a Kensho.'"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"question\": \"where did harrison work\", \"language\": \"italian\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f007669c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Conversational Retrieval Chain\n",
|
||||
"\n",
|
||||
"We can easily add in conversation history. This primarily means adding in chat_message_history"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "3f30c348",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.schema.runnable import RunnableMap\n",
|
||||
"from langchain.schema import format_document"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "64ab1dbf",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts.prompt import PromptTemplate\n",
|
||||
"\n",
|
||||
"_template = \"\"\"Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question, in its original language.\n",
|
||||
"\n",
|
||||
"Chat History:\n",
|
||||
"{chat_history}\n",
|
||||
"Follow Up Input: {question}\n",
|
||||
"Standalone question:\"\"\"\n",
|
||||
"CONDENSE_QUESTION_PROMPT = PromptTemplate.from_template(_template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "7d628c97",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"Answer the question based only on the following context:\n",
|
||||
"{context}\n",
|
||||
"\n",
|
||||
"Question: {question}\n",
|
||||
"\"\"\"\n",
|
||||
"ANSWER_PROMPT = ChatPromptTemplate.from_template(template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "f60a5d0f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"DEFAULT_DOCUMENT_PROMPT = PromptTemplate.from_template(template=\"{page_content}\")\n",
|
||||
"def _combine_documents(docs, document_prompt = DEFAULT_DOCUMENT_PROMPT, document_separator=\"\\n\\n\"):\n",
|
||||
" doc_strings = [format_document(doc, document_prompt) for doc in docs]\n",
|
||||
" return document_separator.join(doc_strings)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "7d007db6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from typing import Tuple, List\n",
|
||||
"def _format_chat_history(chat_history: List[Tuple]) -> str:\n",
|
||||
" buffer = \"\"\n",
|
||||
" for dialogue_turn in chat_history:\n",
|
||||
" human = \"Human: \" + dialogue_turn[0]\n",
|
||||
" ai = \"Assistant: \" + dialogue_turn[1]\n",
|
||||
" buffer += \"\\n\" + \"\\n\".join([human, ai])\n",
|
||||
" return buffer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "5c32cc89",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"_inputs = RunnableMap(\n",
|
||||
" {\n",
|
||||
" \"standalone_question\": {\n",
|
||||
" \"question\": lambda x: x[\"question\"],\n",
|
||||
" \"chat_history\": lambda x: _format_chat_history(x['chat_history'])\n",
|
||||
" } | CONDENSE_QUESTION_PROMPT | ChatOpenAI(temperature=0) | StrOutputParser(),\n",
|
||||
" }\n",
|
||||
")\n",
|
||||
"_context = {\n",
|
||||
" \"context\": itemgetter(\"standalone_question\") | retriever | _combine_documents,\n",
|
||||
" \"question\": lambda x: x[\"standalone_question\"]\n",
|
||||
"}\n",
|
||||
"conversational_qa_chain = _inputs | _context | ANSWER_PROMPT | ChatOpenAI()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "135c8205",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversational_qa_chain.invoke({\n",
|
||||
" \"question\": \"where did harrison work?\",\n",
|
||||
" \"chat_history\": [],\n",
|
||||
"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"id": "424e7e7a",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='Harrison worked at Kensho.', additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"conversational_qa_chain.invoke({\n",
|
||||
" \"question\": \"where did he work?\",\n",
|
||||
" \"chat_history\": [(\"Who wrote this notebook?\", \"Harrison\")],\n",
|
||||
"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c5543183",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### With Memory and returning source documents\n",
|
||||
"\n",
|
||||
"This shows how to use memory with the above. For memory, we need to manage that outside at the memory. For returning the retrieved documents, we just need to pass them through all the way."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"id": "e31dd17c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.memory import ConversationBufferMemory"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 17,
|
||||
"id": "d4bffe94",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"memory = ConversationBufferMemory(return_messages=True, output_key=\"answer\", input_key=\"question\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 18,
|
||||
"id": "733be985",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# First we add a step to load memory\n",
|
||||
"# This needs to be a RunnableMap because its the first input\n",
|
||||
"loaded_memory = RunnableMap(\n",
|
||||
" {\n",
|
||||
" \"question\": itemgetter(\"question\"),\n",
|
||||
" \"memory\": memory.load_memory_variables,\n",
|
||||
" }\n",
|
||||
")\n",
|
||||
"# Next we add a step to expand memory into the variables\n",
|
||||
"expanded_memory = {\n",
|
||||
" \"question\": itemgetter(\"question\"),\n",
|
||||
" \"chat_history\": lambda x: x[\"memory\"][\"history\"]\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"# Now we calculate the standalone question\n",
|
||||
"standalone_question = {\n",
|
||||
" \"standalone_question\": {\n",
|
||||
" \"question\": lambda x: x[\"question\"],\n",
|
||||
" \"chat_history\": lambda x: _format_chat_history(x['chat_history'])\n",
|
||||
" } | CONDENSE_QUESTION_PROMPT | ChatOpenAI(temperature=0) | StrOutputParser(),\n",
|
||||
"}\n",
|
||||
"# Now we retrieve the documents\n",
|
||||
"retrieved_documents = {\n",
|
||||
" \"docs\": itemgetter(\"standalone_question\") | retriever,\n",
|
||||
" \"question\": lambda x: x[\"standalone_question\"]\n",
|
||||
"}\n",
|
||||
"# Now we construct the inputs for the final prompt\n",
|
||||
"final_inputs = {\n",
|
||||
" \"context\": lambda x: _combine_documents(x[\"docs\"]),\n",
|
||||
" \"question\": itemgetter(\"question\")\n",
|
||||
"}\n",
|
||||
"# And finally, we do the part that returns the answers\n",
|
||||
"answer = {\n",
|
||||
" \"answer\": final_inputs | ANSWER_PROMPT | ChatOpenAI(),\n",
|
||||
" \"docs\": itemgetter(\"docs\"),\n",
|
||||
"}\n",
|
||||
"# And now we put it all together!\n",
|
||||
"final_chain = loaded_memory | expanded_memory | standalone_question | retrieved_documents | answer"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 19,
|
||||
"id": "806e390c",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'answer': AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False),\n",
|
||||
" 'docs': [Document(page_content='harrison worked at kensho', metadata={})]}"
|
||||
]
|
||||
},
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"inputs = {\"question\": \"where did harrison work?\"}\n",
|
||||
"result = final_chain.invoke(inputs)\n",
|
||||
"result"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"id": "977399fd",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Note that the memory does not save automatically\n",
|
||||
"# This will be improved in the future\n",
|
||||
"# For now you need to save it yourself\n",
|
||||
"memory.save_context(inputs, {\"answer\": result[\"answer\"].content})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"id": "f94f7de4",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"{'history': [HumanMessage(content='where did harrison work?', additional_kwargs={}, example=False),\n",
|
||||
" AIMessage(content='Harrison was employed at Kensho.', additional_kwargs={}, example=False)]}"
|
||||
]
|
||||
},
|
||||
"execution_count": 21,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"memory.load_memory_variables({})"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "poetry-venv",
|
||||
"language": "python",
|
||||
"name": "poetry-venv"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,227 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "c14da114-1a4a-487d-9cff-e0e8c30ba366",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_position: 3\n",
|
||||
"title: Querying a SQL DB\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "506e9636",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We can replicate our SQLDatabaseChain with Runnables."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "7a927516",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.prompts import ChatPromptTemplate\n",
|
||||
"\n",
|
||||
"template = \"\"\"Based on the table schema below, write a SQL query that would answer the user's question:\n",
|
||||
"{schema}\n",
|
||||
"\n",
|
||||
"Question: {question}\n",
|
||||
"SQL Query:\"\"\"\n",
|
||||
"prompt = ChatPromptTemplate.from_template(template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "3f51f386",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.utilities import SQLDatabase"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7c3449d6-684b-416e-ba16-90a035835a88",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We'll need the Chinook sample DB for this example. There's many places to download it from, e.g. https://database.guide/2-sample-databases-sqlite/"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 20,
|
||||
"id": "2ccca6fc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"db = SQLDatabase.from_uri(\"sqlite:///./Chinook.db\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 21,
|
||||
"id": "05ba88ee",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def get_schema(_):\n",
|
||||
" return db.get_table_info()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 22,
|
||||
"id": "a4eda902",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def run_query(query):\n",
|
||||
" return db.run(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 23,
|
||||
"id": "5046cb17",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from operator import itemgetter\n",
|
||||
"\n",
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.schema.output_parser import StrOutputParser\n",
|
||||
"from langchain.schema.runnable import RunnableLambda, RunnableMap\n",
|
||||
"\n",
|
||||
"model = ChatOpenAI()\n",
|
||||
"\n",
|
||||
"inputs = {\n",
|
||||
" \"schema\": RunnableLambda(get_schema),\n",
|
||||
" \"question\": itemgetter(\"question\")\n",
|
||||
"}\n",
|
||||
"sql_response = (\n",
|
||||
" RunnableMap(inputs)\n",
|
||||
" | prompt\n",
|
||||
" | model.bind(stop=[\"\\nSQLResult:\"])\n",
|
||||
" | StrOutputParser()\n",
|
||||
" )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 24,
|
||||
"id": "a5552039",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'SELECT COUNT(*) FROM Employee'"
|
||||
]
|
||||
},
|
||||
"execution_count": 24,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"sql_response.invoke({\"question\": \"How many employees are there?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 25,
|
||||
"id": "d6fee130",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"Based on the table schema below, question, sql query, and sql response, write a natural language response:\n",
|
||||
"{schema}\n",
|
||||
"\n",
|
||||
"Question: {question}\n",
|
||||
"SQL Query: {query}\n",
|
||||
"SQL Response: {response}\"\"\"\n",
|
||||
"prompt_response = ChatPromptTemplate.from_template(template)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 26,
|
||||
"id": "923aa634",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"full_chain = (\n",
|
||||
" RunnableMap({\n",
|
||||
" \"question\": itemgetter(\"question\"),\n",
|
||||
" \"query\": sql_response,\n",
|
||||
" }) \n",
|
||||
" | {\n",
|
||||
" \"schema\": RunnableLambda(get_schema),\n",
|
||||
" \"question\": itemgetter(\"question\"),\n",
|
||||
" \"query\": itemgetter(\"query\"),\n",
|
||||
" \"response\": lambda x: db.run(x[\"query\"]) \n",
|
||||
" } \n",
|
||||
" | prompt_response \n",
|
||||
" | model\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 27,
|
||||
"id": "e94963d8",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='There are 8 employees.', additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 27,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"full_chain.invoke({\"question\": \"How many employees are there?\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4f358d7b-a721-4db3-9f92-f06913428afc",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,122 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "29781123",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Using tools\n",
|
||||
"\n",
|
||||
"You can use any Tools with Runnables easily."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a5c579dd-2e22-41b0-a789-346dfdecb5a2",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install duckduckgo-search"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "9232d2a9",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatOpenAI\n",
|
||||
"from langchain.prompts import ChatPromptTemplate\n",
|
||||
"from langchain.schema.output_parser import StrOutputParser\n",
|
||||
"from langchain.tools import DuckDuckGoSearchRun"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "a0c64d2c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"search = DuckDuckGoSearchRun()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "391969b6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"template = \"\"\"turn the following user input into a search query for a search engine:\n",
|
||||
"\n",
|
||||
"{input}\"\"\"\n",
|
||||
"prompt = ChatPromptTemplate.from_template(template)\n",
|
||||
"\n",
|
||||
"model = ChatOpenAI()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "e3d9d20d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chain = prompt | model | StrOutputParser() | search"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "55f2967d",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'What sports games are on TV today & tonight? Watch and stream live sports on TV today, tonight, tomorrow. Today\\'s 2023 sports TV schedule includes football, basketball, baseball, hockey, motorsports, soccer and more. Watch on TV or stream online on ESPN, FOX, FS1, CBS, NBC, ABC, Peacock, Paramount+, fuboTV, local channels and many other networks. MLB Games Tonight: How to Watch on TV, Streaming & Odds - Thursday, September 7. Seattle Mariners\\' Julio Rodriguez greets teammates in the dugout after scoring against the Oakland Athletics in a ... Circle - Country Music and Lifestyle. Live coverage of all the MLB action today is available to you, with the information provided below. The Brewers will look to pick up a road win at PNC Park against the Pirates on Wednesday at 12:35 PM ET. Check out the latest odds and with BetMGM Sportsbook. Use bonus code \"GNPLAY\" for special offers! MLB Games Tonight: How to Watch on TV, Streaming & Odds - Tuesday, September 5. Houston Astros\\' Kyle Tucker runs after hitting a double during the fourth inning of a baseball game against the Los Angeles Angels, Sunday, Aug. 13, 2023, in Houston. (AP Photo/Eric Christian Smith) (APMedia) The Houston Astros versus the Texas Rangers is one of ... The second half of tonight\\'s college football schedule still has some good games remaining to watch on your television.. We\\'ve already seen an exciting one when Colorado upset TCU. And we saw some ...'"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"input\": \"I'd like to figure out what games are tonight\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "a16949cf-00ea-43c6-a6aa-797ad4f6918d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "poetry-venv",
|
||||
"language": "python",
|
||||
"name": "poetry-venv"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,2 +0,0 @@
|
||||
label: 'How to'
|
||||
position: 1
|
||||
@@ -1,158 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "fbc4bf6e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Run arbitrary functions\n",
|
||||
"\n",
|
||||
"You can use arbitrary functions in the pipeline\n",
|
||||
"\n",
|
||||
"Note that all inputs to these functions need to be a SINGLE argument. If you have a function that accepts multiple arguments, you should write a wrapper that accepts a single input and unpacks it into multiple argument."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 77,
|
||||
"id": "6bb221b3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.schema.runnable import RunnableLambda\n",
|
||||
"\n",
|
||||
"def length_function(text):\n",
|
||||
" return len(text)\n",
|
||||
"\n",
|
||||
"def _multiple_length_function(text1, text2):\n",
|
||||
" return len(text1) * len(text2)\n",
|
||||
"\n",
|
||||
"def multiple_length_function(_dict):\n",
|
||||
" return _multiple_length_function(_dict[\"text1\"], _dict[\"text2\"])\n",
|
||||
"\n",
|
||||
"prompt = ChatPromptTemplate.from_template(\"what is {a} + {b}\")\n",
|
||||
"\n",
|
||||
"chain1 = prompt | model\n",
|
||||
"\n",
|
||||
"chain = {\n",
|
||||
" \"a\": itemgetter(\"foo\") | RunnableLambda(length_function),\n",
|
||||
" \"b\": {\"text1\": itemgetter(\"foo\"), \"text2\": itemgetter(\"bar\")} | RunnableLambda(multiple_length_function)\n",
|
||||
"} | prompt | model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 78,
|
||||
"id": "5488ec85",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content='3 + 9 equals 12.', additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 78,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"chain.invoke({\"foo\": \"bar\", \"bar\": \"gah\"})"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4728ddd9-914d-42ce-ae9b-72c9ce8ec940",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Accepting a Runnable Config\n",
|
||||
"\n",
|
||||
"Runnable lambdas can optionally accept a [RunnableConfig](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.config.RunnableConfig.html?highlight=runnableconfig#langchain.schema.runnable.config.RunnableConfig), which they can use to pass callbacks, tags, and other configuration information to nested runs."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 139,
|
||||
"id": "80b3b5f6-5d58-44b9-807e-cce9a46bf49f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.schema.runnable import RunnableConfig"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 149,
|
||||
"id": "ff0daf0c-49dd-4d21-9772-e5fa133c5f36",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import json\n",
|
||||
"\n",
|
||||
"def parse_or_fix(text: str, config: RunnableConfig):\n",
|
||||
" fixing_chain = (\n",
|
||||
" ChatPromptTemplate.from_template(\n",
|
||||
" \"Fix the following text:\\n\\n```text\\n{input}\\n```\\nError: {error}\"\n",
|
||||
" \" Don't narrate, just respond with the fixed data.\"\n",
|
||||
" )\n",
|
||||
" | ChatOpenAI()\n",
|
||||
" | StrOutputParser()\n",
|
||||
" )\n",
|
||||
" for _ in range(3):\n",
|
||||
" try:\n",
|
||||
" return json.loads(text)\n",
|
||||
" except Exception as e:\n",
|
||||
" text = fixing_chain.invoke({\"input\": text, \"error\": e}, config)\n",
|
||||
" return \"Failed to parse\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 152,
|
||||
"id": "1a5e709e-9d75-48c7-bb9c-503251990505",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Tokens Used: 65\n",
|
||||
"\tPrompt Tokens: 56\n",
|
||||
"\tCompletion Tokens: 9\n",
|
||||
"Successful Requests: 1\n",
|
||||
"Total Cost (USD): $0.00010200000000000001\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.callbacks import get_openai_callback\n",
|
||||
"\n",
|
||||
"with get_openai_callback() as cb:\n",
|
||||
" RunnableLambda(parse_or_fix).invoke(\"{foo: bar}\", {\"tags\": [\"my-tag\"], \"callbacks\": [cb]})\n",
|
||||
" print(cb)"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,21 +1,12 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "raw",
|
||||
"id": "366a0e68-fd67-4fe5-a292-5c33733339ea",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"---\n",
|
||||
"sidebar_position: 0\n",
|
||||
"title: Interface\n",
|
||||
"---"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "9a9acd2e",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Interface\n",
|
||||
"\n",
|
||||
"In an effort to make it as easy as possible to create custom chains, we've implemented a [\"Runnable\"](https://api.python.langchain.com/en/latest/schema/langchain.schema.runnable.Runnable.html#langchain.schema.runnable.Runnable) protocol that most components implement. This is a standard interface with a few different methods, which makes it easy to define custom chains as well as making it possible to invoke them in a standard way. The standard interface exposed includes:\n",
|
||||
"\n",
|
||||
"- `stream`: stream back chunks of the response\n",
|
||||
@@ -438,7 +429,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.10.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
"source": [
|
||||
"# Data anonymization with Microsoft Presidio\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization/index.ipynb)\n",
|
||||
"[](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization.ipynb)\n",
|
||||
"\n",
|
||||
"## Use case\n",
|
||||
"\n",
|
||||
@@ -439,6 +439,8 @@
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Future works\n",
|
||||
"\n",
|
||||
"- **deanonymization** - add the ability to reverse anonymization. For example, the workflow could look like this: `anonymize -> LLMChain -> deanonymize`. By doing this, we will retain anonymity in requests to, for example, OpenAI, and then be able restore the original data.\n",
|
||||
"- **instance anonymization** - at this point, each occurrence of PII is treated as a separate entity and separately anonymized. Therefore, two occurrences of the name John Doe in the text will be changed to two different names. It is therefore worth introducing support for full instance detection, so that repeated occurrences are treated as a single object."
|
||||
]
|
||||
}
|
||||
@@ -459,7 +461,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.11.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
@@ -1,520 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Mutli-language data anonymization with Microsoft Presidio\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization/multi_language.ipynb)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## Use case\n",
|
||||
"\n",
|
||||
"Multi-language support in data pseudonymization is essential due to differences in language structures and cultural contexts. Different languages may have varying formats for personal identifiers. For example, the structure of names, locations and dates can differ greatly between languages and regions. Furthermore, non-alphanumeric characters, accents, and the direction of writing can impact pseudonymization processes. Without multi-language support, data could remain identifiable or be misinterpreted, compromising data privacy and accuracy. Hence, it enables effective and precise pseudonymization suited for global operations.\n",
|
||||
"\n",
|
||||
"## Overview\n",
|
||||
"\n",
|
||||
"PII detection in Microsoft Presidio relies on several components - in addition to the usual pattern matching (e.g. using regex), the analyser uses a model for Named Entity Recognition (NER) to extract entities such as:\n",
|
||||
"- `PERSON`\n",
|
||||
"- `LOCATION`\n",
|
||||
"- `DATE_TIME`\n",
|
||||
"- `NRP`\n",
|
||||
"- `ORGANIZATION`\n",
|
||||
"\n",
|
||||
"[[Source]](https://github.com/microsoft/presidio/blob/main/presidio-analyzer/presidio_analyzer/predefined_recognizers/spacy_recognizer.py)\n",
|
||||
"\n",
|
||||
"To handle NER in specific languages, we utilize unique models from the `spaCy` library, recognized for its extensive selection covering multiple languages and sizes. However, it's not restrictive, allowing for integration of alternative frameworks such as [Stanza](https://microsoft.github.io/presidio/analyzer/nlp_engines/spacy_stanza/) or [transformers](https://microsoft.github.io/presidio/analyzer/nlp_engines/transformers/) when necessary.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## Quickstart\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Install necessary packages\n",
|
||||
"# ! pip install langchain langchain-experimental openai presidio-analyzer presidio-anonymizer spacy Faker\n",
|
||||
"# ! python -m spacy download en_core_web_lg"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain_experimental.data_anonymizer import PresidioReversibleAnonymizer\n",
|
||||
"\n",
|
||||
"anonymizer = PresidioReversibleAnonymizer(\n",
|
||||
" analyzed_fields=[\"PERSON\"],\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"By default, `PresidioAnonymizer` and `PresidioReversibleAnonymizer` use a model trained on English texts, so they handle other languages moderately well. \n",
|
||||
"\n",
|
||||
"For example, here the model did not detect the person:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Me llamo Sofía'"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"anonymizer.anonymize(\"Me llamo Sofía\") # \"My name is Sofía\" in Spanish"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"They may also take words from another language as actual entities. Here, both the word *'Yo'* (*'I'* in Spanish) and *Sofía* have been classified as `PERSON`:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"'Bridget Kirk soy Sally Knight'"
|
||||
]
|
||||
},
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"anonymizer.anonymize(\"Yo soy Sofía\") # \"I am Sofía\" in Spanish"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you want to anonymise texts from other languages, you need to download other models and add them to the anonymiser configuration:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Download the models for the languages you want to use\n",
|
||||
"# ! python -m spacy download en_core_web_md\n",
|
||||
"# ! python -m spacy download es_core_news_md"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"nlp_config = {\n",
|
||||
" \"nlp_engine_name\": \"spacy\",\n",
|
||||
" \"models\": [\n",
|
||||
" {\"lang_code\": \"en\", \"model_name\": \"en_core_web_md\"},\n",
|
||||
" {\"lang_code\": \"es\", \"model_name\": \"es_core_news_md\"},\n",
|
||||
" ],\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We have therefore added a Spanish language model. Note also that we have downloaded an alternative model for English as well - in this case we have replaced the large model `en_core_web_lg` (560MB) with its smaller version `en_core_web_md` (40MB) - the size is therefore reduced by 14 times! If you care about the speed of anonymisation, it is worth considering it.\n",
|
||||
"\n",
|
||||
"All models for the different languages can be found in the [spaCy documentation](https://spacy.io/usage/models).\n",
|
||||
"\n",
|
||||
"Now pass the configuration as the `languages_config` parameter to Anonymiser. As you can see, both previous examples work flawlessly:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Me llamo Michelle Smith\n",
|
||||
"Yo soy Rachel Wright\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"anonymizer = PresidioReversibleAnonymizer(\n",
|
||||
" analyzed_fields=[\"PERSON\"],\n",
|
||||
" languages_config=nlp_config,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print(\n",
|
||||
" anonymizer.anonymize(\"Me llamo Sofía\", language=\"es\")\n",
|
||||
") # \"My name is Sofía\" in Spanish\n",
|
||||
"print(anonymizer.anonymize(\"Yo soy Sofía\", language=\"es\")) # \"I am Sofía\" in Spanish"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"By default, the language indicated first in the configuration will be used when anonymising text (in this case English):"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"My name is Ronnie Ayala\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(anonymizer.anonymize(\"My name is John\"))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Advanced usage\n",
|
||||
"\n",
|
||||
"### Custom labels in NER model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"It may be that the spaCy model has different class names than those supported by the Microsoft Presidio by default. Take Polish, for example:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Text: Wiktoria, Start: 12, End: 20, Label: persName\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# ! python -m spacy download pl_core_news_md\n",
|
||||
"\n",
|
||||
"import spacy\n",
|
||||
"\n",
|
||||
"nlp = spacy.load(\"pl_core_news_md\")\n",
|
||||
"doc = nlp(\"Nazywam się Wiktoria\") # \"My name is Wiktoria\" in Polish\n",
|
||||
"\n",
|
||||
"for ent in doc.ents:\n",
|
||||
" print(\n",
|
||||
" f\"Text: {ent.text}, Start: {ent.start_char}, End: {ent.end_char}, Label: {ent.label_}\"\n",
|
||||
" )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The name *Victoria* was classified as `persName`, which does not correspond to the default class names `PERSON`/`PER` implemented in Microsoft Presidio (look for `CHECK_LABEL_GROUPS` in [SpacyRecognizer implementation](https://github.com/microsoft/presidio/blob/main/presidio-analyzer/presidio_analyzer/predefined_recognizers/spacy_recognizer.py)). \n",
|
||||
"\n",
|
||||
"You can find out more about custom labels in spaCy models (including your own, trained ones) in [this thread](https://github.com/microsoft/presidio/issues/851).\n",
|
||||
"\n",
|
||||
"That's why our sentence will not be anonymized:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Nazywam się Wiktoria\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"nlp_config = {\n",
|
||||
" \"nlp_engine_name\": \"spacy\",\n",
|
||||
" \"models\": [\n",
|
||||
" {\"lang_code\": \"en\", \"model_name\": \"en_core_web_md\"},\n",
|
||||
" {\"lang_code\": \"es\", \"model_name\": \"es_core_news_md\"},\n",
|
||||
" {\"lang_code\": \"pl\", \"model_name\": \"pl_core_news_md\"},\n",
|
||||
" ],\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"anonymizer = PresidioReversibleAnonymizer(\n",
|
||||
" analyzed_fields=[\"PERSON\", \"LOCATION\", \"DATE_TIME\"],\n",
|
||||
" languages_config=nlp_config,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"print(\n",
|
||||
" anonymizer.anonymize(\"Nazywam się Wiktoria\", language=\"pl\")\n",
|
||||
") # \"My name is Wiktoria\" in Polish"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To address this, create your own `SpacyRecognizer` with your own class mapping and add it to the anonymizer:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from presidio_analyzer.predefined_recognizers import SpacyRecognizer\n",
|
||||
"\n",
|
||||
"polish_check_label_groups = [\n",
|
||||
" ({\"LOCATION\"}, {\"placeName\", \"geogName\"}),\n",
|
||||
" ({\"PERSON\"}, {\"persName\"}),\n",
|
||||
" ({\"DATE_TIME\"}, {\"date\", \"time\"}),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"spacy_recognizer = SpacyRecognizer(\n",
|
||||
" supported_language=\"pl\",\n",
|
||||
" check_label_groups=polish_check_label_groups,\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"anonymizer.add_recognizer(spacy_recognizer)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Now everything works smoothly:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Nazywam się Morgan Walters\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\n",
|
||||
" anonymizer.anonymize(\"Nazywam się Wiktoria\", language=\"pl\")\n",
|
||||
") # \"My name is Wiktoria\" in Polish"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Let's try on more complex example:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Nazywam się Ernest Liu. New Taylorburgh to moje miasto rodzinne. Urodziłam się 1987-01-19\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\n",
|
||||
" anonymizer.anonymize(\n",
|
||||
" \"Nazywam się Wiktoria. Płock to moje miasto rodzinne. Urodziłam się dnia 6 kwietnia 2001 roku\",\n",
|
||||
" language=\"pl\",\n",
|
||||
" )\n",
|
||||
") # \"My name is Wiktoria. Płock is my home town. I was born on 6 April 2001\" in Polish"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"As you can see, thanks to class mapping, the anonymiser can cope with different types of entities. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Custom language-specific operators\n",
|
||||
"\n",
|
||||
"In the example above, the sentence has been anonymised correctly, but the fake data does not fit the Polish language at all. Custom operators can therefore be added, which will resolve the issue:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from faker import Faker\n",
|
||||
"from presidio_anonymizer.entities import OperatorConfig\n",
|
||||
"\n",
|
||||
"fake = Faker(locale=\"pl_PL\") # Setting faker to provide Polish data\n",
|
||||
"\n",
|
||||
"new_operators = {\n",
|
||||
" \"PERSON\": OperatorConfig(\"custom\", {\"lambda\": lambda _: fake.first_name_female()}),\n",
|
||||
" \"LOCATION\": OperatorConfig(\"custom\", {\"lambda\": lambda _: fake.city()}),\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"anonymizer.add_operators(new_operators)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 15,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Nazywam się Marianna. Szczecin to moje miasto rodzinne. Urodziłam się 1976-11-16\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\n",
|
||||
" anonymizer.anonymize(\n",
|
||||
" \"Nazywam się Wiktoria. Płock to moje miasto rodzinne. Urodziłam się dnia 6 kwietnia 2001 roku\",\n",
|
||||
" language=\"pl\",\n",
|
||||
" )\n",
|
||||
") # \"My name is Wiktoria. Płock is my home town. I was born on 6 April 2001\" in Polish"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Limitations\n",
|
||||
"\n",
|
||||
"Remember - results are as good as your recognizers and as your NER models!\n",
|
||||
"\n",
|
||||
"Look at the example below - we downloaded the small model for Spanish (12MB) and it no longer performs as well as the medium version (40MB):"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Model: es_core_news_sm. Result: Me llamo Sofía\n",
|
||||
"Model: es_core_news_md. Result: Me llamo Lawrence Davis\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# ! python -m spacy download es_core_news_sm\n",
|
||||
"\n",
|
||||
"for model in [\"es_core_news_sm\", \"es_core_news_md\"]:\n",
|
||||
" nlp_config = {\n",
|
||||
" \"nlp_engine_name\": \"spacy\",\n",
|
||||
" \"models\": [\n",
|
||||
" {\"lang_code\": \"es\", \"model_name\": model},\n",
|
||||
" ],\n",
|
||||
" }\n",
|
||||
"\n",
|
||||
" anonymizer = PresidioReversibleAnonymizer(\n",
|
||||
" analyzed_fields=[\"PERSON\"],\n",
|
||||
" languages_config=nlp_config,\n",
|
||||
" )\n",
|
||||
"\n",
|
||||
" print(\n",
|
||||
" f\"Model: {model}. Result: {anonymizer.anonymize('Me llamo Sofía', language='es')}\"\n",
|
||||
" )"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In many cases, even the larger models from spaCy will not be sufficient - there are already other, more complex and better methods of detecting named entities, based on transformers. You can read more about this [here](https://microsoft.github.io/presidio/analyzer/nlp_engines/transformers/)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Future works\n",
|
||||
"\n",
|
||||
"- **automatic language detection** - instead of passing the language as a parameter in `anonymizer.anonymize`, we could detect the language/s beforehand and then use the corresponding NER model."
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -6,7 +6,7 @@
|
||||
"source": [
|
||||
"# Reversible data anonymization with Microsoft Presidio\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_data_anonymization/reversible.ipynb)\n",
|
||||
"[](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/guides/privacy/presidio_reversible_anonymization.ipynb)\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## Use case\n",
|
||||
@@ -453,7 +453,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
"version": "3.11.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
@@ -1,310 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Confident\n",
|
||||
"\n",
|
||||
">[DeepEval](https://confident-ai.com) package for unit testing LLMs.\n",
|
||||
"> Using Confident, everyone can build robust language models through faster iterations\n",
|
||||
"> using both unit testing and integration testing. We provide support for each step in the iteration\n",
|
||||
"> from synthetic data creation to testing.\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"In this guide we will demonstrate how to test and measure LLMs in performance. We show how you can use our callback to measure performance and how you can define your own metric and log them into our dashboard.\n",
|
||||
"\n",
|
||||
"DeepEval also offers:\n",
|
||||
"- How to generate synthetic data\n",
|
||||
"- How to measure performance\n",
|
||||
"- A dashboard to monitor and review results over time"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"source": [
|
||||
"## Installation and Setup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!pip install deepeval --upgrade"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Getting API Credentials\n",
|
||||
"\n",
|
||||
"To get the DeepEval API credentials, follow the next steps:\n",
|
||||
"\n",
|
||||
"1. Go to https://app.confident-ai.com\n",
|
||||
"2. Click on \"Organization\"\n",
|
||||
"3. Copy the API Key.\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"When you log in, you will also be asked to set the `implementation` name. The implementation name is required to describe the type of implementation. (Think of what you want to call your project. We recommend making it descriptive.)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"!deepeval login"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Setup DeepEval\n",
|
||||
"\n",
|
||||
"You can, by default, use the `DeepEvalCallbackHandler` to set up the metrics you want to track. However, this has limited support for metrics at the moment (more to be added soon). It currently supports:\n",
|
||||
"- [Answer Relevancy](https://docs.confident-ai.com/docs/measuring_llm_performance/answer_relevancy)\n",
|
||||
"- [Bias](https://docs.confident-ai.com/docs/measuring_llm_performance/debias)\n",
|
||||
"- [Toxicness](https://docs.confident-ai.com/docs/measuring_llm_performance/non_toxic)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from deepeval.metrics.answer_relevancy import AnswerRelevancy\n",
|
||||
"\n",
|
||||
"# Here we want to make sure the answer is minimally relevant\n",
|
||||
"answer_relevancy_metric = AnswerRelevancy(minimum_score=0.5)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Get Started"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To use the `DeepEvalCallbackHandler`, we need the `implementation_name`. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from langchain.callbacks.confident_callback import DeepEvalCallbackHandler\n",
|
||||
"\n",
|
||||
"deepeval_callback = DeepEvalCallbackHandler(\n",
|
||||
" implementation_name=\"langchainQuickstart\",\n",
|
||||
" metrics=[answer_relevancy_metric]\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Scenario 1: Feeding into LLM\n",
|
||||
"\n",
|
||||
"You can then feed it into your LLM with OpenAI."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"LLMResult(generations=[[Generation(text='\\n\\nQ: What did the fish say when he hit the wall? \\nA: Dam.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nThe Moon \\n\\nThe moon is high in the midnight sky,\\nSparkling like a star above.\\nThe night so peaceful, so serene,\\nFilling up the air with love.\\n\\nEver changing and renewing,\\nA never-ending light of grace.\\nThe moon remains a constant view,\\nA reminder of life’s gentle pace.\\n\\nThrough time and space it guides us on,\\nA never-fading beacon of hope.\\nThe moon shines down on us all,\\nAs it continues to rise and elope.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ. What did one magnet say to the other magnet?\\nA. \"I find you very attractive!\"', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nThe world is charged with the grandeur of God.\\nIt will flame out, like shining from shook foil;\\nIt gathers to a greatness, like the ooze of oil\\nCrushed. Why do men then now not reck his rod?\\n\\nGenerations have trod, have trod, have trod;\\nAnd all is seared with trade; bleared, smeared with toil;\\nAnd wears man's smudge and shares man's smell: the soil\\nIs bare now, nor can foot feel, being shod.\\n\\nAnd for all this, nature is never spent;\\nThere lives the dearest freshness deep down things;\\nAnd though the last lights off the black West went\\nOh, morning, at the brown brink eastward, springs —\\n\\nBecause the Holy Ghost over the bent\\nWorld broods with warm breast and with ah! bright wings.\\n\\n~Gerard Manley Hopkins\", generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text='\\n\\nQ: What did one ocean say to the other ocean?\\nA: Nothing, they just waved.', generation_info={'finish_reason': 'stop', 'logprobs': None})], [Generation(text=\"\\n\\nA poem for you\\n\\nOn a field of green\\n\\nThe sky so blue\\n\\nA gentle breeze, the sun above\\n\\nA beautiful world, for us to love\\n\\nLife is a journey, full of surprise\\n\\nFull of joy and full of surprise\\n\\nBe brave and take small steps\\n\\nThe future will be revealed with depth\\n\\nIn the morning, when dawn arrives\\n\\nA fresh start, no reason to hide\\n\\nSomewhere down the road, there's a heart that beats\\n\\nBelieve in yourself, you'll always succeed.\", generation_info={'finish_reason': 'stop', 'logprobs': None})]], llm_output={'token_usage': {'completion_tokens': 504, 'total_tokens': 528, 'prompt_tokens': 24}, 'model_name': 'text-davinci-003'})"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"llm = OpenAI(\n",
|
||||
" temperature=0,\n",
|
||||
" callbacks=[deepeval_callback],\n",
|
||||
" verbose=True,\n",
|
||||
" openai_api_key=\"<YOUR_API_KEY>\",\n",
|
||||
")\n",
|
||||
"output = llm.generate(\n",
|
||||
" [\n",
|
||||
" \"What is the best evaluation tool out there? (no bias at all)\",\n",
|
||||
" ]\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"You can then check the metric if it was successful by calling the `is_successful()` method."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"answer_relevancy_metric.is_successful()\n",
|
||||
"# returns True/False"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Once you have ran that, you should be able to see our dashboard below. \n",
|
||||
"\n",
|
||||
""
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Scenario 2: Tracking an LLM in a chain without callbacks\n",
|
||||
"\n",
|
||||
"To track an LLM in a chain without callbacks, you can plug into it at the end.\n",
|
||||
"\n",
|
||||
"We can start by defining a simple chain as shown below."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import requests\n",
|
||||
"from langchain.chains import RetrievalQA\n",
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.text_splitter import CharacterTextSplitter\n",
|
||||
"from langchain.vectorstores import Chroma\n",
|
||||
"\n",
|
||||
"text_file_url = \"https://raw.githubusercontent.com/hwchase17/chat-your-data/master/state_of_the_union.txt\"\n",
|
||||
"\n",
|
||||
"openai_api_key = \"sk-XXX\"\n",
|
||||
"\n",
|
||||
"with open(\"state_of_the_union.txt\", \"w\") as f:\n",
|
||||
" response = requests.get(text_file_url)\n",
|
||||
" f.write(response.text)\n",
|
||||
"\n",
|
||||
"loader = TextLoader(\"state_of_the_union.txt\")\n",
|
||||
"documents = loader.load()\n",
|
||||
"text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)\n",
|
||||
"texts = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings(openai_api_key=openai_api_key)\n",
|
||||
"docsearch = Chroma.from_documents(texts, embeddings)\n",
|
||||
"\n",
|
||||
"qa = RetrievalQA.from_chain_type(\n",
|
||||
" llm=OpenAI(openai_api_key=openai_api_key), chain_type=\"stuff\",\n",
|
||||
" retriever=docsearch.as_retriever()\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"# Providing a new question-answering pipeline\n",
|
||||
"query = \"Who is the president?\"\n",
|
||||
"result = qa.run(query)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"After defining a chain, you can then manually check for answer similarity."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"answer_relevancy_metric.measure(result, query)\n",
|
||||
"answer_relevancy_metric.is_successful()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### What's next?\n",
|
||||
"\n",
|
||||
"You can create your own custom metrics [here](https://docs.confident-ai.com/docs/quickstart/custom-metrics). \n",
|
||||
"\n",
|
||||
"DeepEval also offers other features such as being able to [automatically create unit tests](https://docs.confident-ai.com/docs/quickstart/synthetic-data-creation), [tests for hallucination](https://docs.confident-ai.com/docs/measuring_llm_performance/factual_consistency).\n",
|
||||
"\n",
|
||||
"If you are interested, check out our Github repository here [https://github.com/confident-ai/deepeval](https://github.com/confident-ai/deepeval). We welcome any PRs and discussions on how to improve LLM performance."
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.11.3"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "a53ebf4a859167383b364e7e7521d0add3c2dbbdecce4edf676e8c4634ff3fbb"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -1,23 +1,19 @@
|
||||
# LLMonitor
|
||||
|
||||
[LLMonitor](https://llmonitor.com?utm_source=langchain&utm_medium=py&utm_campaign=docs) is an open-source observability platform that provides cost and usage analytics, user tracking, tracing and evaluation tools.
|
||||
[LLMonitor](https://llmonitor.com) is an open-source observability platform that provides cost tracking, user tracking and powerful agent tracing.
|
||||
|
||||
<video controls width='100%' >
|
||||
<source src='https://llmonitor.com/videos/demo-annotated.mp4'/>
|
||||
</video>
|
||||
|
||||
## Setup
|
||||
|
||||
Create an account on [llmonitor.com](https://llmonitor.com?utm_source=langchain&utm_medium=py&utm_campaign=docs), then copy your new app's `tracking id`.
|
||||
|
||||
Create an account on [llmonitor.com](https://llmonitor.com), create an `App`, and then copy the associated `tracking id`.
|
||||
Once you have it, set it as an environment variable by running:
|
||||
|
||||
```bash
|
||||
export LLMONITOR_APP_ID="..."
|
||||
```
|
||||
|
||||
If you'd prefer not to set an environment variable, you can pass the key directly when initializing the callback handler:
|
||||
|
||||
```python
|
||||
from langchain.callbacks import LLMonitorCallbackHandler
|
||||
|
||||
@@ -25,13 +21,12 @@ handler = LLMonitorCallbackHandler(app_id="...")
|
||||
```
|
||||
|
||||
## Usage with LLM/Chat models
|
||||
|
||||
```python
|
||||
from langchain.llms import OpenAI
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
from langchain.callbacks import LLMonitorCallbackHandler
|
||||
|
||||
handler = LLMonitorCallbackHandler()
|
||||
handler = LLMonitorCallbackHandler(app_id="...")
|
||||
|
||||
llm = OpenAI(
|
||||
callbacks=[handler],
|
||||
@@ -43,63 +38,26 @@ chat = ChatOpenAI(
|
||||
)
|
||||
```
|
||||
|
||||
## Usage with chains and agents
|
||||
|
||||
Make sure to pass the callback handler to the `run` method so that all related chains and llm calls are correctly tracked.
|
||||
|
||||
It is also recommended to pass `agent_name` in the metadata to be able to distinguish between agents in the dashboard.
|
||||
|
||||
Example:
|
||||
|
||||
```python
|
||||
from langchain.chat_models import ChatOpenAI
|
||||
from langchain.schema import SystemMessage, HumanMessage
|
||||
from langchain.agents import OpenAIFunctionsAgent, AgentExecutor, tool
|
||||
from langchain.callbacks import LLMonitorCallbackHandler
|
||||
|
||||
llm = ChatOpenAI(temperature=0)
|
||||
|
||||
handler = LLMonitorCallbackHandler()
|
||||
|
||||
@tool
|
||||
def get_word_length(word: str) -> int:
|
||||
"""Returns the length of a word."""
|
||||
return len(word)
|
||||
|
||||
tools = [get_word_length]
|
||||
|
||||
prompt = OpenAIFunctionsAgent.create_prompt(
|
||||
system_message=SystemMessage(
|
||||
content="You are very powerful assistant, but bad at calculating lengths of words."
|
||||
)
|
||||
)
|
||||
|
||||
agent = OpenAIFunctionsAgent(llm=llm, tools=tools, prompt=prompt, verbose=True)
|
||||
agent_executor = AgentExecutor(
|
||||
agent=agent, tools=tools, verbose=True, metadata={"agent_name": "WordCount"} # <- recommended, assign a custom name
|
||||
)
|
||||
agent_executor.run("how many letters in the word educa?", callbacks=[handler])
|
||||
```
|
||||
|
||||
Another example:
|
||||
|
||||
## Usage with agents
|
||||
```python
|
||||
from langchain.agents import load_tools, initialize_agent, AgentType
|
||||
from langchain.llms import OpenAI
|
||||
from langchain.callbacks import LLMonitorCallbackHandler
|
||||
|
||||
handler = LLMonitorCallbackHandler()
|
||||
handler = LLMonitorCallbackHandler(app_id="...")
|
||||
|
||||
llm = OpenAI(temperature=0)
|
||||
tools = load_tools(["serpapi", "llm-math"], llm=llm)
|
||||
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, metadata={ "agent_name": "GirlfriendAgeFinder" }) # <- recommended, assign a custom name
|
||||
|
||||
agent = initialize_agent(tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION)
|
||||
agent.run(
|
||||
"Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?",
|
||||
callbacks=[handler],
|
||||
metadata={
|
||||
"agentName": "Leo DiCaprio's girlfriend", # you can assign a custom agent in the metadata
|
||||
},
|
||||
)
|
||||
```
|
||||
|
||||
## Support
|
||||
|
||||
For any question or issue with integration you can reach out to the LLMonitor team on [Discord](http://discord.com/invite/8PafSG58kK) or via [email](mailto:vince@llmonitor.com).
|
||||
|
||||
@@ -1,164 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Konko\n",
|
||||
"\n",
|
||||
">[Konko](https://www.konko.ai/) API is a fully managed Web API designed to help application developers:\n",
|
||||
"\n",
|
||||
"Konko API is a fully managed API designed to help application developers:\n",
|
||||
"\n",
|
||||
"1. Select the right LLM(s) for their application\n",
|
||||
"2. Prototype with various open-source and proprietary LLMs\n",
|
||||
"3. Move to production in-line with their security, privacy, throughput, latency SLAs without infrastructure set-up or administration using Konko AI's SOC 2 compliant infrastructure\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"This example goes over how to use LangChain to interact with `Konko` [models](https://docs.konko.ai/docs/overview)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To run this notebook, you'll need Konko API key. You can request it by messaging support@konko.ai."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.chat_models import ChatKonko\n",
|
||||
"from langchain.prompts.chat import (\n",
|
||||
" ChatPromptTemplate,\n",
|
||||
" SystemMessagePromptTemplate,\n",
|
||||
" AIMessagePromptTemplate,\n",
|
||||
" HumanMessagePromptTemplate,\n",
|
||||
")\n",
|
||||
"from langchain.schema import AIMessage, HumanMessage, SystemMessage"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## 2. Set API Keys\n",
|
||||
"\n",
|
||||
"<br />\n",
|
||||
"\n",
|
||||
"### Option 1: Set Environment Variables\n",
|
||||
"\n",
|
||||
"1. You can set environment variables for \n",
|
||||
" 1. KONKO_API_KEY (Required)\n",
|
||||
" 2. OPENAI_API_KEY (Optional)\n",
|
||||
"2. In your current shell session, use the export command:\n",
|
||||
"\n",
|
||||
"```shell\n",
|
||||
"export KONKO_API_KEY={your_KONKO_API_KEY_here}\n",
|
||||
"export OPENAI_API_KEY={your_OPENAI_API_KEY_here} #Optional\n",
|
||||
"```\n",
|
||||
"\n",
|
||||
"Alternatively, you can add the above lines directly to your shell startup script (such as .bashrc or .bash_profile for Bash shell and .zshrc for Zsh shell) to have them set automatically every time a new shell session starts.\n",
|
||||
"\n",
|
||||
"### Option 2: Set API Keys Programmatically\n",
|
||||
"\n",
|
||||
"If you prefer to set your API keys directly within your Python script or Jupyter notebook, you can use the following commands:\n",
|
||||
"\n",
|
||||
"```python\n",
|
||||
"konko.set_api_key('your_KONKO_API_KEY_here') \n",
|
||||
"konko.set_openai_api_key('your_OPENAI_API_KEY_here') # Optional\n",
|
||||
"```\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Calling a model\n",
|
||||
"\n",
|
||||
"Find a model on the [Konko overview page](https://docs.konko.ai/docs/overview)\n",
|
||||
"\n",
|
||||
"For example, for this [LLama 2 model](https://docs.konko.ai/docs/meta-llama-2-13b-chat). The model id would be: `\"meta-llama/Llama-2-13b-chat-hf\"`\n",
|
||||
"\n",
|
||||
"Another way to find the list of models running on the Konko instance is through this [endpoint](https://docs.konko.ai/reference/listmodels).\n",
|
||||
"\n",
|
||||
"From here, we can initialize our model:\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"chat = ChatKonko(max_tokens=400, model = 'meta-llama/Llama-2-13b-chat-hf')"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"AIMessage(content=\" Sure, I'd be happy to explain the Big Bang Theory briefly!\\n\\nThe Big Bang Theory is the leading explanation for the origin and evolution of the universe, based on a vast amount of observational evidence from many fields of science. In essence, the theory posits that the universe began as an infinitely hot and dense point, known as a singularity, around 13.8 billion years ago. This singularity expanded rapidly, and as it did, it cooled and formed subatomic particles, which eventually coalesced into the first atoms, and later into the stars and galaxies we see today.\\n\\nThe theory gets its name from the idea that the universe began in a state of incredibly high energy and temperature, and has been expanding and cooling ever since. This expansion is thought to have been driven by a mysterious force known as dark energy, which is thought to be responsible for the accelerating expansion of the universe.\\n\\nOne of the key predictions of the Big Bang Theory is that the universe should be homogeneous and isotropic on large scales, meaning that it should look the same in all directions and have the same properties everywhere. This prediction has been confirmed by a wealth of observational evidence, including the cosmic microwave background radiation, which is thought to be a remnant of the early universe.\\n\\nOverall, the Big Bang Theory is a well-established and widely accepted explanation for the origins of the universe, and it has been supported by a vast amount of observational evidence from many fields of science.\", additional_kwargs={}, example=False)"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"messages = [\n",
|
||||
" SystemMessage(\n",
|
||||
" content=\"You are a helpful assistant.\"\n",
|
||||
" ),\n",
|
||||
" HumanMessage(\n",
|
||||
" content=\"Explain Big Bang Theory briefly\"\n",
|
||||
" ),\n",
|
||||
"]\n",
|
||||
"chat(messages)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"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": "3.11.3"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "a0a0263b650d907a3bfe41c0f8d6a63a071b884df3cfdc1579f00cdc1aed6b03"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
}
|
||||
@@ -1,240 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# CTranslate2"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"**CTranslate2** is a C++ and Python library for efficient inference with Transformer models.\n",
|
||||
"\n",
|
||||
"The project implements a custom runtime that applies many performance optimization techniques such as weights quantization, layers fusion, batch reordering, etc., to accelerate and reduce the memory usage of Transformer models on CPU and GPU.\n",
|
||||
"\n",
|
||||
"Full list of features and supported models is included in the [project's repository](https://opennmt.net/CTranslate2/guides/transformers.html). To start, please check out the official [quickstart guide](https://opennmt.net/CTranslate2/quickstart.html).\n",
|
||||
"\n",
|
||||
"To use, you should have `ctranslate2` python package installed."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#!pip install ctranslate2"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To use a Hugging Face model with CTranslate2, it has to be first converted to CTranslate2 format using the `ct2-transformers-converter` command. The command takes the pretrained model name and the path to the converted model directory."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Loading checkpoint shards: 100%|██████████████████| 2/2 [00:01<00:00, 1.81it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# converstion can take several minutes\n",
|
||||
"!ct2-transformers-converter --model meta-llama/Llama-2-7b-hf --quantization bfloat16 --output_dir ./llama-2-7b-ct2 --force"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import CTranslate2\n",
|
||||
"\n",
|
||||
"llm = CTranslate2(\n",
|
||||
" # output_dir from above:\n",
|
||||
" model_path=\"./llama-2-7b-ct2\",\n",
|
||||
" tokenizer_name=\"meta-llama/Llama-2-7b-hf\",\n",
|
||||
" device=\"cuda\",\n",
|
||||
" # device_index can be either single int or list or ints,\n",
|
||||
" # indicating the ids of GPUs to use for inference:\n",
|
||||
" device_index=[0,1], \n",
|
||||
" compute_type=\"bfloat16\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Single call"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 31,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"He presented me with plausible evidence for the existence of unicorns: 1) they are mentioned in ancient texts; and, more importantly to him (and not so much as a matter that would convince most people), he had seen one.\n",
|
||||
"I was skeptical but I didn't want my friend upset by his belief being dismissed outright without any consideration or argument on its behalf whatsoever - which is why we were having this conversation at all! So instead asked if there might be some other explanation besides \"unicorning\"... maybe it could have been an ostrich? Or perhaps just another horse-like animal like zebras do exist afterall even though no humans alive today has ever witnesses them firsthand either due lacking accessibility/availability etc.. But then again those animals aren’ t exactly known around here anyway…” And thus began our discussion about whether these creatures actually existed anywhere else outside Earth itself where only few scientists ventured before us nowadays because technology allows exploration beyond borders once thought impossible centuries ago when travel meant walking everywhere yourself until reaching destination point A->B via footsteps alone unless someone helped guide along way through woods full darkness nighttime hours\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\n",
|
||||
" llm(\n",
|
||||
" \"He presented me with plausible evidence for the existence of unicorns: \",\n",
|
||||
" max_length=256,\n",
|
||||
" sampling_topk=50,\n",
|
||||
" sampling_temperature=0.2,\n",
|
||||
" repetition_penalty=2,\n",
|
||||
" cache_static_prompt=False,\n",
|
||||
" )\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Multiple calls:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 34,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"generations=[[Generation(text='The list of top romantic songs:\\n1. “I Will Always Love You” by Whitney Houston\\n2. “Can’t Help Falling in Love” by Elvis Presley\\n3. “Unchained Melody” by The Righteous Brothers\\n4. “I Will Always Love You” by Dolly Parton\\n5. “I Will Always Love You” by Whitney Houston\\n6. “I Will Always Love You” by Dolly Parton\\n7. “I Will Always Love You” by The Beatles\\n8. “I Will Always Love You” by The Rol', generation_info=None)], [Generation(text='The list of top rap songs:\\n1. “God’s Plan” by Drake\\n2. “Rockstar” by Post Malone\\n3. “Bad and Boujee” by Migos\\n4. “Humble” by Kendrick Lamar\\n5. “Bodak Yellow” by Cardi B\\n6. “I’m the One” by DJ Khaled\\n7. “Motorsport” by Migos\\n8. “No Limit” by G-Eazy\\n9. “Bounce Back” by Big Sean\\n10. “', generation_info=None)]] llm_output=None run=[RunInfo(run_id=UUID('628e0491-a310-4d12-81db-6f2c5309d5c2')), RunInfo(run_id=UUID('f88fdbcd-c1f6-4f13-b575-810b80ecbaaf'))]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"print(\n",
|
||||
" llm.generate(\n",
|
||||
" [\"The list of top romantic songs:\\n1.\", \"The list of top rap songs:\\n1.\"],\n",
|
||||
" max_length=128\n",
|
||||
" )\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Integrate the model in an LLMChain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 46,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Who was the US president in the year the first Pokemon game was released?\n",
|
||||
"\n",
|
||||
"Let's think step by step. 1996 was the year the first Pokemon game was released.\n",
|
||||
"\n",
|
||||
"\\begin{blockquote}\n",
|
||||
"\n",
|
||||
"\\begin{itemize}\n",
|
||||
" \\item 1996 was the year Bill Clinton was president.\n",
|
||||
" \\item 1996 was the year the first Pokemon game was released.\n",
|
||||
" \\item 1996 was the year the first Pokemon game was released.\n",
|
||||
"\n",
|
||||
"\\end{itemize}\n",
|
||||
"\\end{blockquote}\n",
|
||||
"\n",
|
||||
"I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n",
|
||||
"Comment: @JoeZ. I'm not sure if this is a valid question, but I'm sure it's a fun one.\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from langchain import PromptTemplate, LLMChain\n",
|
||||
"\n",
|
||||
"template = \"\"\"{question}\n",
|
||||
"\n",
|
||||
"Let's think step by step. \"\"\"\n",
|
||||
"prompt = PromptTemplate(template=template, input_variables=[\"question\"])\n",
|
||||
"\n",
|
||||
"llm_chain = LLMChain(prompt=prompt, llm=llm)\n",
|
||||
"\n",
|
||||
"question = \"Who was the US president in the year the first Pokemon game was released?\"\n",
|
||||
"\n",
|
||||
"print(llm_chain.run(question))"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.10.12 ('langchain_venv': venv)",
|
||||
"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": "3.10.12"
|
||||
},
|
||||
"orig_nbformat": 4,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "d1d3a3c58a58885896c5459933a599607cdbb9917d7e1ad7516c8786c51f2dd2"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -9,20 +9,13 @@ pip install awadb
|
||||
```
|
||||
|
||||
|
||||
## Vector Store
|
||||
## VectorStore
|
||||
|
||||
There exists a wrapper around AwaDB vector databases, allowing you to use it as a vectorstore,
|
||||
whether for semantic search or example selection.
|
||||
|
||||
```python
|
||||
from langchain.vectorstores import AwaDB
|
||||
```
|
||||
|
||||
See a [usage example](/docs/integrations/vectorstores/awadb).
|
||||
|
||||
|
||||
## Text Embedding Model
|
||||
|
||||
```python
|
||||
from langchain.embeddings import AwaEmbeddings
|
||||
```
|
||||
|
||||
See a [usage example](/docs/integrations/text_embedding/awadb).
|
||||
For a more detailed walkthrough of the AwaDB wrapper, see [here](/docs/integrations/vectorstores/awadb.html).
|
||||
|
||||
@@ -1,22 +0,0 @@
|
||||
# Confident AI
|
||||
|
||||
|
||||
|
||||
>[DeepEval](https://confident-ai.com) package for unit testing LLMs.
|
||||
> Using Confident, everyone can build robust language models through faster iterations
|
||||
> using both unit testing and integration testing. We provide support for each step in the iteration
|
||||
> from synthetic data creation to testing.
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
First, you'll need to install the `DeepEval` Python package as follows:
|
||||
|
||||
```bash
|
||||
pip install deepeval
|
||||
```
|
||||
|
||||
Afterwards, you can get started in as little as a few lines of code.
|
||||
|
||||
```python
|
||||
from langchain.callbacks import DeepEvalCallback
|
||||
```
|
||||
@@ -1,80 +0,0 @@
|
||||
# Konko
|
||||
This page covers how to run models on Konko within LangChain.
|
||||
|
||||
Konko API is a fully managed API designed to help application developers:
|
||||
|
||||
Select the right LLM(s) for their application
|
||||
Prototype with various open-source and proprietary LLMs
|
||||
Move to production in-line with their security, privacy, throughput, latency SLAs without infrastructure set-up or administration using Konko AI's SOC 2 compliant infrastructure
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
### First you'll need an API key
|
||||
You can request it by messaging [support@konko.ai](mailto:support@konko.ai)
|
||||
|
||||
### Install Konko AI's Python SDK
|
||||
|
||||
#### 1. Enable a Python3.8+ environment
|
||||
|
||||
#### 2. Set API Keys
|
||||
|
||||
##### Option 1: Set Environment Variables
|
||||
|
||||
1. You can set environment variables for
|
||||
1. KONKO_API_KEY (Required)
|
||||
2. OPENAI_API_KEY (Optional)
|
||||
|
||||
2. In your current shell session, use the export command:
|
||||
|
||||
```shell
|
||||
export KONKO_API_KEY={your_KONKO_API_KEY_here}
|
||||
export OPENAI_API_KEY={your_OPENAI_API_KEY_here} #Optional
|
||||
```
|
||||
|
||||
Alternatively, you can add the above lines directly to your shell startup script (such as .bashrc or .bash_profile for Bash shell and .zshrc for Zsh shell) to have them set automatically every time a new shell session starts.
|
||||
|
||||
##### Option 2: Set API Keys Programmatically
|
||||
|
||||
If you prefer to set your API keys directly within your Python script or Jupyter notebook, you can use the following commands:
|
||||
|
||||
```python
|
||||
konko.set_api_key('your_KONKO_API_KEY_here')
|
||||
konko.set_openai_api_key('your_OPENAI_API_KEY_here') # Optional
|
||||
```
|
||||
|
||||
#### 3. Install the SDK
|
||||
|
||||
|
||||
```shell
|
||||
pip install konko
|
||||
```
|
||||
|
||||
#### 4. Verify Installation & Authentication
|
||||
|
||||
```python
|
||||
#Confirm konko has installed successfully
|
||||
import konko
|
||||
#Confirm API keys from Konko and OpenAI are set properly
|
||||
konko.Model.list()
|
||||
```
|
||||
|
||||
## Calling a model
|
||||
|
||||
Find a model on the [Konko Introduction page](https://docs.konko.ai/docs#available-models)
|
||||
|
||||
For example, for this [LLama 2 model](https://docs.konko.ai/docs/meta-llama-2-13b-chat). The model id would be: `"meta-llama/Llama-2-13b-chat-hf"`
|
||||
|
||||
Another way to find the list of models running on the Konko instance is through this [endpoint](https://docs.konko.ai/reference/listmodels).
|
||||
|
||||
From here, we can initialize our model:
|
||||
|
||||
```python
|
||||
chat_instance = ChatKonko(max_tokens=10, model = 'meta-llama/Llama-2-13b-chat-hf')
|
||||
```
|
||||
|
||||
And run it:
|
||||
|
||||
```python
|
||||
msg = HumanMessage(content="Hi")
|
||||
chat_response = chat_instance([msg])
|
||||
```
|
||||
@@ -1,24 +1,20 @@
|
||||
# ModelScope
|
||||
|
||||
>[ModelScope](https://www.modelscope.cn/home) is a big repository of the models and datasets.
|
||||
|
||||
This page covers how to use the modelscope ecosystem within LangChain.
|
||||
It is broken into two parts: installation and setup, and then references to specific modelscope wrappers.
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
Install the `modelscope` package.
|
||||
|
||||
```bash
|
||||
pip install modelscope
|
||||
```
|
||||
* Install the Python SDK with `pip install modelscope`
|
||||
|
||||
## Wrappers
|
||||
|
||||
## Text Embedding Models
|
||||
### Embeddings
|
||||
|
||||
There exists a modelscope Embeddings wrapper, which you can access with
|
||||
|
||||
```python
|
||||
from langchain.embeddings import ModelScopeEmbeddings
|
||||
```
|
||||
|
||||
For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/modelscope_hub)
|
||||
For a more detailed walkthrough of this, see [this notebook](/docs/integrations/text_embedding/modelscope_hub.html)
|
||||
|
||||
@@ -1,31 +1,17 @@
|
||||
# NLPCloud
|
||||
|
||||
>[NLP Cloud](https://docs.nlpcloud.com/#introduction) is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data.
|
||||
|
||||
This page covers how to use the NLPCloud ecosystem within LangChain.
|
||||
It is broken into two parts: installation and setup, and then references to specific NLPCloud wrappers.
|
||||
|
||||
## Installation and Setup
|
||||
|
||||
- Install the `nlpcloud` package.
|
||||
|
||||
```bash
|
||||
pip install nlpcloud
|
||||
```
|
||||
|
||||
- Install the Python SDK with `pip install nlpcloud`
|
||||
- Get an NLPCloud api key and set it as an environment variable (`NLPCLOUD_API_KEY`)
|
||||
|
||||
## Wrappers
|
||||
|
||||
## LLM
|
||||
|
||||
See a [usage example](/docs/integrations/llms/nlpcloud).
|
||||
### LLM
|
||||
|
||||
There exists an NLPCloud LLM wrapper, which you can access with
|
||||
```python
|
||||
from langchain.llms import NLPCloud
|
||||
```
|
||||
|
||||
## Text Embedding Models
|
||||
|
||||
See a [usage example](/docs/integrations/text_embedding/nlp_cloud)
|
||||
|
||||
```python
|
||||
from langchain.embeddings import NLPCloudEmbeddings
|
||||
```
|
||||
|
||||
@@ -1,10 +1,4 @@
|
||||
# Portkey
|
||||
|
||||
>[Portkey](https://docs.portkey.ai/overview/introduction) is a platform designed to streamline the deployment
|
||||
> and management of Generative AI applications.
|
||||
> It provides comprehensive features for monitoring, managing models,
|
||||
> and improving the performance of your AI applications.
|
||||
|
||||
## LLMOps for Langchain
|
||||
|
||||
Portkey brings production readiness to Langchain. With Portkey, you can
|
||||
|
||||
@@ -1,14 +1,19 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": []
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Log, Trace, and Monitor\n",
|
||||
"# Log, Trace, and Monitor Langchain LLM Calls\n",
|
||||
"\n",
|
||||
"When building apps or agents using Langchain, you end up making multiple API calls to fulfill a single user request. However, these requests are not chained when you want to analyse them. With [**Portkey**](/docs/ecosystem/integrations/portkey), all the embeddings, completion, and other requests from a single user request will get logged and traced to a common ID, enabling you to gain full visibility of user interactions.\n",
|
||||
"\n",
|
||||
"This notebook serves as a step-by-step guide on how to log, trace, and monitor Langchain LLM calls using `Portkey` in your Langchain app."
|
||||
"This notebook serves as a step-by-step guide on how to integrate and use Portkey in your Langchain app."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -229,9 +234,9 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.11.3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
||||
@@ -18,11 +18,3 @@ See a [usage example](/docs/modules/data_connection/document_transformers/text_s
|
||||
```python
|
||||
from langchain.text_splitter import SpacyTextSplitter
|
||||
```
|
||||
|
||||
## Text Embedding Models
|
||||
|
||||
See a [usage example](/docs/integrations/text_embedding/spacy_embedding)
|
||||
|
||||
```python
|
||||
from langchain.embeddings.spacy_embeddings import SpacyEmbeddings
|
||||
```
|
||||
|
||||
@@ -5,11 +5,9 @@
|
||||
"id": "b14a24db",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# AwaDB\n",
|
||||
"# AwaEmbedding\n",
|
||||
"\n",
|
||||
">[AwaDB](https://github.com/awa-ai/awadb) is an AI Native database for the search and storage of embedding vectors used by LLM Applications.\n",
|
||||
"\n",
|
||||
"This notebook explains how to use `AwaEmbeddings` in LangChain."
|
||||
"This notebook explains how to use AwaEmbedding, which is included in [awadb](https://github.com/awa-ai/awadb), to embedding texts in langchain."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -103,7 +101,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.11.4"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
@@ -5,9 +5,7 @@
|
||||
"id": "75e378f5-55d7-44b6-8e2e-6d7b8b171ec4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Bedrock\n",
|
||||
"\n",
|
||||
">[Amazon Bedrock](https://aws.amazon.com/bedrock/) is a fully managed service that makes FMs from leading AI startups and Amazon available via an API, so you can choose from a wide range of FMs to find the model that is best suited for your use case.\n"
|
||||
"# Bedrock Embeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -93,7 +91,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.9.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -5,29 +5,26 @@
|
||||
"id": "719619d3",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# BGE on Hugging Face\n",
|
||||
"# BGE Hugging Face Embeddings\n",
|
||||
"\n",
|
||||
">[BGE models on the HuggingFace](https://huggingface.co/BAAI/bge-large-en) are [the best open-source embedding models](https://huggingface.co/spaces/mteb/leaderboard).\n",
|
||||
">BGE model is created by the [Beijing Academy of Artificial Intelligence (BAAI)](https://www.baai.ac.cn/english.html). `BAAI` is a private non-profit organization engaged in AI research and development.\n",
|
||||
"\n",
|
||||
"This notebook shows how to use `BGE Embeddings` through `Hugging Face`"
|
||||
"This notebook shows how to use BGE Embeddings through Hugging Face"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 8,
|
||||
"id": "f7a54279",
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#!pip install sentence_transformers"
|
||||
"# !pip install sentence_transformers"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 5,
|
||||
"id": "9e1d5b6b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
@@ -46,24 +43,12 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"execution_count": 7,
|
||||
"id": "e59d1a89",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"384"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"embedding = hf.embed_query(\"hi this is harrison\")\n",
|
||||
"len(embedding)"
|
||||
"embedding = hf.embed_query(\"hi this is harrison\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -91,7 +76,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.10.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -1,14 +1,13 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Google Vertex AI PaLM \n",
|
||||
"# Google Cloud Platform Vertex AI PaLM \n",
|
||||
"\n",
|
||||
">[Vertex AI PaLM API](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/overview) is a service on Google Cloud exposing the embedding models. \n",
|
||||
"\n",
|
||||
"Note: This integration is seperate from the Google PaLM integration.\n",
|
||||
"Note: This is seperate from the Google PaLM integration, it exposes [Vertex AI PaLM API](https://cloud.google.com/vertex-ai/docs/generative-ai/learn/overview) on Google Cloud. \n",
|
||||
"\n",
|
||||
"By default, Google Cloud [does not use](https://cloud.google.com/vertex-ai/docs/generative-ai/data-governance#foundation_model_development) Customer Data to train its foundation models as part of Google Cloud`s AI/ML Privacy Commitment. More details about how Google processes data can also be found in [Google's Customer Data Processing Addendum (CDPA)](https://cloud.google.com/terms/data-processing-addendum).\n",
|
||||
"\n",
|
||||
@@ -97,7 +96,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.9.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
||||
@@ -1,13 +1,12 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# ModelScope\n",
|
||||
"\n",
|
||||
">[ModelScope](https://www.modelscope.cn/home) is big repository of the models and datasets.\n",
|
||||
"\n",
|
||||
"Let's load the ModelScope Embedding class."
|
||||
]
|
||||
},
|
||||
@@ -68,23 +67,16 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"display_name": "chatgpt",
|
||||
"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": "3.10.12"
|
||||
}
|
||||
"version": "3.9.15"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
||||
@@ -1,14 +1,15 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# MosaicML\n",
|
||||
"# MosaicML embeddings\n",
|
||||
"\n",
|
||||
">[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n",
|
||||
"[MosaicML](https://docs.mosaicml.com/en/latest/inference.html) offers a managed inference service. You can either use a variety of open source models, or deploy your own.\n",
|
||||
"\n",
|
||||
"This example goes over how to use LangChain to interact with `MosaicML` Inference for text embedding."
|
||||
"This example goes over how to use LangChain to interact with MosaicML Inference for text embedding."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -93,11 +94,6 @@
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
@@ -107,10 +103,9 @@
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"pygments_lexer": "ipython3"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
||||
@@ -7,7 +7,7 @@
|
||||
"source": [
|
||||
"# NLP Cloud\n",
|
||||
"\n",
|
||||
">[NLP Cloud](https://docs.nlpcloud.com/#introduction) is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data. \n",
|
||||
"NLP Cloud is an artificial intelligence platform that allows you to use the most advanced AI engines, and even train your own engines with your own data. \n",
|
||||
"\n",
|
||||
"The [embeddings](https://docs.nlpcloud.com/#embeddings) endpoint offers the following model:\n",
|
||||
"\n",
|
||||
@@ -80,7 +80,7 @@
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"display_name": "Python 3.11.2 64-bit",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
@@ -94,7 +94,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.11.2"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
||||
@@ -5,13 +5,11 @@
|
||||
"id": "1f83f273",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# SageMaker\n",
|
||||
"# SageMaker Endpoint Embeddings\n",
|
||||
"\n",
|
||||
"Let's load the `SageMaker Endpoints Embeddings` class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
|
||||
"Let's load the SageMaker Endpoints Embeddings class. The class can be used if you host, e.g. your own Hugging Face model on SageMaker.\n",
|
||||
"\n",
|
||||
"For instructions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker). \n",
|
||||
"\n",
|
||||
"**Note**: In order to handle batched requests, you will need to adjust the return line in the `predict_fn()` function within the custom `inference.py` script:\n",
|
||||
"For instructions on how to do this, please see [here](https://www.philschmid.de/custom-inference-huggingface-sagemaker). **Note**: In order to handle batched requests, you will need to adjust the return line in the `predict_fn()` function within the custom `inference.py` script:\n",
|
||||
"\n",
|
||||
"Change from\n",
|
||||
"\n",
|
||||
@@ -145,7 +143,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.9.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
||||
@@ -5,8 +5,8 @@
|
||||
"id": "eec4efda",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Self Hosted\n",
|
||||
"Let's load the `SelfHostedEmbeddings`, `SelfHostedHuggingFaceEmbeddings`, and `SelfHostedHuggingFaceInstructEmbeddings` classes."
|
||||
"# Self Hosted Embeddings\n",
|
||||
"Let's load the SelfHostedEmbeddings, SelfHostedHuggingFaceEmbeddings, and SelfHostedHuggingFaceInstructEmbeddings classes."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -149,7 +149,9 @@
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "fc1bfd0f",
|
||||
"metadata": {},
|
||||
"metadata": {
|
||||
"scrolled": false
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query_result = embeddings.embed_query(text)"
|
||||
@@ -180,7 +182,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.9.1"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
||||
@@ -1,15 +1,16 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"id": "ed47bb62",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Sentence Transformers\n",
|
||||
"# Sentence Transformers Embeddings\n",
|
||||
"\n",
|
||||
">[SentenceTransformers](https://www.sbert.net/) embeddings are called using the `HuggingFaceEmbeddings` integration. We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
|
||||
"[SentenceTransformers](https://www.sbert.net/) embeddings are called using the `HuggingFaceEmbeddings` integration. We have also added an alias for `SentenceTransformerEmbeddings` for users who are more familiar with directly using that package.\n",
|
||||
"\n",
|
||||
"`SentenceTransformers` is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
|
||||
"SentenceTransformers is a python package that can generate text and image embeddings, originating from [Sentence-BERT](https://arxiv.org/abs/1908.10084)"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -108,7 +109,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.12"
|
||||
"version": "3.8.16"
|
||||
},
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
|
||||
@@ -1,31 +1,21 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# SpaCy\n",
|
||||
"# Spacy Embedding\n",
|
||||
"\n",
|
||||
">[spaCy](https://spacy.io/) is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython.\n",
|
||||
" \n",
|
||||
"\n",
|
||||
"## Installation and Setup"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"#!pip install spacy"
|
||||
"### Loading the Spacy embedding class to generate and query embeddings"
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Import the necessary classes"
|
||||
"#### Import the necessary classes"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -38,12 +28,11 @@
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Example\n",
|
||||
"\n",
|
||||
"Initialize SpacyEmbeddings.This will load the Spacy model into memory."
|
||||
"#### Initialize SpacyEmbeddings.This will load the Spacy model into memory."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -56,10 +45,11 @@
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Define some example texts . These could be any documents that you want to analyze - for example, news articles, social media posts, or product reviews."
|
||||
"#### Define some example texts . These could be any documents that you want to analyze - for example, news articles, social media posts, or product reviews."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -77,10 +67,11 @@
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Generate and print embeddings for the texts . The SpacyEmbeddings class generates an embedding for each document, which is a numerical representation of the document's content. These embeddings can be used for various natural language processing tasks, such as document similarity comparison or text classification."
|
||||
"#### Generate and print embeddings for the texts . The SpacyEmbeddings class generates an embedding for each document, which is a numerical representation of the document's content. These embeddings can be used for various natural language processing tasks, such as document similarity comparison or text classification."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -95,10 +86,11 @@
|
||||
]
|
||||
},
|
||||
{
|
||||
"attachments": {},
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Generate and print an embedding for a single piece of text. You can also generate an embedding for a single piece of text, such as a search query. This can be useful for tasks like information retrieval, where you want to find documents that are similar to a given query."
|
||||
"#### Generate and print an embedding for a single piece of text. You can also generate an embedding for a single piece of text, such as a search query. This can be useful for tasks like information retrieval, where you want to find documents that are similar to a given query."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -114,24 +106,11 @@
|
||||
}
|
||||
],
|
||||
"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": "3.10.12"
|
||||
}
|
||||
"name": "python"
|
||||
},
|
||||
"orig_nbformat": 4
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 4
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
|
||||
@@ -24,11 +24,42 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"execution_count": 60,
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Requirement already satisfied: pgvector in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (0.1.8)\n",
|
||||
"Requirement already satisfied: numpy in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from pgvector) (1.24.3)\n",
|
||||
"Requirement already satisfied: openai in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (0.27.7)\n",
|
||||
"Requirement already satisfied: requests>=2.20 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from openai) (2.28.2)\n",
|
||||
"Requirement already satisfied: tqdm in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from openai) (4.65.0)\n",
|
||||
"Requirement already satisfied: aiohttp in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from openai) (3.8.4)\n",
|
||||
"Requirement already satisfied: charset-normalizer<4,>=2 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (3.1.0)\n",
|
||||
"Requirement already satisfied: idna<4,>=2.5 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (3.4)\n",
|
||||
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (1.26.15)\n",
|
||||
"Requirement already satisfied: certifi>=2017.4.17 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.20->openai) (2023.5.7)\n",
|
||||
"Requirement already satisfied: attrs>=17.3.0 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (23.1.0)\n",
|
||||
"Requirement already satisfied: multidict<7.0,>=4.5 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (6.0.4)\n",
|
||||
"Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (4.0.2)\n",
|
||||
"Requirement already satisfied: yarl<2.0,>=1.0 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (1.9.2)\n",
|
||||
"Requirement already satisfied: frozenlist>=1.1.1 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (1.3.3)\n",
|
||||
"Requirement already satisfied: aiosignal>=1.1.2 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from aiohttp->openai) (1.3.1)\n",
|
||||
"Requirement already satisfied: psycopg2-binary in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (2.9.6)\n",
|
||||
"Requirement already satisfied: tiktoken in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (0.4.0)\n",
|
||||
"Requirement already satisfied: regex>=2022.1.18 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from tiktoken) (2023.5.5)\n",
|
||||
"Requirement already satisfied: requests>=2.26.0 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from tiktoken) (2.28.2)\n",
|
||||
"Requirement already satisfied: charset-normalizer<4,>=2 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (3.1.0)\n",
|
||||
"Requirement already satisfied: idna<4,>=2.5 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (3.4)\n",
|
||||
"Requirement already satisfied: urllib3<1.27,>=1.21.1 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (1.26.15)\n",
|
||||
"Requirement already satisfied: certifi>=2017.4.17 in /Users/joyeed/langchain/langchain/.venv/lib/python3.9/site-packages (from requests>=2.26.0->tiktoken) (2023.5.7)\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Pip install necessary package\n",
|
||||
"!pip install pgvector\n",
|
||||
@@ -46,14 +77,17 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:02:16.802456Z",
|
||||
"start_time": "2023-09-09T08:02:07.065604Z"
|
||||
"execution_count": 19,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"OpenAI API Key:········\n"
|
||||
]
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
@@ -63,20 +97,18 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"execution_count": 61,
|
||||
"metadata": {
|
||||
"tags": [],
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:02:19.742896Z",
|
||||
"start_time": "2023-09-09T08:02:19.732527Z"
|
||||
}
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/plain": "False"
|
||||
"text/plain": [
|
||||
"False"
|
||||
]
|
||||
},
|
||||
"execution_count": 3,
|
||||
"execution_count": 61,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
@@ -91,13 +123,9 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"execution_count": 1,
|
||||
"metadata": {
|
||||
"tags": [],
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:02:23.144824Z",
|
||||
"start_time": "2023-09-09T08:02:22.047801Z"
|
||||
}
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
@@ -110,13 +138,8 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:02:25.452472Z",
|
||||
"start_time": "2023-09-09T08:02:25.441563Z"
|
||||
}
|
||||
},
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"loader = TextLoader(\"../../../state_of_the_union.txt\")\n",
|
||||
@@ -129,13 +152,8 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:02:28.174088Z",
|
||||
"start_time": "2023-09-09T08:02:28.162698Z"
|
||||
}
|
||||
},
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# PGVector needs the connection string to the database.\n",
|
||||
@@ -156,22 +174,15 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Similarity Search with Euclidean Distance (Default)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:04:16.696625Z",
|
||||
"start_time": "2023-09-09T08:02:31.817790Z"
|
||||
}
|
||||
},
|
||||
"execution_count": 16,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# The PGVector Module will try to create a table with the name of the collection.\n",
|
||||
@@ -189,13 +200,8 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:05:11.104135Z",
|
||||
"start_time": "2023-09-09T08:05:10.548998Z"
|
||||
}
|
||||
},
|
||||
"execution_count": 17,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"query = \"What did the president say about Ketanji Brown Jackson\"\n",
|
||||
@@ -204,20 +210,15 @@
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:05:13.532334Z",
|
||||
"start_time": "2023-09-09T08:05:13.523191Z"
|
||||
}
|
||||
},
|
||||
"execution_count": 18,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.18456886638850434\n",
|
||||
"Score: 0.18460171628856903\n",
|
||||
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
|
||||
"\n",
|
||||
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
|
||||
@@ -227,7 +228,27 @@
|
||||
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.21742627672631343\n",
|
||||
"Score: 0.18460171628856903\n",
|
||||
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
|
||||
"\n",
|
||||
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
|
||||
"\n",
|
||||
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
|
||||
"\n",
|
||||
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.18470284560586236\n",
|
||||
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
|
||||
"\n",
|
||||
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
|
||||
"\n",
|
||||
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
|
||||
"\n",
|
||||
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.21730864082247825\n",
|
||||
"A former top litigator in private practice. A former federal public defender. And from a family of public school educators and police officers. A consensus builder. Since she’s been nominated, she’s received a broad range of support—from the Fraternal Order of Police to former judges appointed by Democrats and Republicans. \n",
|
||||
"\n",
|
||||
"And if we are to advance liberty and justice, we need to secure the Border and fix the immigration system. \n",
|
||||
@@ -239,38 +260,6 @@
|
||||
"We’re putting in place dedicated immigration judges so families fleeing persecution and violence can have their cases heard faster. \n",
|
||||
"\n",
|
||||
"We’re securing commitments and supporting partners in South and Central America to host more refugees and secure their own borders.\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.22641793174529334\n",
|
||||
"And for our LGBTQ+ Americans, let’s finally get the bipartisan Equality Act to my desk. The onslaught of state laws targeting transgender Americans and their families is wrong. \n",
|
||||
"\n",
|
||||
"As I said last year, especially to our younger transgender Americans, I will always have your back as your President, so you can be yourself and reach your God-given potential. \n",
|
||||
"\n",
|
||||
"While it often appears that we never agree, that isn’t true. I signed 80 bipartisan bills into law last year. From preventing government shutdowns to protecting Asian-Americans from still-too-common hate crimes to reforming military justice. \n",
|
||||
"\n",
|
||||
"And soon, we’ll strengthen the Violence Against Women Act that I first wrote three decades ago. It is important for us to show the nation that we can come together and do big things. \n",
|
||||
"\n",
|
||||
"So tonight I’m offering a Unity Agenda for the Nation. Four big things we can do together. \n",
|
||||
"\n",
|
||||
"First, beat the opioid epidemic.\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.22670040608054465\n",
|
||||
"Tonight, I’m announcing a crackdown on these companies overcharging American businesses and consumers. \n",
|
||||
"\n",
|
||||
"And as Wall Street firms take over more nursing homes, quality in those homes has gone down and costs have gone up. \n",
|
||||
"\n",
|
||||
"That ends on my watch. \n",
|
||||
"\n",
|
||||
"Medicare is going to set higher standards for nursing homes and make sure your loved ones get the care they deserve and expect. \n",
|
||||
"\n",
|
||||
"We’ll also cut costs and keep the economy going strong by giving workers a fair shot, provide more training and apprenticeships, hire them based on their skills not degrees. \n",
|
||||
"\n",
|
||||
"Let’s pass the Paycheck Fairness Act and paid leave. \n",
|
||||
"\n",
|
||||
"Raise the minimum wage to $15 an hour and extend the Child Tax Credit, so no one has to raise a family in poverty. \n",
|
||||
"\n",
|
||||
"Let’s increase Pell Grants and increase our historic support of HBCUs, and invest in what Jill—our First Lady who teaches full-time—calls America’s best-kept secret: community colleges.\n",
|
||||
"--------------------------------------------------------------------------------\n"
|
||||
]
|
||||
}
|
||||
@@ -283,131 +272,6 @@
|
||||
" print(\"-\" * 80)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"source": [
|
||||
"## Maximal Marginal Relevance Search (MMR)\n",
|
||||
"Maximal marginal relevance optimizes for similarity to query AND diversity among selected documents."
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docs_with_score = db.max_marginal_relevance_search_with_score(query)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:05:23.276819Z",
|
||||
"start_time": "2023-09-09T08:05:21.972256Z"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.18453882564037527\n",
|
||||
"Tonight. I call on the Senate to: Pass the Freedom to Vote Act. Pass the John Lewis Voting Rights Act. And while you’re at it, pass the Disclose Act so Americans can know who is funding our elections. \n",
|
||||
"\n",
|
||||
"Tonight, I’d like to honor someone who has dedicated his life to serve this country: Justice Stephen Breyer—an Army veteran, Constitutional scholar, and retiring Justice of the United States Supreme Court. Justice Breyer, thank you for your service. \n",
|
||||
"\n",
|
||||
"One of the most serious constitutional responsibilities a President has is nominating someone to serve on the United States Supreme Court. \n",
|
||||
"\n",
|
||||
"And I did that 4 days ago, when I nominated Circuit Court of Appeals Judge Ketanji Brown Jackson. One of our nation’s top legal minds, who will continue Justice Breyer’s legacy of excellence.\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.23523731441720075\n",
|
||||
"We can’t change how divided we’ve been. But we can change how we move forward—on COVID-19 and other issues we must face together. \n",
|
||||
"\n",
|
||||
"I recently visited the New York City Police Department days after the funerals of Officer Wilbert Mora and his partner, Officer Jason Rivera. \n",
|
||||
"\n",
|
||||
"They were responding to a 9-1-1 call when a man shot and killed them with a stolen gun. \n",
|
||||
"\n",
|
||||
"Officer Mora was 27 years old. \n",
|
||||
"\n",
|
||||
"Officer Rivera was 22. \n",
|
||||
"\n",
|
||||
"Both Dominican Americans who’d grown up on the same streets they later chose to patrol as police officers. \n",
|
||||
"\n",
|
||||
"I spoke with their families and told them that we are forever in debt for their sacrifice, and we will carry on their mission to restore the trust and safety every community deserves. \n",
|
||||
"\n",
|
||||
"I’ve worked on these issues a long time. \n",
|
||||
"\n",
|
||||
"I know what works: Investing in crime preventionand community police officers who’ll walk the beat, who’ll know the neighborhood, and who can restore trust and safety.\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.2448441215698569\n",
|
||||
"One was stationed at bases and breathing in toxic smoke from “burn pits” that incinerated wastes of war—medical and hazard material, jet fuel, and more. \n",
|
||||
"\n",
|
||||
"When they came home, many of the world’s fittest and best trained warriors were never the same. \n",
|
||||
"\n",
|
||||
"Headaches. Numbness. Dizziness. \n",
|
||||
"\n",
|
||||
"A cancer that would put them in a flag-draped coffin. \n",
|
||||
"\n",
|
||||
"I know. \n",
|
||||
"\n",
|
||||
"One of those soldiers was my son Major Beau Biden. \n",
|
||||
"\n",
|
||||
"We don’t know for sure if a burn pit was the cause of his brain cancer, or the diseases of so many of our troops. \n",
|
||||
"\n",
|
||||
"But I’m committed to finding out everything we can. \n",
|
||||
"\n",
|
||||
"Committed to military families like Danielle Robinson from Ohio. \n",
|
||||
"\n",
|
||||
"The widow of Sergeant First Class Heath Robinson. \n",
|
||||
"\n",
|
||||
"He was born a soldier. Army National Guard. Combat medic in Kosovo and Iraq. \n",
|
||||
"\n",
|
||||
"Stationed near Baghdad, just yards from burn pits the size of football fields. \n",
|
||||
"\n",
|
||||
"Heath’s widow Danielle is here with us tonight. They loved going to Ohio State football games. He loved building Legos with their daughter.\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"--------------------------------------------------------------------------------\n",
|
||||
"Score: 0.2513994424701056\n",
|
||||
"And I’m taking robust action to make sure the pain of our sanctions is targeted at Russia’s economy. And I will use every tool at our disposal to protect American businesses and consumers. \n",
|
||||
"\n",
|
||||
"Tonight, I can announce that the United States has worked with 30 other countries to release 60 Million barrels of oil from reserves around the world. \n",
|
||||
"\n",
|
||||
"America will lead that effort, releasing 30 Million barrels from our own Strategic Petroleum Reserve. And we stand ready to do more if necessary, unified with our allies. \n",
|
||||
"\n",
|
||||
"These steps will help blunt gas prices here at home. And I know the news about what’s happening can seem alarming. \n",
|
||||
"\n",
|
||||
"But I want you to know that we are going to be okay. \n",
|
||||
"\n",
|
||||
"When the history of this era is written Putin’s war on Ukraine will have left Russia weaker and the rest of the world stronger. \n",
|
||||
"\n",
|
||||
"While it shouldn’t have taken something so terrible for people around the world to see what’s at stake now everyone sees it clearly.\n",
|
||||
"--------------------------------------------------------------------------------\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"for doc, score in docs_with_score:\n",
|
||||
" print(\"-\" * 80)\n",
|
||||
" print(\"Score: \", score)\n",
|
||||
" print(doc.page_content)\n",
|
||||
" print(\"-\" * 80)"
|
||||
],
|
||||
"metadata": {
|
||||
"collapsed": false,
|
||||
"ExecuteTime": {
|
||||
"end_time": "2023-09-09T08:05:27.478580Z",
|
||||
"start_time": "2023-09-09T08:05:27.470138Z"
|
||||
}
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
|
||||
@@ -10,9 +10,9 @@
|
||||
"\n",
|
||||
"## What is Redis?\n",
|
||||
"\n",
|
||||
"Most developers from a web services background are probably familiar with Redis. At it's core, Redis is an open-source key-value store that can be used as a cache, message broker, and database. Developers choose Redis because it is fast, has a large ecosystem of client libraries, and has been deployed by major enterprises for years.\n",
|
||||
"Most developers from a web services background are probably familiar with Redis. At it's core, Redis is an open-source key-value store that can be used as a cache, message broker, and database. Developers choice Redis because it is fast, has a large ecosystem of client libraries, and has been deployed by major enterprises for years.\n",
|
||||
"\n",
|
||||
"On top of these traditional use cases, Redis provides additional capabilities like the Search and Query capability that allows users to create secondary index structures within Redis. This allows Redis to be a Vector Database, at the speed of a cache. \n",
|
||||
"In addition to the traditional uses of Redis. Redis also provides capabilities built directly into Redis. These capabilities include the Search and Query capability that allows users to create secondary index structures within Redis. This allows Redis to be a Vector Database, at the speed of a cache. \n",
|
||||
"\n",
|
||||
"\n",
|
||||
"## Redis as a Vector Database\n",
|
||||
@@ -123,7 +123,7 @@
|
||||
"source": [
|
||||
"## Install Redis Python Client\n",
|
||||
"\n",
|
||||
"Redis-py is the officially supported client by Redis. Recently released is the RedisVL client which is purpose-built for the Vector Database use cases. Both can be installed with pip."
|
||||
"Redis-py is the officially supported client by Redis. Recently released is the RedisVL client which is purpose built for the Vector Database use cases. Both can be installed with pip."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -153,17 +153,9 @@
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.embeddings import OpenAIEmbeddings\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")\n",
|
||||
"\n",
|
||||
"from langchain.embeddings import OpenAIEmbeddings\n",
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
@@ -223,12 +215,6 @@
|
||||
"source": [
|
||||
"## Initializing Redis\n",
|
||||
"\n",
|
||||
"To locally deploy Redis, run:\n",
|
||||
"```console\n",
|
||||
"docker run -d -p 6379:6379 -p 8001:8001 redis/redis-stack:latest\n",
|
||||
"```\n",
|
||||
"If things are running correctly you should see a nice Redis UI at http://localhost:8001. See the [Deployment Options](#deployment-options) section above for other ways to deploy.\n",
|
||||
"\n",
|
||||
"The Redis VectorStore instance can be initialized in a number of ways. There are multiple class methods that can be used to initialize a Redis VectorStore instance.\n",
|
||||
"\n",
|
||||
"- ``Redis.__init__`` - Initialize directly\n",
|
||||
@@ -237,7 +223,7 @@
|
||||
"- ``Redis.from_texts_return_keys`` - Initialize from a list of texts (optionally with metadata) and return the keys\n",
|
||||
"- ``Redis.from_existing_index`` - Initialize from an existing Redis index\n",
|
||||
"\n",
|
||||
"Below we will use the ``Redis.from_texts`` method."
|
||||
"Below we will use the ``Redis.from_documents`` method."
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -248,12 +234,28 @@
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.vectorstores.redis import Redis\n",
|
||||
"from langchain.vectorstores.redis import Redis"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If you're not interested in the keys of your entries you can also create your redis instance from the documents."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.docstore.document import Document\n",
|
||||
"\n",
|
||||
"rds = Redis.from_texts(\n",
|
||||
" texts,\n",
|
||||
"documents = [Document(page_content=t, metadata=m) for t, m in zip(texts, metadata)]\n",
|
||||
"rds = Redis.from_documents(\n",
|
||||
" documents,\n",
|
||||
" embeddings,\n",
|
||||
" metadatas=metadats,\n",
|
||||
" redis_url=\"redis://localhost:6379\",\n",
|
||||
" index_name=\"users\"\n",
|
||||
")"
|
||||
@@ -411,8 +413,7 @@
|
||||
"- ``similarity_search``: Find the most similar vectors to a given vector.\n",
|
||||
"- ``similarity_search_with_score``: Find the most similar vectors to a given vector and return the vector distance\n",
|
||||
"- ``similarity_search_limit_score``: Find the most similar vectors to a given vector and limit the number of results to the ``score_threshold``\n",
|
||||
"- ``similarity_search_with_relevance_scores``: Find the most similar vectors to a given vector and return the vector similarities\n",
|
||||
"- ``max_marginal_relevance_search``: Find the most similar vectors to a given vector while also optimizing for diversity"
|
||||
"- ``similarity_search_with_relevance_scores``: Find the most similar vectors to a given vector and return the vector similarities"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -452,7 +453,7 @@
|
||||
"results = rds.similarity_search(\"foo\", k=3)\n",
|
||||
"meta = results[1].metadata\n",
|
||||
"print(\"Key of the document in Redis: \", meta.pop(\"id\"))\n",
|
||||
"print(\"Metadata of the document: \", meta)"
|
||||
"print(\"Metadata of the document: \", meta)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
@@ -595,26 +596,6 @@
|
||||
"print(results[0].metadata)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# use maximal marginal relevance search to diversify results\n",
|
||||
"results = rds.max_marginal_relevance_search(\"foo\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# the lambda_mult parameter controls the diversity of the results, the lower the more diverse\n",
|
||||
"results = rds.max_marginal_relevance_search(\"foo\", lambda_mult=0.1)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"metadata": {},
|
||||
@@ -1227,7 +1208,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.11.3"
|
||||
"version": "3.8.13"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -28,41 +28,43 @@
|
||||
"The following function determines cosine similarity, but you can adjust to your needs.\n",
|
||||
"\n",
|
||||
"```sql\n",
|
||||
"-- Enable the pgvector extension to work with embedding vectors\n",
|
||||
"create extension if not exists vector;\n",
|
||||
" -- Enable the pgvector extension to work with embedding vectors\n",
|
||||
" create extension vector;\n",
|
||||
"\n",
|
||||
"-- Create a table to store your documents\n",
|
||||
"create table\n",
|
||||
" documents (\n",
|
||||
" id uuid primary key,\n",
|
||||
" content text, -- corresponds to Document.pageContent\n",
|
||||
" metadata jsonb, -- corresponds to Document.metadata\n",
|
||||
" embedding vector (1536) -- 1536 works for OpenAI embeddings, change if needed\n",
|
||||
" );\n",
|
||||
" -- Create a table to store your documents\n",
|
||||
" create table documents (\n",
|
||||
" id uuid primary key,\n",
|
||||
" content text, -- corresponds to Document.pageContent\n",
|
||||
" metadata jsonb, -- corresponds to Document.metadata\n",
|
||||
" embedding vector(1536) -- 1536 works for OpenAI embeddings, change if needed\n",
|
||||
" );\n",
|
||||
"\n",
|
||||
"-- Create a function to search for documents\n",
|
||||
"create function match_documents (\n",
|
||||
" query_embedding vector (1536),\n",
|
||||
" filter jsonb default '{}'\n",
|
||||
") returns table (\n",
|
||||
" id uuid,\n",
|
||||
" content text,\n",
|
||||
" metadata jsonb,\n",
|
||||
" similarity float\n",
|
||||
") language plpgsql as $$\n",
|
||||
"#variable_conflict use_column\n",
|
||||
"begin\n",
|
||||
" return query\n",
|
||||
" select\n",
|
||||
" id,\n",
|
||||
" content,\n",
|
||||
" metadata,\n",
|
||||
" 1 - (documents.embedding <=> query_embedding) as similarity\n",
|
||||
" from documents\n",
|
||||
" where metadata @> filter\n",
|
||||
" order by documents.embedding <=> query_embedding;\n",
|
||||
"end;\n",
|
||||
"$$;\n",
|
||||
" CREATE FUNCTION match_documents(query_embedding vector(1536), match_count int)\n",
|
||||
" RETURNS TABLE(\n",
|
||||
" id uuid,\n",
|
||||
" content text,\n",
|
||||
" metadata jsonb,\n",
|
||||
" -- we return matched vectors to enable maximal marginal relevance searches\n",
|
||||
" embedding vector(1536),\n",
|
||||
" similarity float)\n",
|
||||
" LANGUAGE plpgsql\n",
|
||||
" AS $$\n",
|
||||
" # variable_conflict use_column\n",
|
||||
" BEGIN\n",
|
||||
" RETURN query\n",
|
||||
" SELECT\n",
|
||||
" id,\n",
|
||||
" content,\n",
|
||||
" metadata,\n",
|
||||
" embedding,\n",
|
||||
" 1 -(documents.embedding <=> query_embedding) AS similarity\n",
|
||||
" FROM\n",
|
||||
" documents\n",
|
||||
" ORDER BY\n",
|
||||
" documents.embedding <=> query_embedding\n",
|
||||
" LIMIT match_count;\n",
|
||||
" END;\n",
|
||||
" $$;\n",
|
||||
"```"
|
||||
]
|
||||
},
|
||||
|
||||
@@ -1,413 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/export/anaconda3/envs/langchainGLM6B/lib/python3.10/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
|
||||
" from .autonotebook import tqdm as notebook_tqdm\n",
|
||||
"INFO 2023-08-28 18:26:07,485-1d: \n",
|
||||
"loading model config\n",
|
||||
"llm device: cuda\n",
|
||||
"embedding device: cuda\n",
|
||||
"dir: /data/zhx/zhx/langchain-ChatGLM_new\n",
|
||||
"flagging username: e2fc35b8e87c4de18d692e951a5f7c46\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"True\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Loading checkpoint shards: 100%|██████████| 7/7 [00:06<00:00, 1.01it/s]\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"\n",
|
||||
"import os, sys, torch\n",
|
||||
"from transformers import AutoTokenizer, AutoModelForCausalLM, AutoModel\n",
|
||||
"from langchain import HuggingFacePipeline, ConversationChain\n",
|
||||
"from langchain.text_splitter import RecursiveCharacterTextSplitter\n",
|
||||
"from langchain.vectorstores.vearch import VearchDb\n",
|
||||
"from langchain.document_loaders import TextLoader\n",
|
||||
"from langchain.prompts import PromptTemplate\n",
|
||||
"from langchain.chains import RetrievalQA\n",
|
||||
"from langchain.embeddings.huggingface import HuggingFaceEmbeddings\n",
|
||||
"\n",
|
||||
"# your local model path\n",
|
||||
"model_path =\"/data/zhx/zhx/langchain-ChatGLM_new/chatglm2-6b\" \n",
|
||||
"\n",
|
||||
"tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)\n",
|
||||
"model = AutoModel.from_pretrained(model_path, trust_remote_code=True).half().cuda(0)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Human: 你好!\n",
|
||||
"ChatGLM:你好👋！我是人工智能助手 ChatGLM2-6B，很高兴见到你，欢迎问我任何问题。\n",
|
||||
"\n",
|
||||
"Human: 你知道凌波微步吗，你知道都有谁学会了吗?\n",
|
||||
"ChatGLM:凌波微步是一种步伐，最早出自于《倚天屠龙记》。在小说中，灭绝师太曾因与练习凌波微步的杨过的恩怨纠葛，而留下了一部经书，内容是记载凌波微步的起源和作用。后来，凌波微步便成为杨过和小龙女的感情象征。在现实生活中，凌波微步是一句口号，是清华大学学生社团“模型社”的社训。\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"query = \"你好!\"\n",
|
||||
"response, history = model.chat(tokenizer, query, history=[])\n",
|
||||
"print(f\"Human: {query}\\nChatGLM:{response}\\n\")\n",
|
||||
"query = \"你知道凌波微步吗，你知道都有谁学会了吗?\"\n",
|
||||
"response, history = model.chat(tokenizer, query, history=history)\n",
|
||||
"print(f\"Human: {query}\\nChatGLM:{response}\\n\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"INFO 2023-08-28 18:27:36,037-1d: Load pretrained SentenceTransformer: /data/zhx/zhx/langchain-ChatGLM_new/text2vec/text2vec-large-chinese\n",
|
||||
"WARNING 2023-08-28 18:27:36,038-1d: No sentence-transformers model found with name /data/zhx/zhx/langchain-ChatGLM_new/text2vec/text2vec-large-chinese. Creating a new one with MEAN pooling.\n",
|
||||
"INFO 2023-08-28 18:27:38,936-1d: Use pytorch device: cuda\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# Add your local knowledge files\n",
|
||||
"file_path = \"/data/zhx/zhx/langchain-ChatGLM_new/knowledge_base/天龙八部/lingboweibu.txt\"#Your local file path\"\n",
|
||||
"loader = TextLoader(file_path,encoding=\"utf-8\")\n",
|
||||
"documents = loader.load()\n",
|
||||
"\n",
|
||||
"# split text into sentences and embedding the sentences\n",
|
||||
"text_splitter = RecursiveCharacterTextSplitter(\n",
|
||||
" chunk_size=500, chunk_overlap=100)\n",
|
||||
"texts = text_splitter.split_documents(documents)\n",
|
||||
"\n",
|
||||
"#your model path\n",
|
||||
"embedding_path = '/data/zhx/zhx/langchain-ChatGLM_new/text2vec/text2vec-large-chinese'\n",
|
||||
"embeddings = HuggingFaceEmbeddings(model_name=embedding_path)\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Batches: 100%|██████████| 1/1 [00:00<00:00, 4.56it/s]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"['7aae36236f784105a0004d8ff3c7c3ad', '7e495d4e5962497db2080e84d52e75ed', '9a640124fc324a8abb0eaa31acb638b7']\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"#first add your document into vearch vectorstore\n",
|
||||
"vearch_db = VearchDb.from_documents(texts,embeddings,table_name=\"your_table_name\",metadata_path=\"/data/zhx/zhx/langchain-ChatGLM_new/knowledge_base/your_table_name\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Batches: 100%|██████████| 1/1 [00:00<00:00, 22.49it/s]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"####################第1段相关文档####################\n",
|
||||
"\n",
|
||||
"午饭过后，段誉又练“凌波微步”，走一步，吸一口气，走第二步时将气呼出，六十四卦走完，四肢全无麻痹之感，料想呼吸顺畅，便无害处。第二次再走时连走两步吸一口气，再走两步始行呼出。这“凌波微步”是以动功修习内功，脚步踏遍六十四卦一个周天，内息自然而然地也转了一个周天。因此他每走一遍，内力便有一分进益。\n",
|
||||
"\n",
|
||||
"这般练了几天，“凌波微步”已走得颇为纯熟，不须再数呼吸，纵然疾行，气息也已无所窒滞。心意既畅，跨步时渐渐想到《洛神赋》中那些与“凌波微步”有关的句子：“仿佛兮若轻云之蔽月，飘飘兮若流风之回雪”，“竦轻躯以鹤立，若将飞而未翔”，“体迅飞凫，飘忽若神”，“动无常则，若危若安。进止难期，若往若还”。\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"百度简介\n",
|
||||
"\n",
|
||||
"凌波微步是「逍遥派」独门轻功身法，精妙异常。\n",
|
||||
"\n",
|
||||
"凌波微步乃是一门极上乘的轻功，所以列于卷轴之末，以易经八八六十四卦为基础，使用者按特定顺序踏着卦象方位行进，从第一步到最后一步正好行走一个大圈。此步法精妙异常，原是要待人练成「北冥神功」，吸人内力，自身内力已【颇为深厚】之后再练。\n",
|
||||
"\n",
|
||||
"####################第2段相关文档####################\n",
|
||||
"\n",
|
||||
"《天龙八部》第五回 微步縠纹生\n",
|
||||
"\n",
|
||||
"卷轴中此外诸种经脉修习之法甚多，皆是取人内力的法门，段誉虽自语宽解，总觉习之有违本性，单是贪多务得，便非好事，当下暂不理会。\n",
|
||||
"\n",
|
||||
"卷到卷轴末端，又见到了“凌波微步”那四字，登时便想起《洛神赋》中那些句子来：“凌波微步，罗袜生尘……转眄流精，光润玉颜。含辞未吐，气若幽兰。华容婀娜，令我忘餐。”曹子建那些千古名句，在脑海中缓缓流过：“秾纤得衷，修短合度，肩若削成，腰如约素。延颈秀项，皓质呈露。芳泽无加，铅华弗御。云髻峨峨，修眉连娟。丹唇外朗，皓齿内鲜。明眸善睐，靥辅承权。瑰姿艳逸，仪静体闲。柔情绰态，媚于语言……”这些句子用在木婉清身上，“这话倒也有理”；但如用之于神仙姊姊，只怕更为适合。想到神仙姊姊的姿容体态，“皎若太阳升朝霞，灼若芙蓉出绿波”，但觉依她吩咐行事，实为人生至乐，心想：“我先来练这‘凌波微步’，此乃逃命之妙法，非害人之手段也，练之有百利而无一害。”\n",
|
||||
"\n",
|
||||
"####################第3段相关文档####################\n",
|
||||
"\n",
|
||||
"《天龙八部》第二回 玉壁月华明\n",
|
||||
"\n",
|
||||
"再展帛卷，长卷上源源皆是裸女画像，或立或卧，或现前胸，或见后背。人像的面容都是一般，但或喜或愁，或含情凝眸，或轻嗔薄怒，神情各异。一共有三十六幅图像，每幅像上均有颜色细线，注明穴道部位及练功法诀。\n",
|
||||
"\n",
|
||||
"帛卷尽处题着“凌波微步”四字，其后绘的是无数足印，注明“妇妹”、“无妄”等等字样，尽是《易经》中的方位。段誉前几日还正全心全意地钻研《易经》，一见到这些名称，登时精神大振，便似遇到故交良友一般。只见足印密密麻麻，不知有几千百个，自一个足印至另一个足印均有绿线贯串，线上绘有箭头，最后写着一行字道：“步法神妙，保身避敌，待积内力，再取敌命。”\n",
|
||||
"\n",
|
||||
"段誉心道：“神仙姊姊所遗的步法，必定精妙之极，遇到强敌时脱身逃走，那就很好，‘再取敌命’也就不必了。”\n",
|
||||
"卷好帛卷，对之作了两个揖，珍而重之地揣入怀中，转身对那玉像道：“神仙姊姊，你吩咐我朝午晚三次练功，段誉不敢有违。今后我对人加倍客气，别人不会来打我，我自然也不会去吸他内力。你这套‘凌波微步’我更要用心练熟，眼见不对，立刻溜之大吉，就吸不到他内力了。”至于“杀尽我逍遥派弟子”一节，却想也不敢去想。\n",
|
||||
"\n",
|
||||
"********ChatGLM:凌波微步是一种轻功身法，属于逍遥派独门轻功。它以《易经》中的六十四卦为基础，按照特定顺序踏着卦象方位行进，从第一步到最后一步正好行走一个大圈。凌波微步精妙异常，可以让人内力相助，自身内力颇为深厚之后再练。《天龙八部》第五回中有描述。\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"\n",
|
||||
"res=vearch_db.similarity_search(query, 3)\n",
|
||||
"query = \"你知道凌波微步吗，你知道都有谁会凌波微步?\"\n",
|
||||
"for idx,tmp in enumerate(res): \n",
|
||||
" print(f\"{'#'*20}第{idx+1}段相关文档{'#'*20}\\n\\n{tmp.page_content}\\n\")\n",
|
||||
"\n",
|
||||
"# combine your local knowleadge and query \n",
|
||||
"context = \"\".join([tmp.page_content for tmp in res])\n",
|
||||
"new_query = f\"基于以下信息，尽可能准确的来回答用户的问题。背景信息:\\n {context} \\n 回答用户这个问题:{query}\\n\\n\"\n",
|
||||
"response, history = model.chat(tokenizer, new_query, history=[])\n",
|
||||
"print(f\"********ChatGLM:{response}\\n\")\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Human: 你知道vearch是什么吗?\n",
|
||||
"ChatGLM:是的，我知道 Vearch。Vearch 是一种矩阵分解 technique，用于将矩阵分解为若干个不可约矩阵的乘积。它是由 Linus Torvalds 开发的，旨在提高 Linux 内核中矩阵操作的性能。\n",
|
||||
"\n",
|
||||
"Vearch 可以通过使用特殊的操作来对矩阵进行操作，从而避免了使用昂贵的矩阵操作库。它也被广泛用于其他操作系统中，如 FreeBSD 和 Solaris。\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Batches: 100%|██████████| 1/1 [00:00<00:00, 31.59it/s]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"['04bc84fff5074b7b8990441e92e6df07', 'e221906153bb4e03bc7095dadea144de', '126034ba51934093920d8732860f340b']\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"['04bc84fff5074b7b8990441e92e6df07',\n",
|
||||
" 'e221906153bb4e03bc7095dadea144de',\n",
|
||||
" '126034ba51934093920d8732860f340b']"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"query = \"你知道vearch是什么吗?\"\n",
|
||||
"response, history = model.chat(tokenizer, query, history=history)\n",
|
||||
"print(f\"Human: {query}\\nChatGLM:{response}\\n\")\n",
|
||||
"\n",
|
||||
"\n",
|
||||
"vearch_info = [\"Vearch 是一款存储大语言模型数据的向量数据库，用于存储和快速搜索模型embedding后的向量，可用于基于个人知识库的大模型应用\",\n",
|
||||
" \"Vearch 支持OpenAI, Llama, ChatGLM等模型，以及LangChain库\",\n",
|
||||
" \"vearch 是基于C语言,go语言开发的，并提供python接口，可以直接通过pip安装\"]\n",
|
||||
"vearch_source=[{'source': '/data/zhx/zhx/langchain-ChatGLM_new/knowledge_base/tlbb/three_body.txt'},{'source': '/data/zhx/zhx/langchain-ChatGLM_new/knowledge_base/tlbb/three_body.txt'},{'source': '/data/zhx/zhx/langchain-ChatGLM_new/knowledge_base/tlbb/three_body.txt'}]\n",
|
||||
"vearch_db.add_texts(vearch_info,vearch_source)\n",
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"Batches: 100%|██████████| 1/1 [00:00<00:00, 25.57it/s]\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"####################第1段相关文档####################\n",
|
||||
"\n",
|
||||
"Vearch 是一款存储大语言模型数据的向量数据库，用于存储和快速搜索模型embedding后的向量，可用于基于个人知识库的大模型应用\n",
|
||||
"\n",
|
||||
"####################第2段相关文档####################\n",
|
||||
"\n",
|
||||
"Vearch 支持OpenAI, Llama, ChatGLM等模型，以及LangChain库\n",
|
||||
"\n",
|
||||
"####################第3段相关文档####################\n",
|
||||
"\n",
|
||||
"vearch 是基于C语言,go语言开发的，并提供python接口，可以直接通过pip安装\n",
|
||||
"\n",
|
||||
"***************ChatGLM:是的，Varch是一个向量数据库，旨在存储和快速搜索模型embedding后的向量。它支持OpenAI、Llama和ChatGLM等模型，并可以直接通过pip安装。Varch是一个基于C语言和Go语言开发的项目，并提供了Python接口。\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"query3 = \"你知道vearch是什么吗?\"\n",
|
||||
"res1 = vearch_db.similarity_search(query3, 3)\n",
|
||||
"for idx,tmp in enumerate(res1): \n",
|
||||
" print(f\"{'#'*20}第{idx+1}段相关文档{'#'*20}\\n\\n{tmp.page_content}\\n\")\n",
|
||||
"\n",
|
||||
"context1 = \"\".join([tmp.page_content for tmp in res1])\n",
|
||||
"new_query1 = f\"基于以下信息，尽可能准确的来回答用户的问题。背景信息:\\n {context1} \\n 回答用户这个问题:{query3}\\n\\n\"\n",
|
||||
"response, history = model.chat(tokenizer, new_query1, history=[])\n",
|
||||
"\n",
|
||||
"print(f\"***************ChatGLM:{response}\\n\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"delete docid True\n",
|
||||
"Human: 你知道vearch是什么吗?\n",
|
||||
"ChatGLM:Vearch是一种高分子化合物,也称为聚合物、高分子材料或合成材料。它是由重复单元组成的大型聚合物,通常由一些重复单元组成,这些单元在聚合过程中结合在一起形成一个连续的高分子链。\n",
|
||||
"\n",
|
||||
"Vearch具有许多独特的性质,例如高强度、高刚性、耐磨、耐腐蚀、耐高温等。它们通常用于制造各种应用,例如塑料制品、橡胶、纤维、建筑材料等。\n",
|
||||
"\n",
|
||||
"after delete docid to query again: {}\n",
|
||||
"get existed docid {'7aae36236f784105a0004d8ff3c7c3ad': Document(page_content='《天龙八部》第二回 玉壁月华明\\n\\n再展帛卷，长卷上源源皆是裸女画像，或立或卧，或现前胸，或见后背。人像的面容都是一般，但或喜或愁，或含情凝眸，或轻嗔薄怒，神情各异。一共有三十六幅图像，每幅像上均有颜色细线，注明穴道部位及练功法诀。\\n\\n帛卷尽处题着“凌波微步”四字，其后绘的是无数足印，注明“妇妹”、“无妄”等等字样，尽是《易经》中的方位。段誉前几日还正全心全意地钻研《易经》，一见到这些名称，登时精神大振，便似遇到故交良友一般。只见足印密密麻麻，不知有几千百个，自一个足印至另一个足印均有绿线贯串，线上绘有箭头，最后写着一行字道：“步法神妙，保身避敌，待积内力，再取敌命。”\\n\\n段誉心道：“神仙姊姊所遗的步法，必定精妙之极，遇到强敌时脱身逃走，那就很好，‘再取敌命’也就不必了。”\\n卷好帛卷，对之作了两个揖，珍而重之地揣入怀中，转身对那玉像道：“神仙姊姊，你吩咐我朝午晚三次练功，段誉不敢有违。今后我对人加倍客气，别人不会来打我，我自然也不会去吸他内力。你这套‘凌波微步’我更要用心练熟，眼见不对，立刻溜之大吉，就吸不到他内力了。”至于“杀尽我逍遥派弟子”一节，却想也不敢去想。', metadata={'source': '/data/zhx/zhx/langchain-ChatGLM_new/knowledge_base/天龙八部/lingboweibu.txt'}), '7e495d4e5962497db2080e84d52e75ed': Document(page_content='《天龙八部》第五回 微步縠纹生\\n\\n卷轴中此外诸种经脉修习之法甚多，皆是取人内力的法门，段誉虽自语宽解，总觉习之有违本性，单是贪多务得，便非好事，当下暂不理会。\\n\\n卷到卷轴末端，又见到了“凌波微步”那四字，登时便想起《洛神赋》中那些句子来：“凌波微步，罗袜生尘……转眄流精，光润玉颜。含辞未吐，气若幽兰。华容婀娜，令我忘餐。”曹子建那些千古名句，在脑海中缓缓流过：“秾纤得衷，修短合度，肩若削成，腰如约素。延颈秀项，皓质呈露。芳泽无加，铅华弗御。云髻峨峨，修眉连娟。丹唇外朗，皓齿内鲜。明眸善睐，靥辅承权。瑰姿艳逸，仪静体闲。柔情绰态，媚于语言……”这些句子用在木婉清身上，“这话倒也有理”；但如用之于神仙姊姊，只怕更为适合。想到神仙姊姊的姿容体态，“皎若太阳升朝霞，灼若芙蓉出绿波”，但觉依她吩咐行事，实为人生至乐，心想：“我先来练这‘凌波微步’，此乃逃命之妙法，非害人之手段也，练之有百利而无一害。”', metadata={'source': '/data/zhx/zhx/langchain-ChatGLM_new/knowledge_base/天龙八部/lingboweibu.txt'})}\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"##delete and get function need to maintian docids \n",
|
||||
"##your docid\n",
|
||||
"res_d=vearch_db.delete(['04bc84fff5074b7b8990441e92e6df07', 'e221906153bb4e03bc7095dadea144de', '126034ba51934093920d8732860f340b'])\n",
|
||||
"print(\"delete docid\",res_d)\n",
|
||||
"query = \"你知道vearch是什么吗?\"\n",
|
||||
"response, history = model.chat(tokenizer, query, history=[])\n",
|
||||
"print(f\"Human: {query}\\nChatGLM:{response}\\n\")\n",
|
||||
"get_id_doc=vearch_db.get(['04bc84fff5074b7b8990441e92e6df07'])\n",
|
||||
"print(\"after delete docid to query again:\",get_id_doc)\n",
|
||||
"get_delet_doc=vearch_db.get(['7aae36236f784105a0004d8ff3c7c3ad', '7e495d4e5962497db2080e84d52e75ed'])\n",
|
||||
"print(\"get existed docid\",get_delet_doc)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3.10.12 ('langchainGLM6B')",
|
||||
"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": "3.10.12"
|
||||
},
|
||||
"orig_nbformat": 4,
|
||||
"vscode": {
|
||||
"interpreter": {
|
||||
"hash": "1fd24e7ef183310e43cbf656d21568350c6a30580b6df7fe3b34654b3770f74d"
|
||||
}
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 2
|
||||
}
|
||||
@@ -141,7 +141,7 @@
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.10.1"
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
|
||||
@@ -1,472 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "13afcae7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Redis self-querying \n",
|
||||
"\n",
|
||||
">[Redis](https://redis.com) is an open-source key-value store that can be used as a cache, message broker, database, vector database and more.\n",
|
||||
"\n",
|
||||
"In the notebook we'll demo the `SelfQueryRetriever` wrapped around a Redis vector store. "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "68e75fb9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Creating a Redis vector store\n",
|
||||
"First we'll want to create a Redis vector store and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
|
||||
"\n",
|
||||
"**Note:** The self-query retriever requires you to have `lark` installed (`pip install lark`) along with integration-specific requirements."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "63a8af5b",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# !pip install redis redisvl openai tiktoken lark"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "83811610-7df3-4ede-b268-68a6a83ba9e2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We want to use `OpenAIEmbeddings` so we have to get the OpenAI API Key."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "dd01b61b-7d32-4a55-85d6-b2d2d4f18840",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "cb4a5787",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.schema import Document\n",
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.vectorstores import Redis\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "bcbe04d9",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docs = [\n",
|
||||
" Document(\n",
|
||||
" page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n",
|
||||
" metadata={\"year\": 1993, \"rating\": 7.7, \"director\": \"Steven Spielberg\", \"genre\": \"science fiction\"},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n",
|
||||
" metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"genre\": \"science fiction\", \"rating\": 8.2},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n",
|
||||
" metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"genre\": \"science fiction\", \"rating\": 8.6},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
|
||||
" metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"genre\": \"drama\", \"rating\": 8.3},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"Toys come alive and have a blast doing so\",\n",
|
||||
" metadata={\"year\": 1995, \"director\": \"John Lasseter\", \"genre\": \"animated\", \"rating\": 9.1,},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n",
|
||||
" metadata={\n",
|
||||
" \"year\": 1979,\n",
|
||||
" \"rating\": 9.9,\n",
|
||||
" \"director\": \"Andrei Tarkovsky\",\n",
|
||||
" \"genre\": \"science fiction\",\n",
|
||||
" },\n",
|
||||
" ),\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "393aff3b",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"`index_schema` does not match generated metadata schema.\n",
|
||||
"If you meant to manually override the schema, please ignore this message.\n",
|
||||
"index_schema: {'tag': [{'name': 'genre'}], 'text': [{'name': 'director'}], 'numeric': [{'name': 'year'}, {'name': 'rating'}]}\n",
|
||||
"generated_schema: {'text': [{'name': 'director'}, {'name': 'genre'}], 'numeric': [{'name': 'year'}, {'name': 'rating'}], 'tag': []}\n",
|
||||
"\n"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"index_schema = {\n",
|
||||
" \"tag\": [{\"name\": \"genre\"}],\n",
|
||||
" \"text\": [{\"name\": \"director\"}],\n",
|
||||
" \"numeric\": [{\"name\": \"year\"}, {\"name\": \"rating\"}],\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"vectorstore = Redis.from_documents(\n",
|
||||
" docs, \n",
|
||||
" embeddings, \n",
|
||||
" redis_url=\"redis://localhost:6379\",\n",
|
||||
" index_name=\"movie_reviews\",\n",
|
||||
" index_schema=index_schema,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5ecaab6d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Creating our self-querying retriever\n",
|
||||
"Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "86e34dbf",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
|
||||
"from langchain.chains.query_constructor.base import AttributeInfo\n",
|
||||
"\n",
|
||||
"metadata_field_info = [\n",
|
||||
" AttributeInfo(\n",
|
||||
" name=\"genre\",\n",
|
||||
" description=\"The genre of the movie\",\n",
|
||||
" type=\"string or list[string]\",\n",
|
||||
" ),\n",
|
||||
" AttributeInfo(\n",
|
||||
" name=\"year\",\n",
|
||||
" description=\"The year the movie was released\",\n",
|
||||
" type=\"integer\",\n",
|
||||
" ),\n",
|
||||
" AttributeInfo(\n",
|
||||
" name=\"director\",\n",
|
||||
" description=\"The name of the movie director\",\n",
|
||||
" type=\"string\",\n",
|
||||
" ),\n",
|
||||
" AttributeInfo(\n",
|
||||
" name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n",
|
||||
" ),\n",
|
||||
"]\n",
|
||||
"document_content_description = \"Brief summary of a movie\"\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "ea1126cb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"retriever = SelfQueryRetriever.from_llm(\n",
|
||||
" llm, \n",
|
||||
" vectorstore, \n",
|
||||
" document_content_description, \n",
|
||||
" metadata_field_info, \n",
|
||||
" verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ea9df8d4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Testing it out\n",
|
||||
"And now we can try actually using our retriever!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "38a126e9",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stderr",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"/Users/bagatur/langchain/libs/langchain/langchain/chains/llm.py:278: UserWarning: The predict_and_parse method is deprecated, instead pass an output parser directly to LLMChain.\n",
|
||||
" warnings.warn(\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query='dinosaur' filter=None limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'id': 'doc:movie_reviews:7b5481d753bc4135851b66fa61def7fb', 'director': 'Steven Spielberg', 'genre': 'science fiction', 'year': '1993', 'rating': '7.7'}),\n",
|
||||
" Document(page_content='Toys come alive and have a blast doing so', metadata={'id': 'doc:movie_reviews:9e4e84daa0374941a6aa4274e9bbb607', 'director': 'John Lasseter', 'genre': 'animated', 'year': '1995', 'rating': '9.1'}),\n",
|
||||
" Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'id': 'doc:movie_reviews:2cc66f38bfbd438eb3a045d90a1a4088', 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'year': '1979', 'rating': '9.9'}),\n",
|
||||
" Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'id': 'doc:movie_reviews:edf567b1d5334e02b2a4c692d853c80c', 'director': 'Satoshi Kon', 'genre': 'science fiction', 'year': '2006', 'rating': '8.6'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example only specifies a relevant query\n",
|
||||
"retriever.get_relevant_documents(\"What are some movies about dinosaurs\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "fc3f1e6e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.4) limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Toys come alive and have a blast doing so', metadata={'id': 'doc:movie_reviews:9e4e84daa0374941a6aa4274e9bbb607', 'director': 'John Lasseter', 'genre': 'animated', 'year': '1995', 'rating': '9.1'}),\n",
|
||||
" Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'id': 'doc:movie_reviews:2cc66f38bfbd438eb3a045d90a1a4088', 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'year': '1979', 'rating': '9.9'}),\n",
|
||||
" Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'id': 'doc:movie_reviews:edf567b1d5334e02b2a4c692d853c80c', 'director': 'Satoshi Kon', 'genre': 'science fiction', 'year': '2006', 'rating': '8.6'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example only specifies a filter\n",
|
||||
"retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.4\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "b19d4da0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'id': 'doc:movie_reviews:bb899807b93c442083fd45e75a4779d5', 'director': 'Greta Gerwig', 'genre': 'drama', 'year': '2019', 'rating': '8.3'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 10,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example specifies a query and a filter\n",
|
||||
"retriever.get_relevant_documents(\"Has Greta Gerwig directed any movies about women\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "f900e40e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.CONTAIN: 'contain'>, attribute='genre', value='science fiction')]) limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'id': 'doc:movie_reviews:2cc66f38bfbd438eb3a045d90a1a4088', 'director': 'Andrei Tarkovsky', 'genre': 'science fiction', 'year': '1979', 'rating': '9.9'}),\n",
|
||||
" Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'id': 'doc:movie_reviews:edf567b1d5334e02b2a4c692d853c80c', 'director': 'Satoshi Kon', 'genre': 'science fiction', 'year': '2006', 'rating': '8.6'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example specifies a composite filter\n",
|
||||
"retriever.get_relevant_documents(\n",
|
||||
" \"What's a highly rated (above 8.5) science fiction film?\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 12,
|
||||
"id": "12a51522",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LT: 'lt'>, attribute='year', value=2005), Comparison(comparator=<Comparator.CONTAIN: 'contain'>, attribute='genre', value='animated')]) limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Toys come alive and have a blast doing so', metadata={'id': 'doc:movie_reviews:9e4e84daa0374941a6aa4274e9bbb607', 'director': 'John Lasseter', 'genre': 'animated', 'year': '1995', 'rating': '9.1'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 12,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example specifies a query and composite filter\n",
|
||||
"retriever.get_relevant_documents(\n",
|
||||
" \"What's a movie after 1990 but before 2005 that's all about toys, and preferably is animated\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Filter k\n",
|
||||
"\n",
|
||||
"We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
|
||||
"\n",
|
||||
"We can do this by passing `enable_limit=True` to the constructor."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "bff36b88-b506-4877-9c63-e5a1a8d78e64",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"retriever = SelfQueryRetriever.from_llm(\n",
|
||||
" llm,\n",
|
||||
" vectorstore,\n",
|
||||
" document_content_description,\n",
|
||||
" metadata_field_info,\n",
|
||||
" enable_limit=True,\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 14,
|
||||
"id": "2758d229-4f97-499c-819f-888acaf8ee10",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query='dinosaur' filter=None limit=2\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'id': 'doc:movie_reviews:7b5481d753bc4135851b66fa61def7fb', 'director': 'Steven Spielberg', 'genre': 'science fiction', 'year': '1993', 'rating': '7.7'}),\n",
|
||||
" Document(page_content='Toys come alive and have a blast doing so', metadata={'id': 'doc:movie_reviews:9e4e84daa0374941a6aa4274e9bbb607', 'director': 'John Lasseter', 'genre': 'animated', 'year': '1995', 'rating': '9.1'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 14,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example only specifies a relevant query\n",
|
||||
"retriever.get_relevant_documents(\"what are two movies about dinosaurs\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "poetry-venv",
|
||||
"language": "python",
|
||||
"name": "poetry-venv"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.1"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -1,587 +0,0 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "13afcae7",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Supabase Vector self-querying \n",
|
||||
"\n",
|
||||
">[Supabase](https://supabase.com/docs) is an open source `Firebase` alternative. \n",
|
||||
"> `Supabase` is built on top of `PostgreSQL`, which offers strong `SQL` \n",
|
||||
"> querying capabilities and enables a simple interface with already-existing tools and frameworks.\n",
|
||||
"\n",
|
||||
">[PostgreSQL](https://en.wikipedia.org/wiki/PostgreSQL) also known as `Postgres`,\n",
|
||||
"> is a free and open-source relational database management system (RDBMS) \n",
|
||||
"> emphasizing extensibility and `SQL` compliance.\n",
|
||||
"\n",
|
||||
"In the notebook we'll demo the `SelfQueryRetriever` wrapped around a Supabase vector store.\n",
|
||||
"\n",
|
||||
"Specifically we will:\n",
|
||||
"1. Create a Supabase database\n",
|
||||
"2. Enable the `pgvector` extension\n",
|
||||
"3. Create a `documents` table and `match_documents` function that will be used by `SupabaseVectorStore`\n",
|
||||
"4. Load sample documents into the vector store (database table)\n",
|
||||
"5. Build and test a self-querying retriever"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "347935ad",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Setup Supabase Database\n",
|
||||
"\n",
|
||||
"1. Head over to https://database.new to provision your Supabase database.\n",
|
||||
"2. In the studio, jump to the [SQL editor](https://supabase.com/dashboard/project/_/sql/new) and run the following script to enable `pgvector` and setup your database as a vector store:\n",
|
||||
" ```sql\n",
|
||||
" -- Enable the pgvector extension to work with embedding vectors\n",
|
||||
" create extension if not exists vector;\n",
|
||||
"\n",
|
||||
" -- Create a table to store your documents\n",
|
||||
" create table\n",
|
||||
" documents (\n",
|
||||
" id uuid primary key,\n",
|
||||
" content text, -- corresponds to Document.pageContent\n",
|
||||
" metadata jsonb, -- corresponds to Document.metadata\n",
|
||||
" embedding vector (1536) -- 1536 works for OpenAI embeddings, change if needed\n",
|
||||
" );\n",
|
||||
"\n",
|
||||
" -- Create a function to search for documents\n",
|
||||
" create function match_documents (\n",
|
||||
" query_embedding vector (1536),\n",
|
||||
" filter jsonb default '{}'\n",
|
||||
" ) returns table (\n",
|
||||
" id uuid,\n",
|
||||
" content text,\n",
|
||||
" metadata jsonb,\n",
|
||||
" similarity float\n",
|
||||
" ) language plpgsql as $$\n",
|
||||
" #variable_conflict use_column\n",
|
||||
" begin\n",
|
||||
" return query\n",
|
||||
" select\n",
|
||||
" id,\n",
|
||||
" content,\n",
|
||||
" metadata,\n",
|
||||
" 1 - (documents.embedding <=> query_embedding) as similarity\n",
|
||||
" from documents\n",
|
||||
" where metadata @> filter\n",
|
||||
" order by documents.embedding <=> query_embedding;\n",
|
||||
" end;\n",
|
||||
" $$;\n",
|
||||
" ```"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "68e75fb9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Creating a Supabase vector store\n",
|
||||
"Next we'll want to create a Supabase vector store and seed it with some data. We've created a small demo set of documents that contain summaries of movies.\n",
|
||||
"\n",
|
||||
"Be sure to install the latest version of `langchain`:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "78546fd7",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install langchain"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "e06df198",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The self-query retriever requires you to have `lark` installed:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "63a8af5b",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install lark"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "114f768f",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"We also need the `openai` and `supabase` packages:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "434ae558",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install openai"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "22431060-52c4-48a7-a97b-9f542b8b0928",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install supabase==1.0.0"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "83811610-7df3-4ede-b268-68a6a83ba9e2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Since we are using `SupabaseVectorStore` and `OpenAIEmbeddings`, we have to load their API keys.\n",
|
||||
"\n",
|
||||
"- To find your `SUPABASE_URL` and `SUPABASE_SERVICE_KEY`, head to your Supabase project's [API settings](https://supabase.com/dashboard/project/_/settings/api).\n",
|
||||
" - `SUPABASE_URL` corresponds to the Project URL\n",
|
||||
" - `SUPABASE_SERVICE_KEY` corresponds to the `service_role` API key\n",
|
||||
"\n",
|
||||
"- To get your `OPENAI_API_KEY`, navigate to [API keys](https://platform.openai.com/account/api-keys) on your OpenAI account and create a new secret key."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 1,
|
||||
"id": "dd01b61b-7d32-4a55-85d6-b2d2d4f18840",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"import getpass\n",
|
||||
"\n",
|
||||
"os.environ[\"SUPABASE_URL\"] = getpass.getpass(\"Supabase URL:\")\n",
|
||||
"os.environ[\"SUPABASE_SERVICE_KEY\"] = getpass.getpass(\"Supabase Service Key:\")\n",
|
||||
"os.environ[\"OPENAI_API_KEY\"] = getpass.getpass(\"OpenAI API Key:\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "3aaf5075",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"_Optional:_ If you're storing your Supabase and OpenAI API keys in a `.env` file, you can load them with [`dotenv`](https://github.com/theskumar/python-dotenv)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e0089221",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"%pip install python-dotenv"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3d56c5ef",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from dotenv import load_dotenv\n",
|
||||
"\n",
|
||||
"load_dotenv()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "f6dd9aef",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"First we'll create a Supabase client and instantiate a OpenAI embeddings class."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "cb4a5787",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import os\n",
|
||||
"from supabase.client import Client, create_client\n",
|
||||
"from langchain.schema import Document\n",
|
||||
"from langchain.embeddings.openai import OpenAIEmbeddings\n",
|
||||
"from langchain.vectorstores import SupabaseVectorStore\n",
|
||||
"\n",
|
||||
"supabase_url = os.environ.get(\"SUPABASE_URL\")\n",
|
||||
"supabase_key = os.environ.get(\"SUPABASE_SERVICE_KEY\")\n",
|
||||
"supabase: Client = create_client(supabase_url, supabase_key)\n",
|
||||
"\n",
|
||||
"embeddings = OpenAIEmbeddings()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "0fca9b0b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Next let's create our documents."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 3,
|
||||
"id": "bcbe04d9",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"docs = [\n",
|
||||
" Document(\n",
|
||||
" page_content=\"A bunch of scientists bring back dinosaurs and mayhem breaks loose\",\n",
|
||||
" metadata={\"year\": 1993, \"rating\": 7.7, \"genre\": \"science fiction\"},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"Leo DiCaprio gets lost in a dream within a dream within a dream within a ...\",\n",
|
||||
" metadata={\"year\": 2010, \"director\": \"Christopher Nolan\", \"rating\": 8.2},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea\",\n",
|
||||
" metadata={\"year\": 2006, \"director\": \"Satoshi Kon\", \"rating\": 8.6},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"A bunch of normal-sized women are supremely wholesome and some men pine after them\",\n",
|
||||
" metadata={\"year\": 2019, \"director\": \"Greta Gerwig\", \"rating\": 8.3},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"Toys come alive and have a blast doing so\",\n",
|
||||
" metadata={\"year\": 1995, \"genre\": \"animated\"},\n",
|
||||
" ),\n",
|
||||
" Document(\n",
|
||||
" page_content=\"Three men walk into the Zone, three men walk out of the Zone\",\n",
|
||||
" metadata={\n",
|
||||
" \"year\": 1979,\n",
|
||||
" \"rating\": 9.9,\n",
|
||||
" \"director\": \"Andrei Tarkovsky\",\n",
|
||||
" \"genre\": \"science fiction\",\n",
|
||||
" \"rating\": 9.9,\n",
|
||||
" },\n",
|
||||
" ),\n",
|
||||
"]\n",
|
||||
"\n",
|
||||
"vectorstore = SupabaseVectorStore.from_documents(docs, embeddings, client=supabase, table_name=\"documents\", query_name=\"match_documents\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "5ecaab6d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Creating our self-querying retriever\n",
|
||||
"Now we can instantiate our retriever. To do this we'll need to provide some information upfront about the metadata fields that our documents support and a short description of the document contents."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "86e34dbf",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"from langchain.llms import OpenAI\n",
|
||||
"from langchain.retrievers.self_query.base import SelfQueryRetriever\n",
|
||||
"from langchain.chains.query_constructor.base import AttributeInfo\n",
|
||||
"\n",
|
||||
"metadata_field_info = [\n",
|
||||
" AttributeInfo(\n",
|
||||
" name=\"genre\",\n",
|
||||
" description=\"The genre of the movie\",\n",
|
||||
" type=\"string or list[string]\",\n",
|
||||
" ),\n",
|
||||
" AttributeInfo(\n",
|
||||
" name=\"year\",\n",
|
||||
" description=\"The year the movie was released\",\n",
|
||||
" type=\"integer\",\n",
|
||||
" ),\n",
|
||||
" AttributeInfo(\n",
|
||||
" name=\"director\",\n",
|
||||
" description=\"The name of the movie director\",\n",
|
||||
" type=\"string\",\n",
|
||||
" ),\n",
|
||||
" AttributeInfo(\n",
|
||||
" name=\"rating\", description=\"A 1-10 rating for the movie\", type=\"float\"\n",
|
||||
" ),\n",
|
||||
"]\n",
|
||||
"document_content_description = \"Brief summary of a movie\"\n",
|
||||
"llm = OpenAI(temperature=0)\n",
|
||||
"retriever = SelfQueryRetriever.from_llm(\n",
|
||||
" llm, vectorstore, document_content_description, metadata_field_info, verbose=True\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "ea9df8d4",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Testing it out\n",
|
||||
"And now we can try actually using our retriever!"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "38a126e9",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query='dinosaur' filter=None limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7}),\n",
|
||||
" Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'}),\n",
|
||||
" Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),\n",
|
||||
" Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 5,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example only specifies a relevant query\n",
|
||||
"retriever.get_relevant_documents(\"What are some movies about dinosaurs\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "fc3f1e6e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query=' ' filter=Comparison(comparator=<Comparator.GT: 'gt'>, attribute='rating', value=8.5) limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'}),\n",
|
||||
" Document(page_content='A psychologist / detective gets lost in a series of dreams within dreams within dreams and Inception reused the idea', metadata={'year': 2006, 'rating': 8.6, 'director': 'Satoshi Kon'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 7,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example only specifies a filter\n",
|
||||
"retriever.get_relevant_documents(\"I want to watch a movie rated higher than 8.5\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "b19d4da0",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query='women' filter=Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='director', value='Greta Gerwig') limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='A bunch of normal-sized women are supremely wholesome and some men pine after them', metadata={'year': 2019, 'rating': 8.3, 'director': 'Greta Gerwig'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example specifies a query and a filter\n",
|
||||
"retriever.get_relevant_documents(\"Has Greta Gerwig directed any movies about women?\")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "f900e40e",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query=' ' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GTE: 'gte'>, attribute='rating', value=8.5), Comparison(comparator=<Comparator.EQ: 'eq'>, attribute='genre', value='science fiction')]) limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Three men walk into the Zone, three men walk out of the Zone', metadata={'year': 1979, 'genre': 'science fiction', 'rating': 9.9, 'director': 'Andrei Tarkovsky'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 8,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example specifies a composite filter\n",
|
||||
"retriever.get_relevant_documents(\n",
|
||||
" \"What's a highly rated (above 8.5) science fiction film?\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "12a51522",
|
||||
"metadata": {},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query='toys' filter=Operation(operator=<Operator.AND: 'and'>, arguments=[Comparison(comparator=<Comparator.GT: 'gt'>, attribute='year', value=1990), Comparison(comparator=<Comparator.LTE: 'lte'>, attribute='year', value=2005), Comparison(comparator=<Comparator.LIKE: 'like'>, attribute='genre', value='animated')]) limit=None\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 9,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example specifies a query and composite filter\n",
|
||||
"retriever.get_relevant_documents(\n",
|
||||
" \"What's a movie after 1990 but before (or on) 2005 that's all about toys, and preferably is animated\"\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "39bd1de1-b9fe-4a98-89da-58d8a7a6ae51",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Filter k\n",
|
||||
"\n",
|
||||
"We can also use the self query retriever to specify `k`: the number of documents to fetch.\n",
|
||||
"\n",
|
||||
"We can do this by passing `enable_limit=True` to the constructor."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "bff36b88-b506-4877-9c63-e5a1a8d78e64",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"retriever = SelfQueryRetriever.from_llm(\n",
|
||||
" llm,\n",
|
||||
" vectorstore,\n",
|
||||
" document_content_description,\n",
|
||||
" metadata_field_info,\n",
|
||||
" enable_limit=True,\n",
|
||||
" verbose=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "2758d229-4f97-499c-819f-888acaf8ee10",
|
||||
"metadata": {
|
||||
"tags": []
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"name": "stdout",
|
||||
"output_type": "stream",
|
||||
"text": [
|
||||
"query='dinosaur' filter=None limit=2\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"data": {
|
||||
"text/plain": [
|
||||
"[Document(page_content='A bunch of scientists bring back dinosaurs and mayhem breaks loose', metadata={'year': 1993, 'genre': 'science fiction', 'rating': 7.7}),\n",
|
||||
" Document(page_content='Toys come alive and have a blast doing so', metadata={'year': 1995, 'genre': 'animated'})]"
|
||||
]
|
||||
},
|
||||
"execution_count": 11,
|
||||
"metadata": {},
|
||||
"output_type": "execute_result"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"# This example only specifies a relevant query\n",
|
||||
"retriever.get_relevant_documents(\"what are two movies about dinosaurs\")"
|
||||
]
|
||||
}
|
||||
],
|
||||
"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": "3.10.12"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
@@ -7,7 +7,7 @@
|
||||
"source": [
|
||||
"# Diffbot Graph Transformer\n",
|
||||
"\n",
|
||||
"[](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/more/graph/diffbot_graphtransformer.ipynb)\n",
|
||||
"[](https://colab.research.google.com/github/langchain-ai/langchain/blob/master/docs/extras/use_cases/more/graph/diffbot_transformer.ipynb)\n",
|
||||
"\n",
|
||||
"## Use case\n",
|
||||
"\n",
|
||||
@@ -77,7 +77,7 @@
|
||||
"id": "5e3b894a-e3ee-46c7-8116-f8377f8f0159",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"This code fetches Wikipedia articles about \"Warren Buffett\" and then uses `DiffbotGraphTransformer` to extract entities and relationships.\n",
|
||||
"This code fetches Wikipedia articles about \"Baldur's Gate 3\" and then uses `DiffbotGraphTransformer` to extract entities and relationships.\n",
|
||||
"The `DiffbotGraphTransformer` outputs a structured data `GraphDocument`, which can be used to populate a graph database.\n",
|
||||
"Note that text chunking is avoided due to Diffbot's [character limit per API request](https://docs.diffbot.com/reference/introduction-to-natural-language-api)."
|
||||
]
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,15 +0,0 @@
|
||||
# Vearch
|
||||
|
||||
Vearch is a scalable distributed system for efficient similarity search of deep learning vectors.
|
||||
|
||||
# Installation and Setup
|
||||
|
||||
Vearch Python SDK enables vearch to use locally. Vearch python sdk can be installed easily by pip install vearch.
|
||||
|
||||
# Vectorstore
|
||||
|
||||
Vearch also can used as vectorstore. Most detalis in [this notebook](docs/modules/indexes/vectorstores/examples/vearch.ipynb)
|
||||
|
||||
```python
|
||||
from langchain.vectorstores import Vearch
|
||||
```
|
||||
@@ -1,5 +1,4 @@
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import Optional
|
||||
|
||||
|
||||
class AnonymizerBase(ABC):
|
||||
@@ -9,12 +8,12 @@ class AnonymizerBase(ABC):
|
||||
wrapping the behavior for all methods in a base class.
|
||||
"""
|
||||
|
||||
def anonymize(self, text: str, language: Optional[str] = None) -> str:
|
||||
def anonymize(self, text: str) -> str:
|
||||
"""Anonymize text"""
|
||||
return self._anonymize(text, language)
|
||||
return self._anonymize(text)
|
||||
|
||||
@abstractmethod
|
||||
def _anonymize(self, text: str, language: Optional[str]) -> str:
|
||||
def _anonymize(self, text: str) -> str:
|
||||
"""Abstract method to anonymize text"""
|
||||
|
||||
|
||||
|
||||
@@ -27,8 +27,8 @@ def get_pseudoanonymizer_mapping(seed: Optional[int] = None) -> Dict[str, Callab
|
||||
fake.random_choices(string.ascii_lowercase + string.digits, length=26)
|
||||
),
|
||||
"IP_ADDRESS": lambda _: fake.ipv4_public(),
|
||||
"LOCATION": lambda _: fake.city(),
|
||||
"DATE_TIME": lambda _: fake.date(),
|
||||
"LOCATION": lambda _: fake.address(),
|
||||
"DATE_TIME": lambda _: fake.iso8601(),
|
||||
"NRP": lambda _: str(fake.random_number(digits=8, fix_len=True)),
|
||||
"MEDICAL_LICENSE": lambda _: fake.bothify(text="??######").upper(),
|
||||
"URL": lambda _: fake.url(),
|
||||
|
||||
@@ -24,8 +24,6 @@ from langchain_experimental.data_anonymizer.faker_presidio_mapping import (
|
||||
|
||||
try:
|
||||
from presidio_analyzer import AnalyzerEngine
|
||||
from presidio_analyzer.nlp_engine import NlpEngineProvider
|
||||
|
||||
except ImportError as e:
|
||||
raise ImportError(
|
||||
"Could not import presidio_analyzer, please install with "
|
||||
@@ -46,29 +44,12 @@ if TYPE_CHECKING:
|
||||
from presidio_analyzer import EntityRecognizer, RecognizerResult
|
||||
from presidio_anonymizer.entities import EngineResult
|
||||
|
||||
# Configuring Anonymizer for multiple languages
|
||||
# Detailed description and examples can be found here:
|
||||
# langchain/docs/extras/guides/privacy/multi_language_anonymization.ipynb
|
||||
DEFAULT_LANGUAGES_CONFIG = {
|
||||
# You can also use Stanza or transformers library.
|
||||
# See https://microsoft.github.io/presidio/analyzer/customizing_nlp_models/
|
||||
"nlp_engine_name": "spacy",
|
||||
"models": [
|
||||
{"lang_code": "en", "model_name": "en_core_web_lg"},
|
||||
# {"lang_code": "de", "model_name": "de_core_news_md"},
|
||||
# {"lang_code": "es", "model_name": "es_core_news_md"},
|
||||
# ...
|
||||
# List of available models: https://spacy.io/usage/models
|
||||
],
|
||||
}
|
||||
|
||||
|
||||
class PresidioAnonymizerBase(AnonymizerBase):
|
||||
def __init__(
|
||||
self,
|
||||
analyzed_fields: Optional[List[str]] = None,
|
||||
operators: Optional[Dict[str, OperatorConfig]] = None,
|
||||
languages_config: Dict = DEFAULT_LANGUAGES_CONFIG,
|
||||
faker_seed: Optional[int] = None,
|
||||
):
|
||||
"""
|
||||
@@ -79,11 +60,6 @@ class PresidioAnonymizerBase(AnonymizerBase):
|
||||
Operators allow for custom anonymization of detected PII.
|
||||
Learn more:
|
||||
https://microsoft.github.io/presidio/tutorial/10_simple_anonymization/
|
||||
languages_config: Configuration for the NLP engine.
|
||||
First language in the list will be used as the main language
|
||||
in self.anonymize(...) when no language is specified.
|
||||
Learn more:
|
||||
https://microsoft.github.io/presidio/analyzer/customizing_nlp_models/
|
||||
faker_seed: Seed used to initialize faker.
|
||||
Defaults to None, in which case faker will be seeded randomly
|
||||
and provide random values.
|
||||
@@ -105,15 +81,7 @@ class PresidioAnonymizerBase(AnonymizerBase):
|
||||
).items()
|
||||
}
|
||||
)
|
||||
|
||||
provider = NlpEngineProvider(nlp_configuration=languages_config)
|
||||
nlp_engine = provider.create_engine()
|
||||
|
||||
self.supported_languages = list(nlp_engine.nlp.keys())
|
||||
|
||||
self._analyzer = AnalyzerEngine(
|
||||
supported_languages=self.supported_languages, nlp_engine=nlp_engine
|
||||
)
|
||||
self._analyzer = AnalyzerEngine()
|
||||
self._anonymizer = AnonymizerEngine()
|
||||
|
||||
def add_recognizer(self, recognizer: EntityRecognizer) -> None:
|
||||
@@ -135,31 +103,18 @@ class PresidioAnonymizerBase(AnonymizerBase):
|
||||
|
||||
|
||||
class PresidioAnonymizer(PresidioAnonymizerBase):
|
||||
def _anonymize(self, text: str, language: Optional[str] = None) -> str:
|
||||
def _anonymize(self, text: str) -> str:
|
||||
"""Anonymize text.
|
||||
Each PII entity is replaced with a fake value.
|
||||
Each time fake values will be different, as they are generated randomly.
|
||||
|
||||
Args:
|
||||
text: text to anonymize
|
||||
language: language to use for analysis of PII
|
||||
If None, the first (main) language in the list
|
||||
of languages specified in the configuration will be used.
|
||||
"""
|
||||
if language is None:
|
||||
language = self.supported_languages[0]
|
||||
|
||||
if language not in self.supported_languages:
|
||||
raise ValueError(
|
||||
f"Language '{language}' is not supported. "
|
||||
f"Supported languages are: {self.supported_languages}. "
|
||||
"Change your language configuration file to add more languages."
|
||||
)
|
||||
|
||||
results = self._analyzer.analyze(
|
||||
text,
|
||||
entities=self.analyzed_fields,
|
||||
language=language,
|
||||
language="en",
|
||||
)
|
||||
|
||||
return self._anonymizer.anonymize(
|
||||
@@ -174,10 +129,9 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
|
||||
self,
|
||||
analyzed_fields: Optional[List[str]] = None,
|
||||
operators: Optional[Dict[str, OperatorConfig]] = None,
|
||||
languages_config: Dict = DEFAULT_LANGUAGES_CONFIG,
|
||||
faker_seed: Optional[int] = None,
|
||||
):
|
||||
super().__init__(analyzed_fields, operators, languages_config, faker_seed)
|
||||
super().__init__(analyzed_fields, operators, faker_seed)
|
||||
self._deanonymizer_mapping = DeanonymizerMapping()
|
||||
|
||||
@property
|
||||
@@ -237,7 +191,7 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
|
||||
|
||||
self._deanonymizer_mapping.update(new_deanonymizer_mapping)
|
||||
|
||||
def _anonymize(self, text: str, language: Optional[str] = None) -> str:
|
||||
def _anonymize(self, text: str) -> str:
|
||||
"""Anonymize text.
|
||||
Each PII entity is replaced with a fake value.
|
||||
Each time fake values will be different, as they are generated randomly.
|
||||
@@ -246,24 +200,11 @@ class PresidioReversibleAnonymizer(PresidioAnonymizerBase, ReversibleAnonymizerB
|
||||
|
||||
Args:
|
||||
text: text to anonymize
|
||||
language: language to use for analysis of PII
|
||||
If None, the first (main) language in the list
|
||||
of languages specified in the configuration will be used.
|
||||
"""
|
||||
if language is None:
|
||||
language = self.supported_languages[0]
|
||||
|
||||
if language not in self.supported_languages:
|
||||
raise ValueError(
|
||||
f"Language '{language}' is not supported. "
|
||||
f"Supported languages are: {self.supported_languages}. "
|
||||
"Change your language configuration file to add more languages."
|
||||
)
|
||||
|
||||
analyzer_results = self._analyzer.analyze(
|
||||
text,
|
||||
entities=self.analyzed_fields,
|
||||
language=language,
|
||||
language="en",
|
||||
)
|
||||
|
||||
filtered_analyzer_results = (
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
[tool.poetry]
|
||||
name = "langchain-experimental"
|
||||
version = "0.0.16"
|
||||
version = "0.0.15"
|
||||
description = "Building applications with LLMs through composability"
|
||||
authors = []
|
||||
license = "MIT"
|
||||
|
||||
@@ -7,16 +7,7 @@ import logging
|
||||
import time
|
||||
from abc import abstractmethod
|
||||
from pathlib import Path
|
||||
from typing import (
|
||||
Any,
|
||||
Callable,
|
||||
Dict,
|
||||
List,
|
||||
Optional,
|
||||
Sequence,
|
||||
Tuple,
|
||||
Union,
|
||||
)
|
||||
from typing import Any, Callable, Dict, List, Optional, Sequence, Tuple, Union
|
||||
|
||||
import yaml
|
||||
|
||||
@@ -45,7 +36,6 @@ from langchain.schema import (
|
||||
)
|
||||
from langchain.schema.language_model import BaseLanguageModel
|
||||
from langchain.schema.messages import BaseMessage
|
||||
from langchain.schema.runnable import Runnable
|
||||
from langchain.tools.base import BaseTool
|
||||
from langchain.utilities.asyncio import asyncio_timeout
|
||||
from langchain.utils.input import get_color_mapping
|
||||
@@ -317,71 +307,6 @@ class AgentOutputParser(BaseOutputParser):
|
||||
"""Parse text into agent action/finish."""
|
||||
|
||||
|
||||
class RunnableAgent(BaseSingleActionAgent):
|
||||
"""Agent powered by runnables."""
|
||||
|
||||
runnable: Runnable[dict, Union[AgentAction, AgentFinish]]
|
||||
"""Runnable to call to get agent action."""
|
||||
_input_keys: List[str] = []
|
||||
"""Input keys."""
|
||||
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
@property
|
||||
def input_keys(self) -> List[str]:
|
||||
"""Return the input keys.
|
||||
|
||||
Returns:
|
||||
List of input keys.
|
||||
"""
|
||||
return self._input_keys
|
||||
|
||||
def plan(
|
||||
self,
|
||||
intermediate_steps: List[Tuple[AgentAction, str]],
|
||||
callbacks: Callbacks = None,
|
||||
**kwargs: Any,
|
||||
) -> Union[AgentAction, AgentFinish]:
|
||||
"""Given input, decided what to do.
|
||||
|
||||
Args:
|
||||
intermediate_steps: Steps the LLM has taken to date,
|
||||
along with the observations.
|
||||
callbacks: Callbacks to run.
|
||||
**kwargs: User inputs.
|
||||
|
||||
Returns:
|
||||
Action specifying what tool to use.
|
||||
"""
|
||||
inputs = {**kwargs, **{"intermediate_steps": intermediate_steps}}
|
||||
output = self.runnable.invoke(inputs, config={"callbacks": callbacks})
|
||||
return output
|
||||
|
||||
async def aplan(
|
||||
self,
|
||||
intermediate_steps: List[Tuple[AgentAction, str]],
|
||||
callbacks: Callbacks = None,
|
||||
**kwargs: Any,
|
||||
) -> Union[AgentAction, AgentFinish]:
|
||||
"""Given input, decided what to do.
|
||||
|
||||
Args:
|
||||
intermediate_steps: Steps the LLM has taken to date,
|
||||
along with observations
|
||||
callbacks: Callbacks to run.
|
||||
**kwargs: User inputs.
|
||||
|
||||
Returns:
|
||||
Action specifying what tool to use.
|
||||
"""
|
||||
inputs = {**kwargs, **{"intermediate_steps": intermediate_steps}}
|
||||
output = await self.runnable.ainvoke(inputs, config={"callbacks": callbacks})
|
||||
return output
|
||||
|
||||
|
||||
class LLMSingleActionAgent(BaseSingleActionAgent):
|
||||
"""Base class for single action agents."""
|
||||
|
||||
@@ -800,14 +725,6 @@ s
|
||||
)
|
||||
return values
|
||||
|
||||
@root_validator(pre=True)
|
||||
def validate_runnable_agent(cls, values: Dict) -> Dict:
|
||||
"""Convert runnable to agent if passed in."""
|
||||
agent = values["agent"]
|
||||
if isinstance(agent, Runnable):
|
||||
values["agent"] = RunnableAgent(runnable=agent)
|
||||
return values
|
||||
|
||||
def save(self, file_path: Union[Path, str]) -> None:
|
||||
"""Raise error - saving not supported for Agent Executors."""
|
||||
raise ValueError(
|
||||
|
||||
@@ -1,188 +0,0 @@
|
||||
# flake8: noqa
|
||||
import os
|
||||
import warnings
|
||||
from typing import Any, Dict, List, Optional, Union
|
||||
|
||||
from langchain.callbacks.base import BaseCallbackHandler
|
||||
from langchain.schema import AgentAction, AgentFinish, LLMResult
|
||||
|
||||
|
||||
class DeepEvalCallbackHandler(BaseCallbackHandler):
|
||||
"""Callback Handler that logs into deepeval.
|
||||
|
||||
Args:
|
||||
implementation_name: name of the `implementation` in deepeval
|
||||
metrics: A list of metrics
|
||||
|
||||
Raises:
|
||||
ImportError: if the `deepeval` package is not installed.
|
||||
|
||||
Examples:
|
||||
>>> from langchain.llms import OpenAI
|
||||
>>> from langchain.callbacks import DeepEvalCallbackHandler
|
||||
>>> from deepeval.metrics import AnswerRelevancy
|
||||
>>> metric = AnswerRelevancy(minimum_score=0.3)
|
||||
>>> deepeval_callback = DeepEvalCallbackHandler(
|
||||
... implementation_name="exampleImplementation",
|
||||
... metrics=[metric],
|
||||
... )
|
||||
>>> llm = OpenAI(
|
||||
... temperature=0,
|
||||
... callbacks=[deepeval_callback],
|
||||
... verbose=True,
|
||||
... openai_api_key="API_KEY_HERE",
|
||||
... )
|
||||
>>> llm.generate([
|
||||
... "What is the best evaluation tool out there? (no bias at all)",
|
||||
... ])
|
||||
"Deepeval, no doubt about it."
|
||||
"""
|
||||
|
||||
REPO_URL: str = "https://github.com/confident-ai/deepeval"
|
||||
ISSUES_URL: str = f"{REPO_URL}/issues"
|
||||
BLOG_URL: str = "https://docs.confident-ai.com" # noqa: E501
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
metrics: List[Any],
|
||||
implementation_name: Optional[str] = None,
|
||||
) -> None:
|
||||
"""Initializes the `deepevalCallbackHandler`.
|
||||
|
||||
Args:
|
||||
implementation_name: Name of the implementation you want.
|
||||
metrics: What metrics do you want to track?
|
||||
|
||||
Raises:
|
||||
ImportError: if the `deepeval` package is not installed.
|
||||
ConnectionError: if the connection to deepeval fails.
|
||||
"""
|
||||
|
||||
super().__init__()
|
||||
|
||||
# Import deepeval (not via `import_deepeval` to keep hints in IDEs)
|
||||
try:
|
||||
import deepeval # ignore: F401,I001
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"""To use the deepeval callback manager you need to have the
|
||||
`deepeval` Python package installed. Please install it with
|
||||
`pip install deepeval`"""
|
||||
)
|
||||
|
||||
if os.path.exists(".deepeval"):
|
||||
warnings.warn(
|
||||
"""You are currently not logging anything to the dashboard, we
|
||||
recommend using `deepeval login`."""
|
||||
)
|
||||
|
||||
# Set the deepeval variables
|
||||
self.implementation_name = implementation_name
|
||||
self.metrics = metrics
|
||||
|
||||
warnings.warn(
|
||||
(
|
||||
"The `DeepEvalCallbackHandler` is currently in beta and is subject to"
|
||||
" change based on updates to `langchain`. Please report any issues to"
|
||||
f" {self.ISSUES_URL} as an `integration` issue."
|
||||
),
|
||||
)
|
||||
|
||||
def on_llm_start(
|
||||
self, serialized: Dict[str, Any], prompts: List[str], **kwargs: Any
|
||||
) -> None:
|
||||
"""Store the prompts"""
|
||||
self.prompts = prompts
|
||||
|
||||
def on_llm_new_token(self, token: str, **kwargs: Any) -> None:
|
||||
"""Do nothing when a new token is generated."""
|
||||
pass
|
||||
|
||||
def on_llm_end(self, response: LLMResult, **kwargs: Any) -> None:
|
||||
"""Log records to deepeval when an LLM ends."""
|
||||
from deepeval.metrics.answer_relevancy import AnswerRelevancy
|
||||
from deepeval.metrics.bias_classifier import UnBiasedMetric
|
||||
from deepeval.metrics.metric import Metric
|
||||
from deepeval.metrics.toxic_classifier import NonToxicMetric
|
||||
|
||||
for metric in self.metrics:
|
||||
for i, generation in enumerate(response.generations):
|
||||
# Here, we only measure the first generation's output
|
||||
output = generation[0].text
|
||||
query = self.prompts[i]
|
||||
if isinstance(metric, AnswerRelevancy):
|
||||
result = metric.measure(
|
||||
output=output,
|
||||
query=query,
|
||||
)
|
||||
print(f"Answer Relevancy: {result}")
|
||||
elif isinstance(metric, UnBiasedMetric):
|
||||
score = metric.measure(output)
|
||||
print(f"Bias Score: {score}")
|
||||
elif isinstance(metric, NonToxicMetric):
|
||||
score = metric.measure(output)
|
||||
print(f"Toxic Score: {score}")
|
||||
else:
|
||||
raise ValueError(
|
||||
f"""Metric {metric.__name__} is not supported by deepeval
|
||||
callbacks."""
|
||||
)
|
||||
|
||||
def on_llm_error(
|
||||
self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
|
||||
) -> None:
|
||||
"""Do nothing when LLM outputs an error."""
|
||||
pass
|
||||
|
||||
def on_chain_start(
|
||||
self, serialized: Dict[str, Any], inputs: Dict[str, Any], **kwargs: Any
|
||||
) -> None:
|
||||
"""Do nothing when chain starts"""
|
||||
pass
|
||||
|
||||
def on_chain_end(self, outputs: Dict[str, Any], **kwargs: Any) -> None:
|
||||
"""Do nothing when chain ends."""
|
||||
pass
|
||||
|
||||
def on_chain_error(
|
||||
self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
|
||||
) -> None:
|
||||
"""Do nothing when LLM chain outputs an error."""
|
||||
pass
|
||||
|
||||
def on_tool_start(
|
||||
self,
|
||||
serialized: Dict[str, Any],
|
||||
input_str: str,
|
||||
**kwargs: Any,
|
||||
) -> None:
|
||||
"""Do nothing when tool starts."""
|
||||
pass
|
||||
|
||||
def on_agent_action(self, action: AgentAction, **kwargs: Any) -> Any:
|
||||
"""Do nothing when agent takes a specific action."""
|
||||
pass
|
||||
|
||||
def on_tool_end(
|
||||
self,
|
||||
output: str,
|
||||
observation_prefix: Optional[str] = None,
|
||||
llm_prefix: Optional[str] = None,
|
||||
**kwargs: Any,
|
||||
) -> None:
|
||||
"""Do nothing when tool ends."""
|
||||
pass
|
||||
|
||||
def on_tool_error(
|
||||
self, error: Union[Exception, KeyboardInterrupt], **kwargs: Any
|
||||
) -> None:
|
||||
"""Do nothing when tool outputs an error."""
|
||||
pass
|
||||
|
||||
def on_text(self, text: str, **kwargs: Any) -> None:
|
||||
"""Do nothing"""
|
||||
pass
|
||||
|
||||
def on_agent_finish(self, finish: AgentFinish, **kwargs: Any) -> None:
|
||||
"""Do nothing"""
|
||||
pass
|
||||
@@ -14,70 +14,6 @@ from langchain.schema.output import LLMResult
|
||||
DEFAULT_API_URL = "https://app.llmonitor.com"
|
||||
|
||||
|
||||
def _serialize(obj: Any) -> Union[Dict[str, Any], List[Any], Any]:
|
||||
if hasattr(obj, "to_json"):
|
||||
return obj.to_json()
|
||||
|
||||
if isinstance(obj, dict):
|
||||
return {key: _serialize(value) for key, value in obj.items()}
|
||||
|
||||
if isinstance(obj, list):
|
||||
return [_serialize(element) for element in obj]
|
||||
|
||||
return obj
|
||||
|
||||
|
||||
def _parse_input(raw_input: Any) -> Any:
|
||||
if not raw_input:
|
||||
return None
|
||||
|
||||
if not isinstance(raw_input, dict):
|
||||
return _serialize(raw_input)
|
||||
|
||||
input_value = raw_input.get("input")
|
||||
inputs_value = raw_input.get("inputs")
|
||||
question_value = raw_input.get("question")
|
||||
query_value = raw_input.get("query")
|
||||
|
||||
if input_value:
|
||||
return input_value
|
||||
if inputs_value:
|
||||
return inputs_value
|
||||
if question_value:
|
||||
return question_value
|
||||
if query_value:
|
||||
return query_value
|
||||
|
||||
return _serialize(raw_input)
|
||||
|
||||
|
||||
def _parse_output(raw_output: dict) -> Any:
|
||||
if not raw_output:
|
||||
return None
|
||||
|
||||
if not isinstance(raw_output, dict):
|
||||
return _serialize(raw_output)
|
||||
|
||||
text_value = raw_output.get("text")
|
||||
output_value = raw_output.get("output")
|
||||
output_text_value = raw_output.get("output_text")
|
||||
answer_value = raw_output.get("answer")
|
||||
result_value = raw_output.get("result")
|
||||
|
||||
if text_value:
|
||||
return text_value
|
||||
if answer_value:
|
||||
return answer_value
|
||||
if output_value:
|
||||
return output_value
|
||||
if output_text_value:
|
||||
return output_text_value
|
||||
if result_value:
|
||||
return result_value
|
||||
|
||||
return _serialize(raw_output)
|
||||
|
||||
|
||||
def _parse_lc_role(
|
||||
role: str,
|
||||
) -> Union[Literal["user", "ai", "system", "function"], None]:
|
||||
@@ -93,27 +29,8 @@ def _parse_lc_role(
|
||||
return None
|
||||
|
||||
|
||||
def _get_user_id(metadata: Any) -> Any:
|
||||
metadata = metadata or {}
|
||||
user_id = metadata.get("user_id")
|
||||
if user_id is None:
|
||||
user_id = metadata.get("userId")
|
||||
return user_id
|
||||
|
||||
|
||||
def _parse_lc_message(message: BaseMessage) -> Dict[str, Any]:
|
||||
parsed = {"text": message.content, "role": _parse_lc_role(message.type)}
|
||||
|
||||
function_call = (message.additional_kwargs or {}).get("function_call")
|
||||
|
||||
if function_call is not None:
|
||||
parsed["functionCall"] = function_call
|
||||
|
||||
return parsed
|
||||
|
||||
|
||||
def _parse_lc_messages(messages: Union[List[BaseMessage], Any]) -> List[Dict[str, Any]]:
|
||||
return [_parse_lc_message(message) for message in messages]
|
||||
def _serialize_lc_message(message: BaseMessage) -> Dict[str, Any]:
|
||||
return {"text": message.content, "role": _parse_lc_role(message.type)}
|
||||
|
||||
|
||||
class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
@@ -145,20 +62,14 @@ class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
|
||||
__api_url: str
|
||||
__app_id: str
|
||||
__verbose: bool
|
||||
|
||||
def __init__(
|
||||
self,
|
||||
app_id: Union[str, None] = None,
|
||||
api_url: Union[str, None] = None,
|
||||
verbose: bool = False,
|
||||
self, app_id: Union[str, None] = None, api_url: Union[str, None] = None
|
||||
) -> None:
|
||||
super().__init__()
|
||||
|
||||
self.__api_url = api_url or os.getenv("LLMONITOR_API_URL") or DEFAULT_API_URL
|
||||
|
||||
self.__verbose = verbose or bool(os.getenv("LLMONITOR_VERBOSE"))
|
||||
|
||||
_app_id = app_id or os.getenv("LLMONITOR_APP_ID")
|
||||
if _app_id is None:
|
||||
raise ValueError(
|
||||
@@ -178,12 +89,7 @@ class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
|
||||
def __send_event(self, event: Dict[str, Any]) -> None:
|
||||
headers = {"Content-Type": "application/json"}
|
||||
|
||||
event = {**event, "app": self.__app_id, "timestamp": str(datetime.utcnow())}
|
||||
|
||||
if self.__verbose:
|
||||
print("llmonitor_callback", event)
|
||||
|
||||
data = {"events": event}
|
||||
requests.post(headers=headers, url=f"{self.__api_url}/api/report", json=data)
|
||||
|
||||
@@ -204,7 +110,7 @@ class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
"userId": (metadata or {}).get("userId"),
|
||||
"runId": str(run_id),
|
||||
"parentRunId": str(parent_run_id) if parent_run_id else None,
|
||||
"input": _parse_input(prompts),
|
||||
"input": prompts[0],
|
||||
"name": kwargs.get("invocation_params", {}).get("model_name"),
|
||||
"tags": tags,
|
||||
"metadata": metadata,
|
||||
@@ -222,15 +128,13 @@ class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
metadata: Union[Dict[str, Any], None] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
user_id = _get_user_id(metadata)
|
||||
|
||||
event = {
|
||||
"event": "start",
|
||||
"type": "llm",
|
||||
"userId": user_id,
|
||||
"userId": (metadata or {}).get("userId"),
|
||||
"runId": str(run_id),
|
||||
"parentRunId": str(parent_run_id) if parent_run_id else None,
|
||||
"input": _parse_lc_messages(messages[0]),
|
||||
"input": [_serialize_lc_message(message[0]) for message in messages],
|
||||
"name": kwargs.get("invocation_params", {}).get("model_name"),
|
||||
"tags": tags,
|
||||
"metadata": metadata,
|
||||
@@ -247,26 +151,36 @@ class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
) -> None:
|
||||
token_usage = (response.llm_output or {}).get("token_usage", {})
|
||||
|
||||
parsed_output = _parse_lc_messages(
|
||||
map(
|
||||
lambda o: o.message if hasattr(o, "message") else None,
|
||||
response.generations[0],
|
||||
)
|
||||
)
|
||||
|
||||
event = {
|
||||
"event": "end",
|
||||
"type": "llm",
|
||||
"runId": str(run_id),
|
||||
"parent_run_id": str(parent_run_id) if parent_run_id else None,
|
||||
"output": parsed_output,
|
||||
"output": {"text": response.generations[0][0].text, "role": "ai"},
|
||||
"tokensUsage": {
|
||||
"prompt": token_usage.get("prompt_tokens"),
|
||||
"completion": token_usage.get("completion_tokens"),
|
||||
"prompt": token_usage.get("prompt_tokens", 0),
|
||||
"completion": token_usage.get("completion_tokens", 0),
|
||||
},
|
||||
}
|
||||
self.__send_event(event)
|
||||
|
||||
def on_llm_error(
|
||||
self,
|
||||
error: Union[Exception, KeyboardInterrupt],
|
||||
*,
|
||||
run_id: UUID,
|
||||
parent_run_id: Union[UUID, None] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
event = {
|
||||
"event": "error",
|
||||
"type": "llm",
|
||||
"runId": str(run_id),
|
||||
"parent_run_id": str(parent_run_id) if parent_run_id else None,
|
||||
"error": {"message": str(error), "stack": traceback.format_exc()},
|
||||
}
|
||||
self.__send_event(event)
|
||||
|
||||
def on_tool_start(
|
||||
self,
|
||||
serialized: Dict[str, Any],
|
||||
@@ -278,11 +192,10 @@ class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
metadata: Union[Dict[str, Any], None] = None,
|
||||
**kwargs: Any,
|
||||
) -> None:
|
||||
user_id = _get_user_id(metadata)
|
||||
event = {
|
||||
"event": "start",
|
||||
"type": "tool",
|
||||
"userId": user_id,
|
||||
"userId": (metadata or {}).get("userId"),
|
||||
"runId": str(run_id),
|
||||
"parentRunId": str(parent_run_id) if parent_run_id else None,
|
||||
"name": serialized.get("name"),
|
||||
@@ -323,34 +236,25 @@ class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
) -> Any:
|
||||
name = serialized.get("id", [None, None, None, None])[3]
|
||||
type = "chain"
|
||||
metadata = metadata or {}
|
||||
|
||||
agentName = metadata.get("agent_name")
|
||||
if agentName is None:
|
||||
agentName = metadata.get("agentName")
|
||||
|
||||
agentName = (metadata or {}).get("agentName")
|
||||
if agentName is not None:
|
||||
type = "agent"
|
||||
name = agentName
|
||||
if name == "AgentExecutor" or name == "PlanAndExecute":
|
||||
type = "agent"
|
||||
|
||||
if parent_run_id is not None:
|
||||
type = "chain"
|
||||
|
||||
user_id = _get_user_id(metadata)
|
||||
|
||||
event = {
|
||||
"event": "start",
|
||||
"type": type,
|
||||
"userId": user_id,
|
||||
"userId": (metadata or {}).get("userId"),
|
||||
"runId": str(run_id),
|
||||
"parentRunId": str(parent_run_id) if parent_run_id else None,
|
||||
"input": _parse_input(inputs),
|
||||
"input": inputs.get("input", inputs),
|
||||
"tags": tags,
|
||||
"metadata": metadata,
|
||||
"name": name,
|
||||
"name": serialized.get("id", [None, None, None, None])[3],
|
||||
}
|
||||
|
||||
self.__send_event(event)
|
||||
|
||||
def on_chain_end(
|
||||
@@ -365,42 +269,7 @@ class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
"event": "end",
|
||||
"type": "chain",
|
||||
"runId": str(run_id),
|
||||
"output": _parse_output(outputs),
|
||||
}
|
||||
self.__send_event(event)
|
||||
|
||||
def on_agent_action(
|
||||
self,
|
||||
action: AgentAction,
|
||||
*,
|
||||
run_id: UUID,
|
||||
parent_run_id: Union[UUID, None] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
event = {
|
||||
"event": "start",
|
||||
"type": "tool",
|
||||
"runId": str(run_id),
|
||||
"parentRunId": str(parent_run_id) if parent_run_id else None,
|
||||
"name": action.tool,
|
||||
"input": _parse_input(action.tool_input),
|
||||
}
|
||||
self.__send_event(event)
|
||||
|
||||
def on_agent_finish(
|
||||
self,
|
||||
finish: AgentFinish,
|
||||
*,
|
||||
run_id: UUID,
|
||||
parent_run_id: Union[UUID, None] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
event = {
|
||||
"event": "end",
|
||||
"type": "agent",
|
||||
"runId": str(run_id),
|
||||
"parentRunId": str(parent_run_id) if parent_run_id else None,
|
||||
"output": _parse_output(finish.return_values),
|
||||
"output": outputs.get("output", outputs),
|
||||
}
|
||||
self.__send_event(event)
|
||||
|
||||
@@ -421,37 +290,38 @@ class LLMonitorCallbackHandler(BaseCallbackHandler):
|
||||
}
|
||||
self.__send_event(event)
|
||||
|
||||
def on_tool_error(
|
||||
def on_agent_action(
|
||||
self,
|
||||
error: Union[Exception, KeyboardInterrupt],
|
||||
action: AgentAction,
|
||||
*,
|
||||
run_id: UUID,
|
||||
parent_run_id: Union[UUID, None] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
event = {
|
||||
"event": "error",
|
||||
"event": "start",
|
||||
"type": "tool",
|
||||
"runId": str(run_id),
|
||||
"parent_run_id": str(parent_run_id) if parent_run_id else None,
|
||||
"error": {"message": str(error), "stack": traceback.format_exc()},
|
||||
"parentRunId": str(parent_run_id) if parent_run_id else None,
|
||||
"name": action.tool,
|
||||
"input": action.tool_input,
|
||||
}
|
||||
self.__send_event(event)
|
||||
|
||||
def on_llm_error(
|
||||
def on_agent_finish(
|
||||
self,
|
||||
error: Union[Exception, KeyboardInterrupt],
|
||||
finish: AgentFinish,
|
||||
*,
|
||||
run_id: UUID,
|
||||
parent_run_id: Union[UUID, None] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
event = {
|
||||
"event": "error",
|
||||
"type": "llm",
|
||||
"event": "end",
|
||||
"type": "agent",
|
||||
"runId": str(run_id),
|
||||
"parent_run_id": str(parent_run_id) if parent_run_id else None,
|
||||
"error": {"message": str(error), "stack": traceback.format_exc()},
|
||||
"parentRunId": str(parent_run_id) if parent_run_id else None,
|
||||
"output": finish.return_values,
|
||||
}
|
||||
self.__send_event(event)
|
||||
|
||||
|
||||
@@ -2,20 +2,29 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from concurrent.futures import Future, ThreadPoolExecutor
|
||||
from concurrent.futures import Future, ThreadPoolExecutor, wait
|
||||
from typing import Any, Dict, List, Optional, Sequence, Set, Union
|
||||
from uuid import UUID
|
||||
|
||||
import langsmith
|
||||
from langsmith import schemas as langsmith_schemas
|
||||
|
||||
from langchain.callbacks import manager
|
||||
from langchain.callbacks.tracers import langchain as langchain_tracer
|
||||
from langchain.callbacks.manager import tracing_v2_enabled
|
||||
from langchain.callbacks.tracers.base import BaseTracer
|
||||
from langchain.callbacks.tracers.langchain import _get_client
|
||||
from langchain.callbacks.tracers.schemas import Run
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_TRACERS: List[EvaluatorCallbackHandler] = []
|
||||
|
||||
|
||||
def wait_for_all_evaluators() -> None:
|
||||
"""Wait for all tracers to finish."""
|
||||
global _TRACERS
|
||||
for tracer in _TRACERS:
|
||||
tracer.wait_for_futures()
|
||||
|
||||
|
||||
class EvaluatorCallbackHandler(BaseTracer):
|
||||
"""A tracer that runs a run evaluator whenever a run is persisted.
|
||||
@@ -70,13 +79,17 @@ class EvaluatorCallbackHandler(BaseTracer):
|
||||
self.example_id = (
|
||||
UUID(example_id) if isinstance(example_id, str) else example_id
|
||||
)
|
||||
self.client = client or langchain_tracer.get_client()
|
||||
self.client = client or _get_client()
|
||||
self.evaluators = evaluators
|
||||
self.max_workers = max_workers or len(evaluators)
|
||||
self.executor = ThreadPoolExecutor(
|
||||
max_workers=max(max_workers or len(evaluators), 1)
|
||||
)
|
||||
self.futures: Set[Future] = set()
|
||||
self.skip_unfinished = skip_unfinished
|
||||
self.project_name = project_name
|
||||
self.logged_feedback: Dict[str, List[langsmith_schemas.Feedback]] = {}
|
||||
global _TRACERS
|
||||
_TRACERS.append(self)
|
||||
|
||||
def _evaluate_in_project(self, run: Run, evaluator: langsmith.RunEvaluator) -> None:
|
||||
"""Evaluate the run in the project.
|
||||
@@ -92,7 +105,7 @@ class EvaluatorCallbackHandler(BaseTracer):
|
||||
try:
|
||||
if self.project_name is None:
|
||||
feedback = self.client.evaluate_run(run, evaluator)
|
||||
with manager.tracing_v2_enabled(
|
||||
with tracing_v2_enabled(
|
||||
project_name=self.project_name, tags=["eval"], client=self.client
|
||||
):
|
||||
feedback = self.client.evaluate_run(run, evaluator)
|
||||
@@ -120,15 +133,14 @@ class EvaluatorCallbackHandler(BaseTracer):
|
||||
return
|
||||
run_ = run.copy()
|
||||
run_.reference_example_id = self.example_id
|
||||
if self.max_workers > 0:
|
||||
with ThreadPoolExecutor(max_workers=self.max_workers) as executor:
|
||||
list(
|
||||
executor.map(
|
||||
self._evaluate_in_project,
|
||||
[run_ for _ in range(len(self.evaluators))],
|
||||
self.evaluators,
|
||||
)
|
||||
)
|
||||
else:
|
||||
for evaluator in self.evaluators:
|
||||
self._evaluate_in_project(run_, evaluator)
|
||||
for evaluator in self.evaluators:
|
||||
self.futures.add(
|
||||
self.executor.submit(self._evaluate_in_project, run_, evaluator)
|
||||
)
|
||||
|
||||
def wait_for_futures(self) -> None:
|
||||
"""Wait for all futures to complete."""
|
||||
futures = list(self.futures)
|
||||
wait(futures)
|
||||
for future in futures:
|
||||
self.futures.remove(future)
|
||||
|
||||
@@ -42,7 +42,7 @@ def wait_for_all_tracers() -> None:
|
||||
tracer.wait_for_futures()
|
||||
|
||||
|
||||
def get_client() -> Client:
|
||||
def _get_client() -> Client:
|
||||
"""Get the client."""
|
||||
global _CLIENT
|
||||
if _CLIENT is None:
|
||||
@@ -83,7 +83,7 @@ class LangChainTracer(BaseTracer):
|
||||
_EXECUTORS.append(self.executor)
|
||||
else:
|
||||
self.executor = None
|
||||
self.client = client or get_client()
|
||||
self.client = client or _get_client()
|
||||
self._futures: Set[Future] = set()
|
||||
self.tags = tags or []
|
||||
global _TRACERS
|
||||
|
||||
@@ -20,7 +20,6 @@ from langchain.chains.llm_checker.base import LLMCheckerChain
|
||||
from langchain.chains.llm_math.base import LLMMathChain
|
||||
from langchain.chains.llm_requests import LLMRequestsChain
|
||||
from langchain.chains.qa_with_sources.base import QAWithSourcesChain
|
||||
from langchain.chains.qa_with_sources.retrieval import RetrievalQAWithSourcesChain
|
||||
from langchain.chains.qa_with_sources.vector_db import VectorDBQAWithSourcesChain
|
||||
from langchain.chains.retrieval_qa.base import RetrievalQA, VectorDBQA
|
||||
from langchain.llms.loading import load_llm, load_llm_from_config
|
||||
@@ -425,30 +424,6 @@ def _load_retrieval_qa(config: dict, **kwargs: Any) -> RetrievalQA:
|
||||
)
|
||||
|
||||
|
||||
def _load_retrieval_qa_with_sources_chain(
|
||||
config: dict, **kwargs: Any
|
||||
) -> RetrievalQAWithSourcesChain:
|
||||
if "retriever" in kwargs:
|
||||
retriever = kwargs.pop("retriever")
|
||||
else:
|
||||
raise ValueError("`retriever` must be present.")
|
||||
if "combine_documents_chain" in config:
|
||||
combine_documents_chain_config = config.pop("combine_documents_chain")
|
||||
combine_documents_chain = load_chain_from_config(combine_documents_chain_config)
|
||||
elif "combine_documents_chain_path" in config:
|
||||
combine_documents_chain = load_chain(config.pop("combine_documents_chain_path"))
|
||||
else:
|
||||
raise ValueError(
|
||||
"One of `combine_documents_chain` or "
|
||||
"`combine_documents_chain_path` must be present."
|
||||
)
|
||||
return RetrievalQAWithSourcesChain(
|
||||
combine_documents_chain=combine_documents_chain,
|
||||
retriever=retriever,
|
||||
**config,
|
||||
)
|
||||
|
||||
|
||||
def _load_vector_db_qa(config: dict, **kwargs: Any) -> VectorDBQA:
|
||||
if "vectorstore" in kwargs:
|
||||
vectorstore = kwargs.pop("vectorstore")
|
||||
@@ -562,7 +537,6 @@ type_to_loader_dict = {
|
||||
"vector_db_qa_with_sources_chain": _load_vector_db_qa_with_sources_chain,
|
||||
"vector_db_qa": _load_vector_db_qa,
|
||||
"retrieval_qa": _load_retrieval_qa,
|
||||
"retrieval_qa_with_sources_chain": _load_retrieval_qa_with_sources_chain,
|
||||
"graph_cypher_chain": _load_graph_cypher_chain,
|
||||
}
|
||||
|
||||
|
||||
@@ -60,8 +60,3 @@ class RetrievalQAWithSourcesChain(BaseQAWithSourcesChain):
|
||||
question, callbacks=run_manager.get_child()
|
||||
)
|
||||
return self._reduce_tokens_below_limit(docs)
|
||||
|
||||
@property
|
||||
def _chain_type(self) -> str:
|
||||
"""Return the chain type."""
|
||||
return "retrieval_qa_with_sources_chain"
|
||||
|
||||
@@ -1,19 +1,6 @@
|
||||
"""**Chat Loaders** load chat messages from common communications platforms.
|
||||
"""Load chat messages from common communications platforms for finetuning.
|
||||
|
||||
Load chat messages from various
|
||||
This module provides functions to load chat messages from various
|
||||
communications platforms such as Facebook Messenger, Telegram, and
|
||||
WhatsApp. The loaded chat messages can be used for fine-tuning models.
|
||||
|
||||
**Class hierarchy:**
|
||||
|
||||
.. code-block::
|
||||
|
||||
BaseChatLoader --> <name>ChatLoader # Examples: WhatsAppChatLoader, IMessageChatLoader
|
||||
|
||||
**Main helpers:**
|
||||
|
||||
.. code-block::
|
||||
|
||||
ChatSession
|
||||
|
||||
""" # noqa: E501
|
||||
WhatsApp. The loaded chat messages can be used for finetuning models.
|
||||
"""
|
||||
|
||||
@@ -1,3 +1,10 @@
|
||||
"""Base definitions for chat loaders.
|
||||
|
||||
A chat loader is a class that loads chat messages from an external
|
||||
source such as a file or a database. The chat messages can then be
|
||||
used for finetuning.
|
||||
"""
|
||||
|
||||
from abc import ABC, abstractmethod
|
||||
from typing import Iterator, List, Sequence, TypedDict
|
||||
|
||||
@@ -5,7 +12,7 @@ from langchain.schema.messages import BaseMessage
|
||||
|
||||
|
||||
class ChatSession(TypedDict):
|
||||
"""Chat Session represents a single
|
||||
"""A chat session represents a single
|
||||
conversation, channel, or other group of messages."""
|
||||
|
||||
messages: Sequence[BaseMessage]
|
||||
|
||||
@@ -10,7 +10,7 @@ logger = logging.getLogger(__file__)
|
||||
|
||||
|
||||
class SingleFileFacebookMessengerChatLoader(BaseChatLoader):
|
||||
"""Load `Facebook Messenger` chat data from a single file.
|
||||
"""A chat loader for loading Facebook Messenger chat data from a single file.
|
||||
|
||||
Args:
|
||||
path (Union[Path, str]): The path to the chat file.
|
||||
@@ -45,7 +45,7 @@ class SingleFileFacebookMessengerChatLoader(BaseChatLoader):
|
||||
|
||||
|
||||
class FolderFacebookMessengerChatLoader(BaseChatLoader):
|
||||
"""Load `Facebook Messenger` chat data from a folder.
|
||||
"""A chat loader for loading Facebook Messenger chat data from a folder.
|
||||
|
||||
Args:
|
||||
path (Union[str, Path]): The path to the directory
|
||||
|
||||
@@ -62,7 +62,7 @@ def _get_message_data(service: Any, message: Any) -> ChatSession:
|
||||
|
||||
|
||||
class GMailLoader(BaseChatLoader):
|
||||
"""Load data from `GMail`.
|
||||
"""This loader goes over how to load data from GMail.
|
||||
|
||||
There are many ways you could want to load data from GMail.
|
||||
This loader is currently fairly opinionated in how to do so.
|
||||
|
||||
@@ -1,27 +1,27 @@
|
||||
"""IMessage Chat Loader.
|
||||
|
||||
This class is used to load chat sessions from the iMessage chat.db SQLite file.
|
||||
It only works on macOS when you have iMessage enabled and have the chat.db file.
|
||||
|
||||
The chat.db file is likely located at ~/Library/Messages/chat.db. However, your
|
||||
terminal may not have permission to access this file. To resolve this, you can
|
||||
copy the file to a different location, change the permissions of the file, or
|
||||
grant full disk access for your terminal emulator in System Settings > Security
|
||||
and Privacy > Full Disk Access.
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from pathlib import Path
|
||||
from typing import TYPE_CHECKING, Iterator, List, Optional, Union
|
||||
|
||||
from langchain import schema
|
||||
from langchain.chat_loaders.base import BaseChatLoader, ChatSession
|
||||
from langchain.chat_loaders import base as chat_loaders
|
||||
|
||||
if TYPE_CHECKING:
|
||||
import sqlite3
|
||||
|
||||
|
||||
class IMessageChatLoader(BaseChatLoader):
|
||||
"""Load chat sessions from the `iMessage` chat.db SQLite file.
|
||||
|
||||
It only works on macOS when you have iMessage enabled and have the chat.db file.
|
||||
|
||||
The chat.db file is likely located at ~/Library/Messages/chat.db. However, your
|
||||
terminal may not have permission to access this file. To resolve this, you can
|
||||
copy the file to a different location, change the permissions of the file, or
|
||||
grant full disk access for your terminal emulator
|
||||
in System Settings > Security and Privacy > Full Disk Access.
|
||||
"""
|
||||
|
||||
class IMessageChatLoader(chat_loaders.BaseChatLoader):
|
||||
def __init__(self, path: Optional[Union[str, Path]] = None):
|
||||
"""
|
||||
Initialize the IMessageChatLoader.
|
||||
@@ -46,7 +46,7 @@ class IMessageChatLoader(BaseChatLoader):
|
||||
|
||||
def _load_single_chat_session(
|
||||
self, cursor: "sqlite3.Cursor", chat_id: int
|
||||
) -> ChatSession:
|
||||
) -> chat_loaders.ChatSession:
|
||||
"""
|
||||
Load a single chat session from the iMessage chat.db.
|
||||
|
||||
@@ -83,9 +83,9 @@ class IMessageChatLoader(BaseChatLoader):
|
||||
)
|
||||
)
|
||||
|
||||
return ChatSession(messages=results)
|
||||
return chat_loaders.ChatSession(messages=results)
|
||||
|
||||
def lazy_load(self) -> Iterator[ChatSession]:
|
||||
def lazy_load(self) -> Iterator[chat_loaders.ChatSession]:
|
||||
"""
|
||||
Lazy load the chat sessions from the iMessage chat.db
|
||||
and yield them in the required format.
|
||||
|
||||
@@ -6,14 +6,12 @@ from pathlib import Path
|
||||
from typing import Dict, Iterator, List, Union
|
||||
|
||||
from langchain import schema
|
||||
from langchain.chat_loaders.base import BaseChatLoader, ChatSession
|
||||
from langchain.chat_loaders import base as chat_loaders
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class SlackChatLoader(BaseChatLoader):
|
||||
"""Load `Slack` conversations from a dump zip file."""
|
||||
|
||||
class SlackChatLoader(chat_loaders.BaseChatLoader):
|
||||
def __init__(
|
||||
self,
|
||||
path: Union[str, Path],
|
||||
@@ -27,7 +25,9 @@ class SlackChatLoader(BaseChatLoader):
|
||||
if not self.zip_path.exists():
|
||||
raise FileNotFoundError(f"File {self.zip_path} not found")
|
||||
|
||||
def _load_single_chat_session(self, messages: List[Dict]) -> ChatSession:
|
||||
def _load_single_chat_session(
|
||||
self, messages: List[Dict]
|
||||
) -> chat_loaders.ChatSession:
|
||||
results: List[Union[schema.AIMessage, schema.HumanMessage]] = []
|
||||
previous_sender = None
|
||||
for message in messages:
|
||||
@@ -60,7 +60,7 @@ class SlackChatLoader(BaseChatLoader):
|
||||
)
|
||||
)
|
||||
previous_sender = sender
|
||||
return ChatSession(messages=results)
|
||||
return chat_loaders.ChatSession(messages=results)
|
||||
|
||||
def _read_json(self, zip_file: zipfile.ZipFile, file_path: str) -> List[dict]:
|
||||
"""Read JSON data from a zip subfile."""
|
||||
@@ -70,7 +70,7 @@ class SlackChatLoader(BaseChatLoader):
|
||||
raise ValueError(f"Expected list of dictionaries, got {type(data)}")
|
||||
return data
|
||||
|
||||
def lazy_load(self) -> Iterator[ChatSession]:
|
||||
def lazy_load(self) -> Iterator[chat_loaders.ChatSession]:
|
||||
"""
|
||||
Lazy load the chat sessions from the Slack dump file and yield them
|
||||
in the required format.
|
||||
|
||||
@@ -7,13 +7,14 @@ from pathlib import Path
|
||||
from typing import Iterator, List, Union
|
||||
|
||||
from langchain import schema
|
||||
from langchain.chat_loaders.base import BaseChatLoader, ChatSession
|
||||
from langchain.chat_loaders import base as chat_loaders
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class TelegramChatLoader(BaseChatLoader):
|
||||
"""Load `telegram` conversations to LangChain chat messages.
|
||||
class TelegramChatLoader(chat_loaders.BaseChatLoader):
|
||||
"""A loading utility for converting telegram conversations
|
||||
to LangChain chat messages.
|
||||
|
||||
To export, use the Telegram Desktop app from
|
||||
https://desktop.telegram.org/, select a conversation, click the three dots
|
||||
@@ -35,14 +36,16 @@ class TelegramChatLoader(BaseChatLoader):
|
||||
"""
|
||||
self.path = path if isinstance(path, str) else str(path)
|
||||
|
||||
def _load_single_chat_session_html(self, file_path: str) -> ChatSession:
|
||||
def _load_single_chat_session_html(
|
||||
self, file_path: str
|
||||
) -> chat_loaders.ChatSession:
|
||||
"""Load a single chat session from an HTML file.
|
||||
|
||||
Args:
|
||||
file_path (str): Path to the HTML file.
|
||||
|
||||
Returns:
|
||||
ChatSession: The loaded chat session.
|
||||
chat_loaders.ChatSession: The loaded chat session.
|
||||
"""
|
||||
try:
|
||||
from bs4 import BeautifulSoup
|
||||
@@ -79,16 +82,18 @@ class TelegramChatLoader(BaseChatLoader):
|
||||
)
|
||||
previous_sender = from_name
|
||||
|
||||
return ChatSession(messages=results)
|
||||
return chat_loaders.ChatSession(messages=results)
|
||||
|
||||
def _load_single_chat_session_json(self, file_path: str) -> ChatSession:
|
||||
def _load_single_chat_session_json(
|
||||
self, file_path: str
|
||||
) -> chat_loaders.ChatSession:
|
||||
"""Load a single chat session from a JSON file.
|
||||
|
||||
Args:
|
||||
file_path (str): Path to the JSON file.
|
||||
|
||||
Returns:
|
||||
ChatSession: The loaded chat session.
|
||||
chat_loaders.ChatSession: The loaded chat session.
|
||||
"""
|
||||
with open(file_path, "r", encoding="utf-8") as file:
|
||||
data = json.load(file)
|
||||
@@ -110,7 +115,7 @@ class TelegramChatLoader(BaseChatLoader):
|
||||
)
|
||||
)
|
||||
|
||||
return ChatSession(messages=results)
|
||||
return chat_loaders.ChatSession(messages=results)
|
||||
|
||||
def _iterate_files(self, path: str) -> Iterator[str]:
|
||||
"""Iterate over files in a directory or zip file.
|
||||
@@ -135,12 +140,12 @@ class TelegramChatLoader(BaseChatLoader):
|
||||
with tempfile.TemporaryDirectory() as temp_dir:
|
||||
yield zip_file.extract(file, path=temp_dir)
|
||||
|
||||
def lazy_load(self) -> Iterator[ChatSession]:
|
||||
def lazy_load(self) -> Iterator[chat_loaders.ChatSession]:
|
||||
"""Lazy load the messages from the chat file and yield them
|
||||
in as chat sessions.
|
||||
|
||||
Yields:
|
||||
ChatSession: The loaded chat session.
|
||||
chat_loaders.ChatSession: The loaded chat session.
|
||||
"""
|
||||
for file_path in self._iterate_files(self.path):
|
||||
if file_path.endswith(".html"):
|
||||
|
||||
@@ -5,15 +5,13 @@ import zipfile
|
||||
from typing import Iterator, List, Union
|
||||
|
||||
from langchain import schema
|
||||
from langchain.chat_loaders.base import BaseChatLoader, ChatSession
|
||||
from langchain.chat_loaders import base as chat_loaders
|
||||
from langchain.schema import messages
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class WhatsAppChatLoader(BaseChatLoader):
|
||||
"""Load `WhatsApp` conversations from a dump zip file or directory."""
|
||||
|
||||
class WhatsAppChatLoader(chat_loaders.BaseChatLoader):
|
||||
def __init__(self, path: str):
|
||||
"""Initialize the WhatsAppChatLoader.
|
||||
|
||||
@@ -42,7 +40,7 @@ class WhatsAppChatLoader(BaseChatLoader):
|
||||
flags=re.IGNORECASE,
|
||||
)
|
||||
|
||||
def _load_single_chat_session(self, file_path: str) -> ChatSession:
|
||||
def _load_single_chat_session(self, file_path: str) -> chat_loaders.ChatSession:
|
||||
"""Load a single chat session from a file.
|
||||
|
||||
Args:
|
||||
@@ -84,7 +82,7 @@ class WhatsAppChatLoader(BaseChatLoader):
|
||||
)
|
||||
else:
|
||||
logger.debug(f"Could not parse line: {line}")
|
||||
return ChatSession(messages=results)
|
||||
return chat_loaders.ChatSession(messages=results)
|
||||
|
||||
def _iterate_files(self, path: str) -> Iterator[str]:
|
||||
"""Iterate over the files in a directory or zip file.
|
||||
@@ -108,7 +106,7 @@ class WhatsAppChatLoader(BaseChatLoader):
|
||||
if file.endswith(".txt"):
|
||||
yield zip_file.extract(file)
|
||||
|
||||
def lazy_load(self) -> Iterator[ChatSession]:
|
||||
def lazy_load(self) -> Iterator[chat_loaders.ChatSession]:
|
||||
"""Lazy load the messages from the chat file and yield
|
||||
them as chat sessions.
|
||||
|
||||
|
||||
@@ -20,12 +20,12 @@ an interface where "chat messages" are the inputs and outputs.
|
||||
from langchain.chat_models.anthropic import ChatAnthropic
|
||||
from langchain.chat_models.anyscale import ChatAnyscale
|
||||
from langchain.chat_models.azure_openai import AzureChatOpenAI
|
||||
from langchain.chat_models.bedrock import BedrockChat
|
||||
from langchain.chat_models.ernie import ErnieBotChat
|
||||
from langchain.chat_models.fake import FakeListChatModel
|
||||
from langchain.chat_models.google_palm import ChatGooglePalm
|
||||
from langchain.chat_models.human import HumanInputChatModel
|
||||
from langchain.chat_models.jinachat import JinaChat
|
||||
from langchain.chat_models.konko import ChatKonko
|
||||
from langchain.chat_models.litellm import ChatLiteLLM
|
||||
from langchain.chat_models.mlflow_ai_gateway import ChatMLflowAIGateway
|
||||
from langchain.chat_models.ollama import ChatOllama
|
||||
@@ -36,6 +36,7 @@ from langchain.chat_models.vertexai import ChatVertexAI
|
||||
__all__ = [
|
||||
"ChatOpenAI",
|
||||
"AzureChatOpenAI",
|
||||
"BedrockChat",
|
||||
"FakeListChatModel",
|
||||
"PromptLayerChatOpenAI",
|
||||
"ChatAnthropic",
|
||||
@@ -48,5 +49,4 @@ __all__ = [
|
||||
"ChatAnyscale",
|
||||
"ChatLiteLLM",
|
||||
"ErnieBotChat",
|
||||
"ChatKonko",
|
||||
]
|
||||
|
||||
@@ -1,292 +0,0 @@
|
||||
"""KonkoAI chat wrapper."""
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import (
|
||||
Any,
|
||||
Dict,
|
||||
Iterator,
|
||||
List,
|
||||
Mapping,
|
||||
Optional,
|
||||
Set,
|
||||
Tuple,
|
||||
Union,
|
||||
)
|
||||
|
||||
import requests
|
||||
|
||||
from langchain.adapters.openai import convert_dict_to_message, convert_message_to_dict
|
||||
from langchain.callbacks.manager import (
|
||||
CallbackManagerForLLMRun,
|
||||
)
|
||||
from langchain.chat_models.openai import ChatOpenAI, _convert_delta_to_message_chunk
|
||||
from langchain.pydantic_v1 import Field, root_validator
|
||||
from langchain.schema import ChatGeneration, ChatResult
|
||||
from langchain.schema.messages import AIMessageChunk, BaseMessage
|
||||
from langchain.schema.output import ChatGenerationChunk
|
||||
from langchain.utils import get_from_dict_or_env
|
||||
|
||||
DEFAULT_API_BASE = "https://api.konko.ai/v1"
|
||||
DEFAULT_MODEL = "meta-llama/Llama-2-13b-chat-hf"
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class ChatKonko(ChatOpenAI):
|
||||
"""`ChatKonko` Chat large language models API.
|
||||
|
||||
To use, you should have the ``konko`` python package installed, and the
|
||||
environment variable ``KONKO_API_KEY`` and ``OPENAI_API_KEY`` set with your API key.
|
||||
|
||||
Any parameters that are valid to be passed to the konko.create call can be passed
|
||||
in, even if not explicitly saved on this class.
|
||||
|
||||
Example:
|
||||
.. code-block:: python
|
||||
|
||||
from langchain.chat_models import ChatKonko
|
||||
llm = ChatKonko(model="meta-llama/Llama-2-13b-chat-hf")
|
||||
"""
|
||||
|
||||
@property
|
||||
def lc_secrets(self) -> Dict[str, str]:
|
||||
return {"konko_api_key": "KONKO_API_KEY", "openai_api_key": "OPENAI_API_KEY"}
|
||||
|
||||
@property
|
||||
def lc_serializable(self) -> bool:
|
||||
return True
|
||||
|
||||
client: Any = None #: :meta private:
|
||||
model: str = Field(default=DEFAULT_MODEL, alias="model")
|
||||
"""Model name to use."""
|
||||
temperature: float = 0.7
|
||||
"""What sampling temperature to use."""
|
||||
model_kwargs: Dict[str, Any] = Field(default_factory=dict)
|
||||
"""Holds any model parameters valid for `create` call not explicitly specified."""
|
||||
openai_api_key: Optional[str] = None
|
||||
konko_api_key: Optional[str] = None
|
||||
request_timeout: Optional[Union[float, Tuple[float, float]]] = None
|
||||
"""Timeout for requests to Konko completion API."""
|
||||
max_retries: int = 6
|
||||
"""Maximum number of retries to make when generating."""
|
||||
streaming: bool = False
|
||||
"""Whether to stream the results or not."""
|
||||
n: int = 1
|
||||
"""Number of chat completions to generate for each prompt."""
|
||||
max_tokens: int = 20
|
||||
"""Maximum number of tokens to generate."""
|
||||
|
||||
@root_validator()
|
||||
def validate_environment(cls, values: Dict) -> Dict:
|
||||
"""Validate that api key and python package exists in environment."""
|
||||
values["konko_api_key"] = get_from_dict_or_env(
|
||||
values, "konko_api_key", "KONKO_API_KEY"
|
||||
)
|
||||
try:
|
||||
import konko
|
||||
|
||||
except ImportError:
|
||||
raise ValueError(
|
||||
"Could not import konko python package. "
|
||||
"Please install it with `pip install konko`."
|
||||
)
|
||||
try:
|
||||
values["client"] = konko.ChatCompletion
|
||||
except AttributeError:
|
||||
raise ValueError(
|
||||
"`konko` has no `ChatCompletion` attribute, this is likely "
|
||||
"due to an old version of the konko package. Try upgrading it "
|
||||
"with `pip install --upgrade konko`."
|
||||
)
|
||||
if values["n"] < 1:
|
||||
raise ValueError("n must be at least 1.")
|
||||
if values["n"] > 1 and values["streaming"]:
|
||||
raise ValueError("n must be 1 when streaming.")
|
||||
return values
|
||||
|
||||
@property
|
||||
def _default_params(self) -> Dict[str, Any]:
|
||||
"""Get the default parameters for calling Konko API."""
|
||||
return {
|
||||
"model": self.model,
|
||||
"request_timeout": self.request_timeout,
|
||||
"max_tokens": self.max_tokens,
|
||||
"stream": self.streaming,
|
||||
"n": self.n,
|
||||
"temperature": self.temperature,
|
||||
**self.model_kwargs,
|
||||
}
|
||||
|
||||
@staticmethod
|
||||
def get_available_models(
|
||||
konko_api_key: Optional[str] = None,
|
||||
openai_api_key: Optional[str] = None,
|
||||
konko_api_base: str = DEFAULT_API_BASE,
|
||||
) -> Set[str]:
|
||||
"""Get available models from Konko API."""
|
||||
|
||||
# Try to retrieve the OpenAI API key if it's not passed as an argument
|
||||
if not openai_api_key:
|
||||
try:
|
||||
openai_api_key = os.environ["OPENAI_API_KEY"]
|
||||
except KeyError:
|
||||
pass # It's okay if it's not set, we just won't use it
|
||||
|
||||
# Try to retrieve the Konko API key if it's not passed as an argument
|
||||
if not konko_api_key:
|
||||
try:
|
||||
konko_api_key = os.environ["KONKO_API_KEY"]
|
||||
except KeyError:
|
||||
raise ValueError(
|
||||
"Konko API key must be passed as keyword argument or "
|
||||
"set in environment variable KONKO_API_KEY."
|
||||
)
|
||||
|
||||
models_url = f"{konko_api_base}/models"
|
||||
|
||||
headers = {
|
||||
"Authorization": f"Bearer {konko_api_key}",
|
||||
}
|
||||
|
||||
if openai_api_key:
|
||||
headers["X-OpenAI-Api-Key"] = openai_api_key
|
||||
|
||||
models_response = requests.get(models_url, headers=headers)
|
||||
|
||||
if models_response.status_code != 200:
|
||||
raise ValueError(
|
||||
f"Error getting models from {models_url}: "
|
||||
f"{models_response.status_code}"
|
||||
)
|
||||
|
||||
return {model["id"] for model in models_response.json()["data"]}
|
||||
|
||||
def completion_with_retry(
|
||||
self, run_manager: Optional[CallbackManagerForLLMRun] = None, **kwargs: Any
|
||||
) -> Any:
|
||||
def _completion_with_retry(**kwargs: Any) -> Any:
|
||||
return self.client.create(**kwargs)
|
||||
|
||||
return _completion_with_retry(**kwargs)
|
||||
|
||||
def _combine_llm_outputs(self, llm_outputs: List[Optional[dict]]) -> dict:
|
||||
overall_token_usage: dict = {}
|
||||
for output in llm_outputs:
|
||||
if output is None:
|
||||
# Happens in streaming
|
||||
continue
|
||||
token_usage = output["token_usage"]
|
||||
for k, v in token_usage.items():
|
||||
if k in overall_token_usage:
|
||||
overall_token_usage[k] += v
|
||||
else:
|
||||
overall_token_usage[k] = v
|
||||
return {"token_usage": overall_token_usage, "model_name": self.model}
|
||||
|
||||
def _stream(
|
||||
self,
|
||||
messages: List[BaseMessage],
|
||||
stop: Optional[List[str]] = None,
|
||||
run_manager: Optional[CallbackManagerForLLMRun] = None,
|
||||
**kwargs: Any,
|
||||
) -> Iterator[ChatGenerationChunk]:
|
||||
message_dicts, params = self._create_message_dicts(messages, stop)
|
||||
params = {**params, **kwargs, "stream": True}
|
||||
|
||||
default_chunk_class = AIMessageChunk
|
||||
for chunk in self.completion_with_retry(
|
||||
messages=message_dicts, run_manager=run_manager, **params
|
||||
):
|
||||
if len(chunk["choices"]) == 0:
|
||||
continue
|
||||
choice = chunk["choices"][0]
|
||||
chunk = _convert_delta_to_message_chunk(
|
||||
choice["delta"], default_chunk_class
|
||||
)
|
||||
finish_reason = choice.get("finish_reason")
|
||||
generation_info = (
|
||||
dict(finish_reason=finish_reason) if finish_reason is not None else None
|
||||
)
|
||||
default_chunk_class = chunk.__class__
|
||||
yield ChatGenerationChunk(message=chunk, generation_info=generation_info)
|
||||
if run_manager:
|
||||
run_manager.on_llm_new_token(chunk.content, chunk=chunk)
|
||||
|
||||
def _generate(
|
||||
self,
|
||||
messages: List[BaseMessage],
|
||||
stop: Optional[List[str]] = None,
|
||||
run_manager: Optional[CallbackManagerForLLMRun] = None,
|
||||
stream: Optional[bool] = None,
|
||||
**kwargs: Any,
|
||||
) -> ChatResult:
|
||||
if stream if stream is not None else self.streaming:
|
||||
generation: Optional[ChatGenerationChunk] = None
|
||||
for chunk in self._stream(
|
||||
messages=messages, stop=stop, run_manager=run_manager, **kwargs
|
||||
):
|
||||
if generation is None:
|
||||
generation = chunk
|
||||
else:
|
||||
generation += chunk
|
||||
assert generation is not None
|
||||
return ChatResult(generations=[generation])
|
||||
|
||||
message_dicts, params = self._create_message_dicts(messages, stop)
|
||||
params = {**params, **kwargs}
|
||||
response = self.completion_with_retry(
|
||||
messages=message_dicts, run_manager=run_manager, **params
|
||||
)
|
||||
return self._create_chat_result(response)
|
||||
|
||||
def _create_message_dicts(
|
||||
self, messages: List[BaseMessage], stop: Optional[List[str]]
|
||||
) -> Tuple[List[Dict[str, Any]], Dict[str, Any]]:
|
||||
params = self._client_params
|
||||
if stop is not None:
|
||||
if "stop" in params:
|
||||
raise ValueError("`stop` found in both the input and default params.")
|
||||
params["stop"] = stop
|
||||
message_dicts = [convert_message_to_dict(m) for m in messages]
|
||||
return message_dicts, params
|
||||
|
||||
def _create_chat_result(self, response: Mapping[str, Any]) -> ChatResult:
|
||||
generations = []
|
||||
for res in response["choices"]:
|
||||
message = convert_dict_to_message(res["message"])
|
||||
gen = ChatGeneration(
|
||||
message=message,
|
||||
generation_info=dict(finish_reason=res.get("finish_reason")),
|
||||
)
|
||||
generations.append(gen)
|
||||
token_usage = response.get("usage", {})
|
||||
llm_output = {"token_usage": token_usage, "model_name": self.model}
|
||||
return ChatResult(generations=generations, llm_output=llm_output)
|
||||
|
||||
@property
|
||||
def _identifying_params(self) -> Dict[str, Any]:
|
||||
"""Get the identifying parameters."""
|
||||
return {**{"model_name": self.model}, **self._default_params}
|
||||
|
||||
@property
|
||||
def _client_params(self) -> Dict[str, Any]:
|
||||
"""Get the parameters used for the konko client."""
|
||||
return {**self._default_params}
|
||||
|
||||
def _get_invocation_params(
|
||||
self, stop: Optional[List[str]] = None, **kwargs: Any
|
||||
) -> Dict[str, Any]:
|
||||
"""Get the parameters used to invoke the model."""
|
||||
return {
|
||||
"model": self.model,
|
||||
**super()._get_invocation_params(stop=stop),
|
||||
**self._default_params,
|
||||
**kwargs,
|
||||
}
|
||||
|
||||
@property
|
||||
def _llm_type(self) -> str:
|
||||
"""Return type of chat model."""
|
||||
return "konko-chat"
|
||||
@@ -218,7 +218,7 @@ class ChatLiteLLM(BaseChatModel):
|
||||
not return the full n completions if duplicates are generated."""
|
||||
max_tokens: int = 256
|
||||
|
||||
max_retries: int = 6
|
||||
max_retries: int = 4
|
||||
|
||||
@property
|
||||
def _default_params(self) -> Dict[str, Any]:
|
||||
|
||||
@@ -156,7 +156,7 @@ class ChatOpenAI(BaseChatModel):
|
||||
openai_proxy: Optional[str] = None
|
||||
request_timeout: Optional[Union[float, Tuple[float, float]]] = None
|
||||
"""Timeout for requests to OpenAI completion API. Default is 600 seconds."""
|
||||
max_retries: int = 6
|
||||
max_retries: int = 4
|
||||
"""Maximum number of retries to make when generating."""
|
||||
streaming: bool = False
|
||||
"""Whether to stream the results or not."""
|
||||
|
||||
@@ -1,7 +1,5 @@
|
||||
import asyncio
|
||||
import logging
|
||||
import threading
|
||||
from functools import partial
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
import requests
|
||||
@@ -16,7 +14,6 @@ logger = logging.getLogger(__name__)
|
||||
class ErnieEmbeddings(BaseModel, Embeddings):
|
||||
"""`Ernie Embeddings V1` embedding models."""
|
||||
|
||||
ernie_api_base: Optional[str] = None
|
||||
ernie_client_id: Optional[str] = None
|
||||
ernie_client_secret: Optional[str] = None
|
||||
access_token: Optional[str] = None
|
||||
@@ -29,9 +26,6 @@ class ErnieEmbeddings(BaseModel, Embeddings):
|
||||
|
||||
@root_validator()
|
||||
def validate_environment(cls, values: Dict) -> Dict:
|
||||
values["ernie_api_base"] = get_from_dict_or_env(
|
||||
values, "ernie_api_base", "ERNIE_API_BASE", "https://aip.baidubce.com"
|
||||
)
|
||||
values["ernie_client_id"] = get_from_dict_or_env(
|
||||
values,
|
||||
"ernie_client_id",
|
||||
@@ -46,7 +40,7 @@ class ErnieEmbeddings(BaseModel, Embeddings):
|
||||
|
||||
def _embedding(self, json: object) -> dict:
|
||||
base_url = (
|
||||
f"{self.ernie_api_base}/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings"
|
||||
"https://aip.baidubce.com/rpc/2.0/ai_custom/v1/wenxinworkshop/embeddings"
|
||||
)
|
||||
resp = requests.post(
|
||||
f"{base_url}/embedding-v1",
|
||||
@@ -77,15 +71,6 @@ class ErnieEmbeddings(BaseModel, Embeddings):
|
||||
self.access_token = str(resp.json().get("access_token"))
|
||||
|
||||
def embed_documents(self, texts: List[str]) -> List[List[float]]:
|
||||
"""Embed search docs.
|
||||
|
||||
Args:
|
||||
texts: The list of texts to embed
|
||||
|
||||
Returns:
|
||||
List[List[float]]: List of embeddings, one for each text.
|
||||
"""
|
||||
|
||||
if not self.access_token:
|
||||
self._refresh_access_token_with_lock()
|
||||
text_in_chunks = [
|
||||
@@ -105,15 +90,6 @@ class ErnieEmbeddings(BaseModel, Embeddings):
|
||||
return lst
|
||||
|
||||
def embed_query(self, text: str) -> List[float]:
|
||||
"""Embed query text.
|
||||
|
||||
Args:
|
||||
text: The text to embed.
|
||||
|
||||
Returns:
|
||||
List[float]: Embeddings for the text.
|
||||
"""
|
||||
|
||||
if not self.access_token:
|
||||
self._refresh_access_token_with_lock()
|
||||
resp = self._embedding({"input": [text]})
|
||||
@@ -124,31 +100,3 @@ class ErnieEmbeddings(BaseModel, Embeddings):
|
||||
else:
|
||||
raise ValueError(f"Error from Ernie: {resp}")
|
||||
return resp["data"][0]["embedding"]
|
||||
|
||||
async def aembed_query(self, text: str) -> List[float]:
|
||||
"""Asynchronous Embed query text.
|
||||
|
||||
Args:
|
||||
text: The text to embed.
|
||||
|
||||
Returns:
|
||||
List[float]: Embeddings for the text.
|
||||
"""
|
||||
|
||||
return await asyncio.get_running_loop().run_in_executor(
|
||||
None, partial(self.embed_query, text)
|
||||
)
|
||||
|
||||
async def aembed_documents(self, texts: List[str]) -> List[List[float]]:
|
||||
"""Asynchronous Embed search docs.
|
||||
|
||||
Args:
|
||||
texts: The list of texts to embed
|
||||
|
||||
Returns:
|
||||
List[List[float]]: List of embeddings, one for each text.
|
||||
"""
|
||||
|
||||
result = await asyncio.gather(*[self.aembed_query(text) for text in texts])
|
||||
|
||||
return list(result)
|
||||
|
||||
@@ -177,7 +177,7 @@ class OpenAIEmbeddings(BaseModel, Embeddings):
|
||||
disallowed_special: Union[Literal["all"], Set[str], Sequence[str]] = "all"
|
||||
chunk_size: int = 1000
|
||||
"""Maximum number of texts to embed in each batch"""
|
||||
max_retries: int = 6
|
||||
max_retries: int = 4
|
||||
"""Maximum number of retries to make when generating."""
|
||||
request_timeout: Optional[Union[float, Tuple[float, float]]] = None
|
||||
"""Timeout in seconds for the OpenAPI request."""
|
||||
|
||||
@@ -37,7 +37,6 @@ from langchain.llms.chatglm import ChatGLM
|
||||
from langchain.llms.clarifai import Clarifai
|
||||
from langchain.llms.cohere import Cohere
|
||||
from langchain.llms.ctransformers import CTransformers
|
||||
from langchain.llms.ctranslate2 import CTranslate2
|
||||
from langchain.llms.databricks import Databricks
|
||||
from langchain.llms.deepinfra import DeepInfra
|
||||
from langchain.llms.deepsparse import DeepSparse
|
||||
@@ -101,7 +100,6 @@ __all__ = [
|
||||
"Beam",
|
||||
"Bedrock",
|
||||
"CTransformers",
|
||||
"CTranslate2",
|
||||
"CerebriumAI",
|
||||
"ChatGLM",
|
||||
"Clarifai",
|
||||
@@ -180,7 +178,6 @@ type_to_cls_dict: Dict[str, Type[BaseLLM]] = {
|
||||
"clarifai": Clarifai,
|
||||
"cohere": Cohere,
|
||||
"ctransformers": CTransformers,
|
||||
"ctranslate2": CTranslate2,
|
||||
"databricks": Databricks,
|
||||
"deepinfra": DeepInfra,
|
||||
"deepsparse": DeepSparse,
|
||||
|
||||
@@ -1,128 +0,0 @@
|
||||
from typing import Any, Dict, List, Optional, Union
|
||||
|
||||
from langchain.callbacks.manager import CallbackManagerForLLMRun
|
||||
from langchain.llms.base import BaseLLM
|
||||
from langchain.pydantic_v1 import Field, root_validator
|
||||
from langchain.schema.output import Generation, LLMResult
|
||||
|
||||
|
||||
class CTranslate2(BaseLLM):
|
||||
"""CTranslate2 language model."""
|
||||
|
||||
model_path: str = ""
|
||||
"""Path to the CTranslate2 model directory."""
|
||||
|
||||
tokenizer_name: str = ""
|
||||
"""Name of the original Hugging Face model needed to load the proper tokenizer."""
|
||||
|
||||
device: str = "cpu"
|
||||
"""Device to use (possible values are: cpu, cuda, auto)."""
|
||||
|
||||
device_index: Union[int, List[int]] = 0
|
||||
"""Device IDs where to place this generator on."""
|
||||
|
||||
compute_type: Union[str, Dict[str, str]] = "default"
|
||||
"""
|
||||
Model computation type or a dictionary mapping a device name to the computation type
|
||||
(possible values are: default, auto, int8, int8_float32, int8_float16,
|
||||
int8_bfloat16, int16, float16, bfloat16, float32).
|
||||
"""
|
||||
|
||||
max_length: int = 512
|
||||
"""Maximum generation length."""
|
||||
|
||||
sampling_topk: int = 1
|
||||
"""Randomly sample predictions from the top K candidates."""
|
||||
|
||||
sampling_topp: float = 1
|
||||
"""Keep the most probable tokens whose cumulative probability exceeds this value."""
|
||||
|
||||
sampling_temperature: float = 1
|
||||
"""Sampling temperature to generate more random samples."""
|
||||
|
||||
client: Any #: :meta private:
|
||||
|
||||
tokenizer: Any #: :meta private:
|
||||
|
||||
ctranslate2_kwargs: Dict[str, Any] = Field(default_factory=dict)
|
||||
"""
|
||||
Holds any model parameters valid for `ctranslate2.Generator` call not
|
||||
explicitly specified.
|
||||
"""
|
||||
|
||||
@root_validator()
|
||||
def validate_environment(cls, values: Dict) -> Dict:
|
||||
"""Validate that python package exists in environment."""
|
||||
|
||||
try:
|
||||
import ctranslate2
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"Could not import ctranslate2 python package. "
|
||||
"Please install it with `pip install ctranslate2`."
|
||||
)
|
||||
|
||||
try:
|
||||
import transformers
|
||||
except ImportError:
|
||||
raise ImportError(
|
||||
"Could not import transformers python package. "
|
||||
"Please install it with `pip install transformers`."
|
||||
)
|
||||
|
||||
values["client"] = ctranslate2.Generator(
|
||||
model_path=values["model_path"],
|
||||
device=values["device"],
|
||||
device_index=values["device_index"],
|
||||
compute_type=values["compute_type"],
|
||||
**values["ctranslate2_kwargs"],
|
||||
)
|
||||
|
||||
values["tokenizer"] = transformers.AutoTokenizer.from_pretrained(
|
||||
values["tokenizer_name"]
|
||||
)
|
||||
|
||||
return values
|
||||
|
||||
@property
|
||||
def _default_params(self) -> Dict[str, Any]:
|
||||
"""Get the default parameters."""
|
||||
return {
|
||||
"max_length": self.max_length,
|
||||
"sampling_topk": self.sampling_topk,
|
||||
"sampling_topp": self.sampling_topp,
|
||||
"sampling_temperature": self.sampling_temperature,
|
||||
}
|
||||
|
||||
def _generate(
|
||||
self,
|
||||
prompts: List[str],
|
||||
stop: Optional[List[str]] = None,
|
||||
run_manager: Optional[CallbackManagerForLLMRun] = None,
|
||||
**kwargs: Any,
|
||||
) -> LLMResult:
|
||||
# build sampling parameters
|
||||
params = {**self._default_params, **kwargs}
|
||||
|
||||
# call the model
|
||||
encoded_prompts = self.tokenizer(prompts)["input_ids"]
|
||||
tokenized_prompts = [
|
||||
self.tokenizer.convert_ids_to_tokens(encoded_prompt)
|
||||
for encoded_prompt in encoded_prompts
|
||||
]
|
||||
|
||||
results = self.client.generate_batch(tokenized_prompts, **params)
|
||||
|
||||
sequences = [result.sequences_ids[0] for result in results]
|
||||
decoded_sequences = [self.tokenizer.decode(seq) for seq in sequences]
|
||||
|
||||
generations = []
|
||||
for text in decoded_sequences:
|
||||
generations.append([Generation(text=text)])
|
||||
|
||||
return LLMResult(generations=generations)
|
||||
|
||||
@property
|
||||
def _llm_type(self) -> str:
|
||||
"""Return type of llm."""
|
||||
return "ctranslate2"
|
||||
@@ -174,7 +174,7 @@ class BaseOpenAI(BaseLLM):
|
||||
"""Timeout for requests to OpenAI completion API. Default is 600 seconds."""
|
||||
logit_bias: Optional[Dict[str, float]] = Field(default_factory=dict)
|
||||
"""Adjust the probability of specific tokens being generated."""
|
||||
max_retries: int = 6
|
||||
max_retries: int = 4
|
||||
"""Maximum number of retries to make when generating."""
|
||||
streaming: bool = False
|
||||
"""Whether to stream the results or not."""
|
||||
@@ -715,7 +715,7 @@ class OpenAIChat(BaseLLM):
|
||||
openai_api_base: Optional[str] = None
|
||||
# to support explicit proxy for OpenAI
|
||||
openai_proxy: Optional[str] = None
|
||||
max_retries: int = 6
|
||||
max_retries: int = 4
|
||||
"""Maximum number of retries to make when generating."""
|
||||
prefix_messages: List = Field(default_factory=list)
|
||||
"""Series of messages for Chat input."""
|
||||
|
||||
@@ -169,7 +169,7 @@ class VertexAI(_VertexAICommon, LLM):
|
||||
tuned_model_name = values.get("tuned_model_name")
|
||||
model_name = values["model_name"]
|
||||
try:
|
||||
if not is_codey_model(model_name):
|
||||
if tuned_model_name or not is_codey_model(model_name):
|
||||
from vertexai.preview.language_models import TextGenerationModel
|
||||
|
||||
if tuned_model_name:
|
||||
@@ -181,12 +181,7 @@ class VertexAI(_VertexAICommon, LLM):
|
||||
else:
|
||||
from vertexai.preview.language_models import CodeGenerationModel
|
||||
|
||||
if tuned_model_name:
|
||||
values["client"] = CodeGenerationModel.get_tuned_model(
|
||||
tuned_model_name
|
||||
)
|
||||
else:
|
||||
values["client"] = CodeGenerationModel.from_pretrained(model_name)
|
||||
values["client"] = CodeGenerationModel.from_pretrained(model_name)
|
||||
except ImportError:
|
||||
raise_vertex_import_error()
|
||||
return values
|
||||
|
||||
@@ -1,7 +1,5 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
from typing import TYPE_CHECKING, Dict, List, Optional
|
||||
from typing import Dict, List, Optional
|
||||
|
||||
from langchain.schema import (
|
||||
BaseChatMessageHistory,
|
||||
@@ -13,9 +11,6 @@ from langchain.schema.messages import (
|
||||
messages_to_dict,
|
||||
)
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from boto3.session import Session
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@@ -47,21 +42,13 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
|
||||
endpoint_url: Optional[str] = None,
|
||||
primary_key_name: str = "SessionId",
|
||||
key: Optional[Dict[str, str]] = None,
|
||||
boto3_session: Optional[Session] = None,
|
||||
):
|
||||
if boto3_session:
|
||||
client = boto3_session.resource("dynamodb")
|
||||
import boto3
|
||||
|
||||
if endpoint_url:
|
||||
client = boto3.resource("dynamodb", endpoint_url=endpoint_url)
|
||||
else:
|
||||
try:
|
||||
import boto3
|
||||
except ImportError as e:
|
||||
raise ImportError(
|
||||
"Unable to import boto3, please install with `pip install boto3`."
|
||||
) from e
|
||||
if endpoint_url:
|
||||
client = boto3.resource("dynamodb", endpoint_url=endpoint_url)
|
||||
else:
|
||||
client = boto3.resource("dynamodb")
|
||||
client = boto3.resource("dynamodb")
|
||||
self.table = client.Table(table_name)
|
||||
self.session_id = session_id
|
||||
self.key: Dict = key or {primary_key_name: session_id}
|
||||
@@ -69,12 +56,7 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
|
||||
@property
|
||||
def messages(self) -> List[BaseMessage]: # type: ignore
|
||||
"""Retrieve the messages from DynamoDB"""
|
||||
try:
|
||||
from botocore.exceptions import ClientError
|
||||
except ImportError as e:
|
||||
raise ImportError(
|
||||
"Unable to import botocore, please install with `pip install botocore`."
|
||||
) from e
|
||||
from botocore.exceptions import ClientError
|
||||
|
||||
response = None
|
||||
try:
|
||||
@@ -95,12 +77,7 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
|
||||
|
||||
def add_message(self, message: BaseMessage) -> None:
|
||||
"""Append the message to the record in DynamoDB"""
|
||||
try:
|
||||
from botocore.exceptions import ClientError
|
||||
except ImportError as e:
|
||||
raise ImportError(
|
||||
"Unable to import botocore, please install with `pip install botocore`."
|
||||
) from e
|
||||
from botocore.exceptions import ClientError
|
||||
|
||||
messages = messages_to_dict(self.messages)
|
||||
_message = _message_to_dict(message)
|
||||
@@ -113,12 +90,7 @@ class DynamoDBChatMessageHistory(BaseChatMessageHistory):
|
||||
|
||||
def clear(self) -> None:
|
||||
"""Clear session memory from DynamoDB"""
|
||||
try:
|
||||
from botocore.exceptions import ClientError
|
||||
except ImportError as e:
|
||||
raise ImportError(
|
||||
"Unable to import botocore, please install with `pip install botocore`."
|
||||
) from e
|
||||
from botocore.exceptions import ClientError
|
||||
|
||||
try:
|
||||
self.table.delete_item(self.key)
|
||||
|
||||
@@ -229,7 +229,7 @@ class ChatMessagePromptTemplate(BaseStringMessagePromptTemplate):
|
||||
|
||||
|
||||
class HumanMessagePromptTemplate(BaseStringMessagePromptTemplate):
|
||||
"""Human message prompt template. This is a message sent from the user."""
|
||||
"""Human message prompt template. This is a message that is sent to the user."""
|
||||
|
||||
def format(self, **kwargs: Any) -> BaseMessage:
|
||||
"""Format the prompt template.
|
||||
@@ -245,7 +245,7 @@ class HumanMessagePromptTemplate(BaseStringMessagePromptTemplate):
|
||||
|
||||
|
||||
class AIMessagePromptTemplate(BaseStringMessagePromptTemplate):
|
||||
"""AI message prompt template. This is a message sent from the AI."""
|
||||
"""AI message prompt template. This is a message that is not sent to the user."""
|
||||
|
||||
def format(self, **kwargs: Any) -> BaseMessage:
|
||||
"""Format the prompt template.
|
||||
|
||||
@@ -2,8 +2,8 @@
|
||||
|
||||
from typing import Any, Dict, List, Optional, Type, cast
|
||||
|
||||
from langchain import LLMChain
|
||||
from langchain.callbacks.manager import CallbackManagerForRetrieverRun
|
||||
from langchain.chains import LLMChain
|
||||
from langchain.chains.query_constructor.base import load_query_constructor_chain
|
||||
from langchain.chains.query_constructor.ir import StructuredQuery, Visitor
|
||||
from langchain.chains.query_constructor.schema import AttributeInfo
|
||||
@@ -16,8 +16,6 @@ from langchain.retrievers.self_query.milvus import MilvusTranslator
|
||||
from langchain.retrievers.self_query.myscale import MyScaleTranslator
|
||||
from langchain.retrievers.self_query.pinecone import PineconeTranslator
|
||||
from langchain.retrievers.self_query.qdrant import QdrantTranslator
|
||||
from langchain.retrievers.self_query.redis import RedisTranslator
|
||||
from langchain.retrievers.self_query.supabase import SupabaseVectorTranslator
|
||||
from langchain.retrievers.self_query.vectara import VectaraTranslator
|
||||
from langchain.retrievers.self_query.weaviate import WeaviateTranslator
|
||||
from langchain.schema import BaseRetriever, Document
|
||||
@@ -31,8 +29,6 @@ from langchain.vectorstores import (
|
||||
MyScale,
|
||||
Pinecone,
|
||||
Qdrant,
|
||||
Redis,
|
||||
SupabaseVectorStore,
|
||||
Vectara,
|
||||
VectorStore,
|
||||
Weaviate,
|
||||
@@ -41,6 +37,7 @@ from langchain.vectorstores import (
|
||||
|
||||
def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
|
||||
"""Get the translator class corresponding to the vector store class."""
|
||||
vectorstore_cls = vectorstore.__class__
|
||||
BUILTIN_TRANSLATORS: Dict[Type[VectorStore], Type[Visitor]] = {
|
||||
Pinecone: PineconeTranslator,
|
||||
Chroma: ChromaTranslator,
|
||||
@@ -52,21 +49,17 @@ def _get_builtin_translator(vectorstore: VectorStore) -> Visitor:
|
||||
DeepLake: DeepLakeTranslator,
|
||||
ElasticsearchStore: ElasticsearchTranslator,
|
||||
Milvus: MilvusTranslator,
|
||||
SupabaseVectorStore: SupabaseVectorTranslator,
|
||||
}
|
||||
if vectorstore_cls not in BUILTIN_TRANSLATORS:
|
||||
raise ValueError(
|
||||
f"Self query retriever with Vector Store type {vectorstore_cls}"
|
||||
f" not supported."
|
||||
)
|
||||
if isinstance(vectorstore, Qdrant):
|
||||
return QdrantTranslator(metadata_key=vectorstore.metadata_payload_key)
|
||||
elif isinstance(vectorstore, MyScale):
|
||||
return MyScaleTranslator(metadata_key=vectorstore.metadata_column)
|
||||
elif isinstance(vectorstore, Redis):
|
||||
return RedisTranslator.from_vectorstore(vectorstore)
|
||||
elif vectorstore.__class__ in BUILTIN_TRANSLATORS:
|
||||
return BUILTIN_TRANSLATORS[vectorstore.__class__]()
|
||||
else:
|
||||
raise ValueError(
|
||||
f"Self query retriever with Vector Store type {vectorstore.__class__}"
|
||||
f" not supported."
|
||||
)
|
||||
return BUILTIN_TRANSLATORS[vectorstore_cls]()
|
||||
|
||||
|
||||
class SelfQueryRetriever(BaseRetriever, BaseModel):
|
||||
@@ -84,9 +77,8 @@ class SelfQueryRetriever(BaseRetriever, BaseModel):
|
||||
structured_query_translator: Visitor
|
||||
"""Translator for turning internal query language into vectorstore search params."""
|
||||
verbose: bool = False
|
||||
|
||||
use_original_query: bool = False
|
||||
"""Use original query instead of the revised new query from LLM"""
|
||||
use_original_query: bool = False
|
||||
|
||||
class Config:
|
||||
"""Configuration for this pydantic object."""
|
||||
|
||||
@@ -1,102 +0,0 @@
|
||||
from __future__ import annotations
|
||||
|
||||
from typing import Any, Tuple
|
||||
|
||||
from langchain.chains.query_constructor.ir import (
|
||||
Comparator,
|
||||
Comparison,
|
||||
Operation,
|
||||
Operator,
|
||||
StructuredQuery,
|
||||
Visitor,
|
||||
)
|
||||
from langchain.vectorstores.redis import Redis
|
||||
from langchain.vectorstores.redis.filters import (
|
||||
RedisFilterExpression,
|
||||
RedisFilterField,
|
||||
RedisFilterOperator,
|
||||
RedisNum,
|
||||
RedisTag,
|
||||
RedisText,
|
||||
)
|
||||
from langchain.vectorstores.redis.schema import RedisModel
|
||||
|
||||
_COMPARATOR_TO_BUILTIN_METHOD = {
|
||||
Comparator.EQ: "__eq__",
|
||||
Comparator.NE: "__ne__",
|
||||
Comparator.LT: "__lt__",
|
||||
Comparator.GT: "__gt__",
|
||||
Comparator.LTE: "__le__",
|
||||
Comparator.GTE: "__ge__",
|
||||
Comparator.CONTAIN: "__eq__",
|
||||
Comparator.LIKE: "__mod__",
|
||||
}
|
||||
|
||||
|
||||
class RedisTranslator(Visitor):
|
||||
"""Translate"""
|
||||
|
||||
allowed_comparators = (
|
||||
Comparator.EQ,
|
||||
Comparator.NE,
|
||||
Comparator.LT,
|
||||
Comparator.LTE,
|
||||
Comparator.GT,
|
||||
Comparator.GTE,
|
||||
Comparator.CONTAIN,
|
||||
Comparator.LIKE,
|
||||
)
|
||||
"""Subset of allowed logical comparators."""
|
||||
allowed_operators = (Operator.AND, Operator.OR)
|
||||
"""Subset of allowed logical operators."""
|
||||
|
||||
def __init__(self, schema: RedisModel) -> None:
|
||||
self._schema = schema
|
||||
|
||||
def _attribute_to_filter_field(self, attribute: str) -> RedisFilterField:
|
||||
if attribute in [tf.name for tf in self._schema.text]:
|
||||
return RedisText(attribute)
|
||||
elif attribute in [tf.name for tf in self._schema.tag or []]:
|
||||
return RedisTag(attribute)
|
||||
elif attribute in [tf.name for tf in self._schema.numeric or []]:
|
||||
return RedisNum(attribute)
|
||||
else:
|
||||
raise ValueError(
|
||||
f"Invalid attribute {attribute} not in vector store schema. Schema is:"
|
||||
f"\n{self._schema.as_dict()}"
|
||||
)
|
||||
|
||||
def visit_comparison(self, comparison: Comparison) -> RedisFilterExpression:
|
||||
filter_field = self._attribute_to_filter_field(comparison.attribute)
|
||||
comparison_method = _COMPARATOR_TO_BUILTIN_METHOD[comparison.comparator]
|
||||
return getattr(filter_field, comparison_method)(comparison.value)
|
||||
|
||||
def visit_operation(self, operation: Operation) -> Any:
|
||||
left = operation.arguments[0].accept(self)
|
||||
if len(operation.arguments) > 2:
|
||||
right = self.visit_operation(
|
||||
Operation(
|
||||
operator=operation.operator, arguments=operation.arguments[1:]
|
||||
)
|
||||
)
|
||||
else:
|
||||
right = operation.arguments[1].accept(self)
|
||||
redis_operator = (
|
||||
RedisFilterOperator.OR
|
||||
if operation.operator == Operator.OR
|
||||
else RedisFilterOperator.AND
|
||||
)
|
||||
return RedisFilterExpression(operator=redis_operator, left=left, right=right)
|
||||
|
||||
def visit_structured_query(
|
||||
self, structured_query: StructuredQuery
|
||||
) -> Tuple[str, dict]:
|
||||
if structured_query.filter is None:
|
||||
kwargs = {}
|
||||
else:
|
||||
kwargs = {"filter": structured_query.filter.accept(self)}
|
||||
return structured_query.query, kwargs
|
||||
|
||||
@classmethod
|
||||
def from_vectorstore(cls, vectorstore: Redis) -> RedisTranslator:
|
||||
return cls(vectorstore._schema)
|
||||
@@ -1,97 +0,0 @@
|
||||
from typing import Any, Dict, Tuple
|
||||
|
||||
from langchain.chains.query_constructor.ir import (
|
||||
Comparator,
|
||||
Comparison,
|
||||
Operation,
|
||||
Operator,
|
||||
StructuredQuery,
|
||||
Visitor,
|
||||
)
|
||||
|
||||
|
||||
class SupabaseVectorTranslator(Visitor):
|
||||
"""Translate Langchain filters to Supabase PostgREST filters."""
|
||||
|
||||
allowed_operators = [Operator.AND, Operator.OR]
|
||||
"""Subset of allowed logical operators."""
|
||||
|
||||
allowed_comparators = [
|
||||
Comparator.EQ,
|
||||
Comparator.NE,
|
||||
Comparator.GT,
|
||||
Comparator.GTE,
|
||||
Comparator.LT,
|
||||
Comparator.LTE,
|
||||
Comparator.LIKE,
|
||||
]
|
||||
"""Subset of allowed logical comparators."""
|
||||
|
||||
metadata_column = "metadata"
|
||||
|
||||
def _map_comparator(self, comparator: Comparator) -> str:
|
||||
"""
|
||||
Maps Langchain comparator to PostgREST comparator:
|
||||
|
||||
https://postgrest.org/en/stable/references/api/tables_views.html#operators
|
||||
"""
|
||||
postgrest_comparator = {
|
||||
Comparator.EQ: "eq",
|
||||
Comparator.NE: "neq",
|
||||
Comparator.GT: "gt",
|
||||
Comparator.GTE: "gte",
|
||||
Comparator.LT: "lt",
|
||||
Comparator.LTE: "lte",
|
||||
Comparator.LIKE: "like",
|
||||
}.get(comparator)
|
||||
|
||||
if postgrest_comparator is None:
|
||||
raise Exception(
|
||||
f"Comparator '{comparator}' is not currently "
|
||||
"supported in Supabase Vector"
|
||||
)
|
||||
|
||||
return postgrest_comparator
|
||||
|
||||
def _get_json_operator(self, value: Any) -> str:
|
||||
if isinstance(value, str):
|
||||
return "->>"
|
||||
else:
|
||||
return "->"
|
||||
|
||||
def visit_operation(self, operation: Operation) -> str:
|
||||
args = [arg.accept(self) for arg in operation.arguments]
|
||||
return f"{operation.operator.value}({','.join(args)})"
|
||||
|
||||
def visit_comparison(self, comparison: Comparison) -> str:
|
||||
if isinstance(comparison.value, list):
|
||||
return self.visit_operation(
|
||||
Operation(
|
||||
operator=Operator.AND,
|
||||
arguments=(
|
||||
Comparison(
|
||||
comparator=comparison.comparator,
|
||||
attribute=comparison.attribute,
|
||||
value=value,
|
||||
)
|
||||
for value in comparison.value
|
||||
),
|
||||
)
|
||||
)
|
||||
|
||||
return ".".join(
|
||||
[
|
||||
f"{self.metadata_column}{self._get_json_operator(comparison.value)}{comparison.attribute}",
|
||||
f"{self._map_comparator(comparison.comparator)}",
|
||||
f"{comparison.value}",
|
||||
]
|
||||
)
|
||||
|
||||
def visit_structured_query(
|
||||
self, structured_query: StructuredQuery
|
||||
) -> Tuple[str, Dict[str, str]]:
|
||||
if structured_query.filter is None:
|
||||
kwargs = {}
|
||||
else:
|
||||
kwargs = {"postgrest_filter": structured_query.filter.accept(self)}
|
||||
return structured_query.query, kwargs
|
||||
@@ -254,7 +254,7 @@ class Runnable(Generic[Input, Output], ABC):
|
||||
def with_retry(
|
||||
self,
|
||||
*,
|
||||
retry_if_exception_type: Tuple[Type[BaseException], ...] = (Exception,),
|
||||
retry_if_exception_type: Tuple[Type[BaseException]] = (Exception,),
|
||||
wait_exponential_jitter: bool = True,
|
||||
stop_after_attempt: int = 3,
|
||||
) -> Runnable[Input, Output]:
|
||||
@@ -280,7 +280,7 @@ class Runnable(Generic[Input, Output], ABC):
|
||||
self,
|
||||
fallbacks: Sequence[Runnable[Input, Output]],
|
||||
*,
|
||||
exceptions_to_handle: Tuple[Type[BaseException], ...] = (Exception,),
|
||||
exceptions_to_handle: Tuple[Type[BaseException]] = (Exception,),
|
||||
) -> RunnableWithFallbacks[Input, Output]:
|
||||
return RunnableWithFallbacks(
|
||||
runnable=self,
|
||||
@@ -653,7 +653,7 @@ class RunnableWithFallbacks(Serializable, Runnable[Input, Output]):
|
||||
|
||||
runnable: Runnable[Input, Output]
|
||||
fallbacks: Sequence[Runnable[Input, Output]]
|
||||
exceptions_to_handle: Tuple[Type[BaseException], ...] = (Exception,)
|
||||
exceptions_to_handle: Tuple[Type[BaseException]] = (Exception,)
|
||||
|
||||
class Config:
|
||||
arbitrary_types_allowed = True
|
||||
|
||||
@@ -24,7 +24,7 @@ U = TypeVar("U")
|
||||
class RunnableRetry(RunnableBinding[Input, Output]):
|
||||
"""Retry a Runnable if it fails."""
|
||||
|
||||
retry_exception_types: Tuple[Type[BaseException], ...] = (Exception,)
|
||||
retry_exception_types: Tuple[Type[BaseException]] = (Exception,)
|
||||
|
||||
wait_exponential_jitter: bool = True
|
||||
|
||||
|
||||
@@ -1,729 +0,0 @@
|
||||
import random
|
||||
|
||||
adjectives = [
|
||||
"abandoned",
|
||||
"aching",
|
||||
"advanced",
|
||||
"ample",
|
||||
"artistic",
|
||||
"back",
|
||||
"best",
|
||||
"bold",
|
||||
"brief",
|
||||
"clear",
|
||||
"cold",
|
||||
"complicated",
|
||||
"cooked",
|
||||
"crazy",
|
||||
"crushing",
|
||||
"damp",
|
||||
"dear",
|
||||
"definite",
|
||||
"dependable",
|
||||
"diligent",
|
||||
"drab",
|
||||
"earnest",
|
||||
"elderly",
|
||||
"enchanted",
|
||||
"essential",
|
||||
"excellent",
|
||||
"extraneous",
|
||||
"fixed",
|
||||
"flowery",
|
||||
"formal",
|
||||
"fresh",
|
||||
"frosty",
|
||||
"giving",
|
||||
"glossy",
|
||||
"healthy",
|
||||
"helpful",
|
||||
"impressionable",
|
||||
"kind",
|
||||
"large",
|
||||
"left",
|
||||
"long",
|
||||
"loyal",
|
||||
"mealy",
|
||||
"memorable",
|
||||
"monthly",
|
||||
"new",
|
||||
"notable",
|
||||
"only",
|
||||
"ordinary",
|
||||
"passionate",
|
||||
"perfect",
|
||||
"pertinent",
|
||||
"proper",
|
||||
"puzzled",
|
||||
"reflecting",
|
||||
"respectful",
|
||||
"roasted",
|
||||
"scholarly",
|
||||
"shiny",
|
||||
"slight",
|
||||
"sparkling",
|
||||
"spotless",
|
||||
"stupendous",
|
||||
"sunny",
|
||||
"tart",
|
||||
"terrific",
|
||||
"timely",
|
||||
"unique",
|
||||
"upbeat",
|
||||
"vacant",
|
||||
"virtual",
|
||||
"warm",
|
||||
"weary",
|
||||
"whispered",
|
||||
"worthwhile",
|
||||
"yellow",
|
||||
]
|
||||
|
||||
nouns = [
|
||||
"account",
|
||||
"acknowledgment",
|
||||
"address",
|
||||
"advertising",
|
||||
"airplane",
|
||||
"animal",
|
||||
"appointment",
|
||||
"arrival",
|
||||
"artist",
|
||||
"attachment",
|
||||
"attitude",
|
||||
"availability",
|
||||
"backpack",
|
||||
"bag",
|
||||
"balance",
|
||||
"bass",
|
||||
"bean",
|
||||
"beauty",
|
||||
"bibliography",
|
||||
"bill",
|
||||
"bite",
|
||||
"blossom",
|
||||
"boat",
|
||||
"book",
|
||||
"box",
|
||||
"boy",
|
||||
"bread",
|
||||
"bridge",
|
||||
"broccoli",
|
||||
"building",
|
||||
"butter",
|
||||
"button",
|
||||
"cabbage",
|
||||
"cake",
|
||||
"camera",
|
||||
"camp",
|
||||
"candle",
|
||||
"candy",
|
||||
"canvas",
|
||||
"car",
|
||||
"card",
|
||||
"carrot",
|
||||
"cart",
|
||||
"case",
|
||||
"cat",
|
||||
"chain",
|
||||
"chair",
|
||||
"chalk",
|
||||
"chance",
|
||||
"change",
|
||||
"channel",
|
||||
"character",
|
||||
"charge",
|
||||
"charm",
|
||||
"chart",
|
||||
"check",
|
||||
"cheek",
|
||||
"cheese",
|
||||
"chef",
|
||||
"cherry",
|
||||
"chicken",
|
||||
"child",
|
||||
"church",
|
||||
"circle",
|
||||
"class",
|
||||
"clay",
|
||||
"click",
|
||||
"clock",
|
||||
"cloth",
|
||||
"cloud",
|
||||
"clove",
|
||||
"club",
|
||||
"coach",
|
||||
"coal",
|
||||
"coast",
|
||||
"coat",
|
||||
"cod",
|
||||
"coffee",
|
||||
"collar",
|
||||
"color",
|
||||
"comb",
|
||||
"comfort",
|
||||
"comic",
|
||||
"committee",
|
||||
"community",
|
||||
"company",
|
||||
"comparison",
|
||||
"competition",
|
||||
"condition",
|
||||
"connection",
|
||||
"control",
|
||||
"cook",
|
||||
"copper",
|
||||
"copy",
|
||||
"corn",
|
||||
"cough",
|
||||
"country",
|
||||
"cover",
|
||||
"crate",
|
||||
"crayon",
|
||||
"cream",
|
||||
"creator",
|
||||
"crew",
|
||||
"crown",
|
||||
"current",
|
||||
"curtain",
|
||||
"curve",
|
||||
"cushion",
|
||||
"dad",
|
||||
"daughter",
|
||||
"day",
|
||||
"death",
|
||||
"debt",
|
||||
"decision",
|
||||
"deer",
|
||||
"degree",
|
||||
"design",
|
||||
"desire",
|
||||
"desk",
|
||||
"detail",
|
||||
"development",
|
||||
"digestion",
|
||||
"dime",
|
||||
"dinner",
|
||||
"direction",
|
||||
"dirt",
|
||||
"discovery",
|
||||
"discussion",
|
||||
"disease",
|
||||
"disgust",
|
||||
"distance",
|
||||
"distribution",
|
||||
"division",
|
||||
"doctor",
|
||||
"dog",
|
||||
"door",
|
||||
"drain",
|
||||
"drawer",
|
||||
"dress",
|
||||
"drink",
|
||||
"driving",
|
||||
"dust",
|
||||
"ear",
|
||||
"earth",
|
||||
"edge",
|
||||
"education",
|
||||
"effect",
|
||||
"egg",
|
||||
"end",
|
||||
"energy",
|
||||
"engine",
|
||||
"error",
|
||||
"event",
|
||||
"example",
|
||||
"exchange",
|
||||
"existence",
|
||||
"expansion",
|
||||
"experience",
|
||||
"expert",
|
||||
"eye",
|
||||
"face",
|
||||
"fact",
|
||||
"fall",
|
||||
"family",
|
||||
"farm",
|
||||
"father",
|
||||
"fear",
|
||||
"feeling",
|
||||
"field",
|
||||
"finger",
|
||||
"fire",
|
||||
"fish",
|
||||
"flag",
|
||||
"flight",
|
||||
"floor",
|
||||
"flower",
|
||||
"fold",
|
||||
"food",
|
||||
"football",
|
||||
"force",
|
||||
"form",
|
||||
"frame",
|
||||
"friend",
|
||||
"frog",
|
||||
"fruit",
|
||||
"fuel",
|
||||
"furniture",
|
||||
"game",
|
||||
"garden",
|
||||
"gate",
|
||||
"girl",
|
||||
"glass",
|
||||
"glove",
|
||||
"goat",
|
||||
"gold",
|
||||
"government",
|
||||
"grade",
|
||||
"grain",
|
||||
"grass",
|
||||
"green",
|
||||
"grip",
|
||||
"group",
|
||||
"growth",
|
||||
"guide",
|
||||
"guitar",
|
||||
"hair",
|
||||
"hall",
|
||||
"hand",
|
||||
"harbor",
|
||||
"harmony",
|
||||
"hat",
|
||||
"head",
|
||||
"health",
|
||||
"heart",
|
||||
"heat",
|
||||
"hill",
|
||||
"history",
|
||||
"hobbies",
|
||||
"hole",
|
||||
"hope",
|
||||
"horn",
|
||||
"horse",
|
||||
"hospital",
|
||||
"hour",
|
||||
"house",
|
||||
"humor",
|
||||
"idea",
|
||||
"impulse",
|
||||
"income",
|
||||
"increase",
|
||||
"industry",
|
||||
"ink",
|
||||
"insect",
|
||||
"instrument",
|
||||
"insurance",
|
||||
"interest",
|
||||
"invention",
|
||||
"iron",
|
||||
"island",
|
||||
"jelly",
|
||||
"jet",
|
||||
"jewel",
|
||||
"join",
|
||||
"judge",
|
||||
"juice",
|
||||
"jump",
|
||||
"kettle",
|
||||
"key",
|
||||
"kick",
|
||||
"kiss",
|
||||
"kitten",
|
||||
"knee",
|
||||
"knife",
|
||||
"knowledge",
|
||||
"land",
|
||||
"language",
|
||||
"laugh",
|
||||
"law",
|
||||
"lead",
|
||||
"learning",
|
||||
"leather",
|
||||
"leg",
|
||||
"lettuce",
|
||||
"level",
|
||||
"library",
|
||||
"lift",
|
||||
"light",
|
||||
"limit",
|
||||
"line",
|
||||
"linen",
|
||||
"lip",
|
||||
"liquid",
|
||||
"list",
|
||||
"look",
|
||||
"loss",
|
||||
"love",
|
||||
"lunch",
|
||||
"machine",
|
||||
"man",
|
||||
"manager",
|
||||
"map",
|
||||
"marble",
|
||||
"mark",
|
||||
"market",
|
||||
"mass",
|
||||
"match",
|
||||
"meal",
|
||||
"measure",
|
||||
"meat",
|
||||
"meeting",
|
||||
"memory",
|
||||
"metal",
|
||||
"middle",
|
||||
"milk",
|
||||
"mind",
|
||||
"mine",
|
||||
"minute",
|
||||
"mist",
|
||||
"mitten",
|
||||
"mom",
|
||||
"money",
|
||||
"monkey",
|
||||
"month",
|
||||
"moon",
|
||||
"morning",
|
||||
"mother",
|
||||
"motion",
|
||||
"mountain",
|
||||
"mouth",
|
||||
"muscle",
|
||||
"music",
|
||||
"nail",
|
||||
"name",
|
||||
"nation",
|
||||
"neck",
|
||||
"need",
|
||||
"news",
|
||||
"night",
|
||||
"noise",
|
||||
"note",
|
||||
"number",
|
||||
"nut",
|
||||
"observation",
|
||||
"offer",
|
||||
"oil",
|
||||
"operation",
|
||||
"opinion",
|
||||
"orange",
|
||||
"order",
|
||||
"organization",
|
||||
"ornament",
|
||||
"oven",
|
||||
"page",
|
||||
"pail",
|
||||
"pain",
|
||||
"paint",
|
||||
"pan",
|
||||
"pancake",
|
||||
"paper",
|
||||
"parcel",
|
||||
"parent",
|
||||
"part",
|
||||
"passenger",
|
||||
"paste",
|
||||
"payment",
|
||||
"peace",
|
||||
"pear",
|
||||
"pen",
|
||||
"pencil",
|
||||
"person",
|
||||
"pest",
|
||||
"pet",
|
||||
"picture",
|
||||
"pie",
|
||||
"pin",
|
||||
"pipe",
|
||||
"pizza",
|
||||
"place",
|
||||
"plane",
|
||||
"plant",
|
||||
"plastic",
|
||||
"plate",
|
||||
"play",
|
||||
"pleasure",
|
||||
"plot",
|
||||
"plough",
|
||||
"pocket",
|
||||
"point",
|
||||
"poison",
|
||||
"police",
|
||||
"pollution",
|
||||
"popcorn",
|
||||
"porter",
|
||||
"position",
|
||||
"pot",
|
||||
"potato",
|
||||
"powder",
|
||||
"power",
|
||||
"price",
|
||||
"print",
|
||||
"process",
|
||||
"produce",
|
||||
"product",
|
||||
"profit",
|
||||
"property",
|
||||
"prose",
|
||||
"protest",
|
||||
"pull",
|
||||
"pump",
|
||||
"punishment",
|
||||
"purpose",
|
||||
"push",
|
||||
"quarter",
|
||||
"question",
|
||||
"quiet",
|
||||
"quill",
|
||||
"quilt",
|
||||
"quince",
|
||||
"rabbit",
|
||||
"rail",
|
||||
"rain",
|
||||
"range",
|
||||
"rat",
|
||||
"rate",
|
||||
"ray",
|
||||
"reaction",
|
||||
"reading",
|
||||
"reason",
|
||||
"record",
|
||||
"regret",
|
||||
"relation",
|
||||
"religion",
|
||||
"representative",
|
||||
"request",
|
||||
"respect",
|
||||
"rest",
|
||||
"reward",
|
||||
"rhythm",
|
||||
"rice",
|
||||
"river",
|
||||
"road",
|
||||
"roll",
|
||||
"room",
|
||||
"root",
|
||||
"rose",
|
||||
"route",
|
||||
"rub",
|
||||
"rule",
|
||||
"run",
|
||||
"sack",
|
||||
"sail",
|
||||
"salt",
|
||||
"sand",
|
||||
"scale",
|
||||
"scarecrow",
|
||||
"scarf",
|
||||
"scene",
|
||||
"scent",
|
||||
"school",
|
||||
"science",
|
||||
"scissors",
|
||||
"screw",
|
||||
"sea",
|
||||
"seat",
|
||||
"secretary",
|
||||
"seed",
|
||||
"selection",
|
||||
"self",
|
||||
"sense",
|
||||
"servant",
|
||||
"shade",
|
||||
"shake",
|
||||
"shame",
|
||||
"shape",
|
||||
"sheep",
|
||||
"sheet",
|
||||
"shelf",
|
||||
"ship",
|
||||
"shirt",
|
||||
"shock",
|
||||
"shoe",
|
||||
"shop",
|
||||
"show",
|
||||
"side",
|
||||
"sign",
|
||||
"silk",
|
||||
"sink",
|
||||
"sister",
|
||||
"size",
|
||||
"sky",
|
||||
"slave",
|
||||
"sleep",
|
||||
"smash",
|
||||
"smell",
|
||||
"smile",
|
||||
"smoke",
|
||||
"snail",
|
||||
"snake",
|
||||
"sneeze",
|
||||
"snow",
|
||||
"soap",
|
||||
"society",
|
||||
"sock",
|
||||
"soda",
|
||||
"sofa",
|
||||
"son",
|
||||
"song",
|
||||
"sort",
|
||||
"sound",
|
||||
"soup",
|
||||
"space",
|
||||
"spark",
|
||||
"speed",
|
||||
"sponge",
|
||||
"spoon",
|
||||
"spray",
|
||||
"spring",
|
||||
"spy",
|
||||
"square",
|
||||
"stamp",
|
||||
"star",
|
||||
"start",
|
||||
"statement",
|
||||
"station",
|
||||
"steam",
|
||||
"steel",
|
||||
"stem",
|
||||
"step",
|
||||
"stew",
|
||||
"stick",
|
||||
"stitch",
|
||||
"stocking",
|
||||
"stomach",
|
||||
"stone",
|
||||
"stop",
|
||||
"store",
|
||||
"story",
|
||||
"stove",
|
||||
"stranger",
|
||||
"straw",
|
||||
"stream",
|
||||
"street",
|
||||
"stretch",
|
||||
"string",
|
||||
"structure",
|
||||
"substance",
|
||||
"sugar",
|
||||
"suggestion",
|
||||
"suit",
|
||||
"summer",
|
||||
"sun",
|
||||
"support",
|
||||
"surprise",
|
||||
"sweater",
|
||||
"swim",
|
||||
"system",
|
||||
"table",
|
||||
"tail",
|
||||
"talk",
|
||||
"tank",
|
||||
"taste",
|
||||
"tax",
|
||||
"tea",
|
||||
"teaching",
|
||||
"team",
|
||||
"tendency",
|
||||
"test",
|
||||
"texture",
|
||||
"theory",
|
||||
"thing",
|
||||
"thought",
|
||||
"thread",
|
||||
"throat",
|
||||
"thumb",
|
||||
"thunder",
|
||||
"ticket",
|
||||
"time",
|
||||
"tin",
|
||||
"title",
|
||||
"toad",
|
||||
"toe",
|
||||
"tooth",
|
||||
"toothpaste",
|
||||
"touch",
|
||||
"town",
|
||||
"toy",
|
||||
"trade",
|
||||
"train",
|
||||
"transport",
|
||||
"tray",
|
||||
"treatment",
|
||||
"tree",
|
||||
"trick",
|
||||
"trip",
|
||||
"trouble",
|
||||
"trousers",
|
||||
"truck",
|
||||
"tub",
|
||||
"turkey",
|
||||
"turn",
|
||||
"twist",
|
||||
"umbrella",
|
||||
"uncle",
|
||||
"underwear",
|
||||
"unit",
|
||||
"use",
|
||||
"vacation",
|
||||
"value",
|
||||
"van",
|
||||
"vase",
|
||||
"vegetable",
|
||||
"veil",
|
||||
"vein",
|
||||
"verse",
|
||||
"vessel",
|
||||
"view",
|
||||
"visitor",
|
||||
"voice",
|
||||
"volcano",
|
||||
"walk",
|
||||
"wall",
|
||||
"war",
|
||||
"wash",
|
||||
"waste",
|
||||
"watch",
|
||||
"water",
|
||||
"wave",
|
||||
"wax",
|
||||
"way",
|
||||
"wealth",
|
||||
"weather",
|
||||
"week",
|
||||
"weight",
|
||||
"wheel",
|
||||
"whip",
|
||||
"whistle",
|
||||
"window",
|
||||
"wine",
|
||||
"wing",
|
||||
"winter",
|
||||
"wire",
|
||||
"wish",
|
||||
"woman",
|
||||
"wood",
|
||||
"wool",
|
||||
"word",
|
||||
"work",
|
||||
"worm",
|
||||
"wound",
|
||||
"wrist",
|
||||
"writer",
|
||||
"yard",
|
||||
"yoke",
|
||||
"zebra",
|
||||
"zinc",
|
||||
"zipper",
|
||||
"zone",
|
||||
]
|
||||
|
||||
|
||||
def random_name(prefix: str = "test") -> str:
|
||||
"""Generate a random name."""
|
||||
adjective = random.choice(adjectives)
|
||||
noun = random.choice(nouns)
|
||||
number = random.randint(1, 100)
|
||||
|
||||
return f"{prefix}-{adjective}-{noun}-{number}"
|
||||
@@ -1,82 +0,0 @@
|
||||
"""A simple progress bar for the console."""
|
||||
import threading
|
||||
from typing import Any, Dict, Optional, Sequence
|
||||
from uuid import UUID
|
||||
|
||||
from langchain.callbacks import base as base_callbacks
|
||||
from langchain.schema.document import Document
|
||||
from langchain.schema.output import LLMResult
|
||||
|
||||
|
||||
class ProgressBarCallback(base_callbacks.BaseCallbackHandler):
|
||||
"""A simple progress bar for the console."""
|
||||
|
||||
def __init__(self, total: int, ncols: int = 50, **kwargs: Any):
|
||||
"""Initialize the progress bar.
|
||||
|
||||
Args:
|
||||
total: int, the total number of items to be processed.
|
||||
ncols: int, the character width of the progress bar.
|
||||
"""
|
||||
self.total = total
|
||||
self.ncols = ncols
|
||||
self.counter = 0
|
||||
self.lock = threading.Lock()
|
||||
self._print_bar()
|
||||
|
||||
def increment(self) -> None:
|
||||
"""Increment the counter and update the progress bar."""
|
||||
with self.lock:
|
||||
self.counter += 1
|
||||
self._print_bar()
|
||||
|
||||
def _print_bar(self) -> None:
|
||||
"""Print the progress bar to the console."""
|
||||
progress = self.counter / self.total
|
||||
arrow = "-" * int(round(progress * self.ncols) - 1) + ">"
|
||||
spaces = " " * (self.ncols - len(arrow))
|
||||
print(f"\r[{arrow + spaces}] {self.counter}/{self.total}", end="")
|
||||
|
||||
def on_chain_end(
|
||||
self,
|
||||
outputs: Dict[str, Any],
|
||||
*,
|
||||
run_id: UUID,
|
||||
parent_run_id: Optional[UUID] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
if parent_run_id is None:
|
||||
self.increment()
|
||||
|
||||
def on_retriever_end(
|
||||
self,
|
||||
documents: Sequence[Document],
|
||||
*,
|
||||
run_id: UUID,
|
||||
parent_run_id: Optional[UUID] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
if parent_run_id is None:
|
||||
self.increment()
|
||||
|
||||
def on_llm_end(
|
||||
self,
|
||||
response: LLMResult,
|
||||
*,
|
||||
run_id: UUID,
|
||||
parent_run_id: Optional[UUID] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
if parent_run_id is None:
|
||||
self.increment()
|
||||
|
||||
def on_tool_end(
|
||||
self,
|
||||
output: str,
|
||||
*,
|
||||
run_id: UUID,
|
||||
parent_run_id: Optional[UUID] = None,
|
||||
**kwargs: Any,
|
||||
) -> Any:
|
||||
if parent_run_id is None:
|
||||
self.increment()
|
||||
File diff suppressed because it is too large
Load Diff
@@ -148,27 +148,13 @@ class ChainStringRunMapper(StringRunMapper):
|
||||
def map(self, run: Run) -> Dict[str, str]:
|
||||
"""Maps the Run to a dictionary."""
|
||||
if not run.outputs:
|
||||
raise ValueError(
|
||||
f"Run with ID {run.id} lacks outputs required for evaluation."
|
||||
" Ensure the Run has valid outputs."
|
||||
)
|
||||
raise ValueError(f"Run {run.id} has no outputs to evaluate.")
|
||||
if self.input_key is not None and self.input_key not in run.inputs:
|
||||
raise ValueError(
|
||||
f"Run with ID {run.id} is missing the expected input key"
|
||||
f" '{self.input_key}'.\nAvailable input keys in this Run"
|
||||
f" are: {run.inputs.keys()}.\nAdjust the evaluator's"
|
||||
f" input_key or ensure your input data includes key"
|
||||
f" '{self.input_key}'."
|
||||
)
|
||||
raise ValueError(f"Run {run.id} does not have input key {self.input_key}.")
|
||||
elif self.prediction_key is not None and self.prediction_key not in run.outputs:
|
||||
available_keys = ", ".join(run.outputs.keys())
|
||||
raise ValueError(
|
||||
f"Run with ID {run.id} doesn't have the expected prediction key"
|
||||
f" '{self.prediction_key}'. Available prediction keys in this Run are:"
|
||||
f" {available_keys}. Adjust the evaluator's prediction_key or"
|
||||
" ensure the Run object's outputs the expected key."
|
||||
f"Run {run.id} does not have prediction key {self.prediction_key}."
|
||||
)
|
||||
|
||||
else:
|
||||
input_ = self._get_key(run.inputs, self.input_key, "input")
|
||||
prediction = self._get_key(run.outputs, self.prediction_key, "prediction")
|
||||
|
||||
@@ -627,7 +627,6 @@ class Language(str, Enum):
|
||||
LATEX = "latex"
|
||||
HTML = "html"
|
||||
SOL = "sol"
|
||||
CSHARP = "csharp"
|
||||
|
||||
|
||||
class RecursiveCharacterTextSplitter(TextSplitter):
|
||||
@@ -1003,43 +1002,6 @@ class RecursiveCharacterTextSplitter(TextSplitter):
|
||||
"<title",
|
||||
"",
|
||||
]
|
||||
elif language == Language.CSHARP:
|
||||
return [
|
||||
"\ninterface ",
|
||||
"\nenum ",
|
||||
"\nimplements ",
|
||||
"\ndelegate ",
|
||||
"\nevent ",
|
||||
# Split along class definitions
|
||||
"\nclass ",
|
||||
"\nabstract ",
|
||||
# Split along method definitions
|
||||
"\npublic ",
|
||||
"\nprotected ",
|
||||
"\nprivate ",
|
||||
"\nstatic ",
|
||||
"\nreturn ",
|
||||
# Split along control flow statements
|
||||
"\nif ",
|
||||
"\ncontinue ",
|
||||
"\nfor ",
|
||||
"\nforeach ",
|
||||
"\nwhile ",
|
||||
"\nswitch ",
|
||||
"\nbreak ",
|
||||
"\ncase ",
|
||||
"\nelse ",
|
||||
# Split by exceptions
|
||||
"\ntry ",
|
||||
"\nthrow ",
|
||||
"\nfinally ",
|
||||
"\ncatch ",
|
||||
# Split by the normal type of lines
|
||||
"\n\n",
|
||||
"\n",
|
||||
" ",
|
||||
"",
|
||||
]
|
||||
elif language == Language.SOL:
|
||||
return [
|
||||
# Split along compiler information definitions
|
||||
@@ -1070,7 +1032,6 @@ class RecursiveCharacterTextSplitter(TextSplitter):
|
||||
" ",
|
||||
"",
|
||||
]
|
||||
|
||||
else:
|
||||
raise ValueError(
|
||||
f"Language {language} is not supported! "
|
||||
@@ -1081,9 +1042,7 @@ class RecursiveCharacterTextSplitter(TextSplitter):
|
||||
class NLTKTextSplitter(TextSplitter):
|
||||
"""Splitting text using NLTK package."""
|
||||
|
||||
def __init__(
|
||||
self, separator: str = "\n\n", language: str = "english", **kwargs: Any
|
||||
) -> None:
|
||||
def __init__(self, separator: str = "\n\n", **kwargs: Any) -> None:
|
||||
"""Initialize the NLTK splitter."""
|
||||
super().__init__(**kwargs)
|
||||
try:
|
||||
@@ -1095,12 +1054,11 @@ class NLTKTextSplitter(TextSplitter):
|
||||
"NLTK is not installed, please install it with `pip install nltk`."
|
||||
)
|
||||
self._separator = separator
|
||||
self._language = language
|
||||
|
||||
def split_text(self, text: str) -> List[str]:
|
||||
"""Split incoming text and return chunks."""
|
||||
# First we naively split the large input into a bunch of smaller ones.
|
||||
splits = self._tokenizer(text, language=self._language)
|
||||
splits = self._tokenizer(text)
|
||||
return self._merge_splits(splits, self._separator)
|
||||
|
||||
|
||||
|
||||
@@ -592,7 +592,7 @@ class StructuredTool(BaseTool):
|
||||
None, partial(self.invoke, input, config, **kwargs)
|
||||
)
|
||||
|
||||
return await super().ainvoke(input, config, **kwargs)
|
||||
return super().ainvoke(input, config, **kwargs)
|
||||
|
||||
# --- Tool ---
|
||||
|
||||
|
||||
@@ -93,7 +93,7 @@ class QuerySQLCheckerTool(BaseSQLDatabaseTool, BaseTool):
|
||||
name: str = "sql_db_query_checker"
|
||||
description: str = """
|
||||
Use this tool to double check if your query is correct before executing it.
|
||||
Always use this tool before executing a query with sql_db_query!
|
||||
Always use this tool before executing a query with query_sql_db!
|
||||
"""
|
||||
|
||||
@root_validator(pre=True)
|
||||
|
||||
@@ -17,10 +17,6 @@ def _array_to_buffer(array: List[float], dtype: Any = np.float32) -> bytes:
|
||||
return np.array(array).astype(dtype).tobytes()
|
||||
|
||||
|
||||
def _buffer_to_array(buffer: bytes, dtype: Any = np.float32) -> List[float]:
|
||||
return np.frombuffer(buffer, dtype=dtype).tolist()
|
||||
|
||||
|
||||
class TokenEscaper:
|
||||
"""
|
||||
Escape punctuation within an input string.
|
||||
|
||||
@@ -142,7 +142,6 @@ class Chroma(VectorStore):
|
||||
query_embeddings: Optional[List[List[float]]] = None,
|
||||
n_results: int = 4,
|
||||
where: Optional[Dict[str, str]] = None,
|
||||
where_document: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
"""Query the chroma collection."""
|
||||
@@ -158,7 +157,6 @@ class Chroma(VectorStore):
|
||||
query_embeddings=query_embeddings,
|
||||
n_results=n_results,
|
||||
where=where,
|
||||
where_document=where_document,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
@@ -266,7 +264,6 @@ class Chroma(VectorStore):
|
||||
embedding: List[float],
|
||||
k: int = DEFAULT_K,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
where_document: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
"""Return docs most similar to embedding vector.
|
||||
@@ -278,10 +275,7 @@ class Chroma(VectorStore):
|
||||
List of Documents most similar to the query vector.
|
||||
"""
|
||||
results = self.__query_collection(
|
||||
query_embeddings=embedding,
|
||||
n_results=k,
|
||||
where=filter,
|
||||
where_document=where_document,
|
||||
query_embeddings=embedding, n_results=k, where=filter
|
||||
)
|
||||
return _results_to_docs(results)
|
||||
|
||||
@@ -290,7 +284,6 @@ class Chroma(VectorStore):
|
||||
embedding: List[float],
|
||||
k: int = DEFAULT_K,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
where_document: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Tuple[Document, float]]:
|
||||
"""
|
||||
@@ -307,10 +300,7 @@ class Chroma(VectorStore):
|
||||
Lower score represents more similarity.
|
||||
"""
|
||||
results = self.__query_collection(
|
||||
query_embeddings=embedding,
|
||||
n_results=k,
|
||||
where=filter,
|
||||
where_document=where_document,
|
||||
query_embeddings=embedding, n_results=k, where=filter
|
||||
)
|
||||
return _results_to_docs_and_scores(results)
|
||||
|
||||
@@ -319,7 +309,6 @@ class Chroma(VectorStore):
|
||||
query: str,
|
||||
k: int = DEFAULT_K,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
where_document: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Tuple[Document, float]]:
|
||||
"""Run similarity search with Chroma with distance.
|
||||
@@ -336,18 +325,12 @@ class Chroma(VectorStore):
|
||||
"""
|
||||
if self._embedding_function is None:
|
||||
results = self.__query_collection(
|
||||
query_texts=[query],
|
||||
n_results=k,
|
||||
where=filter,
|
||||
where_document=where_document,
|
||||
query_texts=[query], n_results=k, where=filter
|
||||
)
|
||||
else:
|
||||
query_embedding = self._embedding_function.embed_query(query)
|
||||
results = self.__query_collection(
|
||||
query_embeddings=[query_embedding],
|
||||
n_results=k,
|
||||
where=filter,
|
||||
where_document=where_document,
|
||||
query_embeddings=[query_embedding], n_results=k, where=filter
|
||||
)
|
||||
|
||||
return _results_to_docs_and_scores(results)
|
||||
@@ -391,7 +374,6 @@ class Chroma(VectorStore):
|
||||
fetch_k: int = 20,
|
||||
lambda_mult: float = 0.5,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
where_document: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
"""Return docs selected using the maximal marginal relevance.
|
||||
@@ -416,7 +398,6 @@ class Chroma(VectorStore):
|
||||
query_embeddings=embedding,
|
||||
n_results=fetch_k,
|
||||
where=filter,
|
||||
where_document=where_document,
|
||||
include=["metadatas", "documents", "distances", "embeddings"],
|
||||
)
|
||||
mmr_selected = maximal_marginal_relevance(
|
||||
@@ -438,7 +419,6 @@ class Chroma(VectorStore):
|
||||
fetch_k: int = 20,
|
||||
lambda_mult: float = 0.5,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
where_document: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
"""Return docs selected using the maximal marginal relevance.
|
||||
@@ -465,12 +445,7 @@ class Chroma(VectorStore):
|
||||
|
||||
embedding = self._embedding_function.embed_query(query)
|
||||
docs = self.max_marginal_relevance_search_by_vector(
|
||||
embedding,
|
||||
k,
|
||||
fetch_k,
|
||||
lambda_mult=lambda_mult,
|
||||
filter=filter,
|
||||
where_document=where_document,
|
||||
embedding, k, fetch_k, lambda_mult=lambda_mult, filter=filter
|
||||
)
|
||||
return docs
|
||||
|
||||
@@ -497,7 +472,7 @@ class Chroma(VectorStore):
|
||||
offset: The offset to start returning results from.
|
||||
Useful for paging results with limit. Optional.
|
||||
where_document: A WhereDocument type dict used to filter by the documents.
|
||||
E.g. `{$contains: "hello"}`. Optional.
|
||||
E.g. `{$contains: {"text": "hello"}}`. Optional.
|
||||
include: A list of what to include in the results.
|
||||
Can contain `"embeddings"`, `"metadatas"`, `"documents"`.
|
||||
Ids are always included.
|
||||
|
||||
@@ -1,11 +1,9 @@
|
||||
from __future__ import annotations
|
||||
|
||||
import asyncio
|
||||
import contextlib
|
||||
import enum
|
||||
import logging
|
||||
import uuid
|
||||
from functools import partial
|
||||
from typing import (
|
||||
TYPE_CHECKING,
|
||||
Any,
|
||||
@@ -19,7 +17,6 @@ from typing import (
|
||||
Type,
|
||||
)
|
||||
|
||||
import numpy as np
|
||||
import sqlalchemy
|
||||
from sqlalchemy import delete
|
||||
from sqlalchemy.dialects.postgresql import UUID
|
||||
@@ -29,7 +26,6 @@ from langchain.docstore.document import Document
|
||||
from langchain.embeddings.base import Embeddings
|
||||
from langchain.utils import get_from_dict_or_env
|
||||
from langchain.vectorstores.base import VectorStore
|
||||
from langchain.vectorstores.utils import maximal_marginal_relevance
|
||||
|
||||
if TYPE_CHECKING:
|
||||
from langchain.vectorstores._pgvector_data_models import CollectionStore
|
||||
@@ -58,11 +54,6 @@ class BaseModel(Base):
|
||||
uuid = sqlalchemy.Column(UUID(as_uuid=True), primary_key=True, default=uuid.uuid4)
|
||||
|
||||
|
||||
def _results_to_docs(docs_and_scores: Any) -> List[Document]:
|
||||
"""Return docs from docs and scores."""
|
||||
return [doc for doc, _ in docs_and_scores]
|
||||
|
||||
|
||||
class PGVector(VectorStore):
|
||||
"""`Postgres`/`PGVector` vector store.
|
||||
|
||||
@@ -348,7 +339,7 @@ class PGVector(VectorStore):
|
||||
filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None.
|
||||
|
||||
Returns:
|
||||
List of Documents most similar to the query and score for each.
|
||||
List of Documents most similar to the query and score for each
|
||||
"""
|
||||
embedding = self.embedding_function.embed_query(query)
|
||||
docs = self.similarity_search_with_score_by_vector(
|
||||
@@ -376,31 +367,6 @@ class PGVector(VectorStore):
|
||||
k: int = 4,
|
||||
filter: Optional[dict] = None,
|
||||
) -> List[Tuple[Document, float]]:
|
||||
results = self.__query_collection(embedding=embedding, k=k, filter=filter)
|
||||
|
||||
return self._results_to_docs_and_scores(results)
|
||||
|
||||
def _results_to_docs_and_scores(self, results: Any) -> List[Tuple[Document, float]]:
|
||||
"""Return docs and scores from results."""
|
||||
docs = [
|
||||
(
|
||||
Document(
|
||||
page_content=result.EmbeddingStore.document,
|
||||
metadata=result.EmbeddingStore.cmetadata,
|
||||
),
|
||||
result.distance if self.embedding_function is not None else None,
|
||||
)
|
||||
for result in results
|
||||
]
|
||||
return docs
|
||||
|
||||
def __query_collection(
|
||||
self,
|
||||
embedding: List[float],
|
||||
k: int = 4,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
) -> List[Any]:
|
||||
"""Query the collection."""
|
||||
with Session(self._conn) as session:
|
||||
collection = self.get_collection(session)
|
||||
if not collection:
|
||||
@@ -444,7 +410,18 @@ class PGVector(VectorStore):
|
||||
.limit(k)
|
||||
.all()
|
||||
)
|
||||
return results
|
||||
|
||||
docs = [
|
||||
(
|
||||
Document(
|
||||
page_content=result.EmbeddingStore.document,
|
||||
metadata=result.EmbeddingStore.cmetadata,
|
||||
),
|
||||
result.distance if self.embedding_function is not None else None,
|
||||
)
|
||||
for result in results
|
||||
]
|
||||
return docs
|
||||
|
||||
def similarity_search_by_vector(
|
||||
self,
|
||||
@@ -466,7 +443,7 @@ class PGVector(VectorStore):
|
||||
docs_and_scores = self.similarity_search_with_score_by_vector(
|
||||
embedding=embedding, k=k, filter=filter
|
||||
)
|
||||
return _results_to_docs(docs_and_scores)
|
||||
return [doc for doc, _ in docs_and_scores]
|
||||
|
||||
@classmethod
|
||||
def from_texts(
|
||||
@@ -663,190 +640,3 @@ class PGVector(VectorStore):
|
||||
f" for distance_strategy of {self._distance_strategy}."
|
||||
"Consider providing relevance_score_fn to PGVector constructor."
|
||||
)
|
||||
|
||||
def max_marginal_relevance_search_with_score_by_vector(
|
||||
self,
|
||||
embedding: List[float],
|
||||
k: int = 4,
|
||||
fetch_k: int = 20,
|
||||
lambda_mult: float = 0.5,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Tuple[Document, float]]:
|
||||
"""Return docs selected using the maximal marginal relevance with score
|
||||
to embedding vector.
|
||||
|
||||
Maximal marginal relevance optimizes for similarity to query AND diversity
|
||||
among selected documents.
|
||||
|
||||
Args:
|
||||
embedding: Embedding to look up documents similar to.
|
||||
k (int): Number of Documents to return. Defaults to 4.
|
||||
fetch_k (int): Number of Documents to fetch to pass to MMR algorithm.
|
||||
Defaults to 20.
|
||||
lambda_mult (float): Number between 0 and 1 that determines the degree
|
||||
of diversity among the results with 0 corresponding
|
||||
to maximum diversity and 1 to minimum diversity.
|
||||
Defaults to 0.5.
|
||||
filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None.
|
||||
|
||||
Returns:
|
||||
List[Tuple[Document, float]]: List of Documents selected by maximal marginal
|
||||
relevance to the query and score for each.
|
||||
"""
|
||||
results = self.__query_collection(embedding=embedding, k=fetch_k, filter=filter)
|
||||
|
||||
embedding_list = [result.EmbeddingStore.embedding for result in results]
|
||||
|
||||
mmr_selected = maximal_marginal_relevance(
|
||||
np.array(embedding, dtype=np.float32),
|
||||
embedding_list,
|
||||
k=k,
|
||||
lambda_mult=lambda_mult,
|
||||
)
|
||||
|
||||
candidates = self._results_to_docs_and_scores(results)
|
||||
|
||||
return [r for i, r in enumerate(candidates) if i in mmr_selected]
|
||||
|
||||
def max_marginal_relevance_search(
|
||||
self,
|
||||
query: str,
|
||||
k: int = 4,
|
||||
fetch_k: int = 20,
|
||||
lambda_mult: float = 0.5,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
"""Return docs selected using the maximal marginal relevance.
|
||||
|
||||
Maximal marginal relevance optimizes for similarity to query AND diversity
|
||||
among selected documents.
|
||||
|
||||
Args:
|
||||
query (str): Text to look up documents similar to.
|
||||
k (int): Number of Documents to return. Defaults to 4.
|
||||
fetch_k (int): Number of Documents to fetch to pass to MMR algorithm.
|
||||
Defaults to 20.
|
||||
lambda_mult (float): Number between 0 and 1 that determines the degree
|
||||
of diversity among the results with 0 corresponding
|
||||
to maximum diversity and 1 to minimum diversity.
|
||||
Defaults to 0.5.
|
||||
filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None.
|
||||
|
||||
Returns:
|
||||
List[Document]: List of Documents selected by maximal marginal relevance.
|
||||
"""
|
||||
embedding = self.embedding_function.embed_query(query)
|
||||
return self.max_marginal_relevance_search_by_vector(
|
||||
embedding,
|
||||
k=k,
|
||||
fetch_k=fetch_k,
|
||||
lambda_mult=lambda_mult,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
def max_marginal_relevance_search_with_score(
|
||||
self,
|
||||
query: str,
|
||||
k: int = 4,
|
||||
fetch_k: int = 20,
|
||||
lambda_mult: float = 0.5,
|
||||
filter: Optional[dict] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Tuple[Document, float]]:
|
||||
"""Return docs selected using the maximal marginal relevance with score.
|
||||
|
||||
Maximal marginal relevance optimizes for similarity to query AND diversity
|
||||
among selected documents.
|
||||
|
||||
Args:
|
||||
query (str): Text to look up documents similar to.
|
||||
k (int): Number of Documents to return. Defaults to 4.
|
||||
fetch_k (int): Number of Documents to fetch to pass to MMR algorithm.
|
||||
Defaults to 20.
|
||||
lambda_mult (float): Number between 0 and 1 that determines the degree
|
||||
of diversity among the results with 0 corresponding
|
||||
to maximum diversity and 1 to minimum diversity.
|
||||
Defaults to 0.5.
|
||||
filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None.
|
||||
|
||||
Returns:
|
||||
List[Tuple[Document, float]]: List of Documents selected by maximal marginal
|
||||
relevance to the query and score for each.
|
||||
"""
|
||||
embedding = self.embedding_function.embed_query(query)
|
||||
docs = self.max_marginal_relevance_search_with_score_by_vector(
|
||||
embedding=embedding,
|
||||
k=k,
|
||||
fetch_k=fetch_k,
|
||||
lambda_mult=lambda_mult,
|
||||
filter=filter,
|
||||
**kwargs,
|
||||
)
|
||||
return docs
|
||||
|
||||
def max_marginal_relevance_search_by_vector(
|
||||
self,
|
||||
embedding: List[float],
|
||||
k: int = 4,
|
||||
fetch_k: int = 20,
|
||||
lambda_mult: float = 0.5,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
"""Return docs selected using the maximal marginal relevance
|
||||
to embedding vector.
|
||||
|
||||
Maximal marginal relevance optimizes for similarity to query AND diversity
|
||||
among selected documents.
|
||||
|
||||
Args:
|
||||
embedding (str): Text to look up documents similar to.
|
||||
k (int): Number of Documents to return. Defaults to 4.
|
||||
fetch_k (int): Number of Documents to fetch to pass to MMR algorithm.
|
||||
Defaults to 20.
|
||||
lambda_mult (float): Number between 0 and 1 that determines the degree
|
||||
of diversity among the results with 0 corresponding
|
||||
to maximum diversity and 1 to minimum diversity.
|
||||
Defaults to 0.5.
|
||||
filter (Optional[Dict[str, str]]): Filter by metadata. Defaults to None.
|
||||
|
||||
Returns:
|
||||
List[Document]: List of Documents selected by maximal marginal relevance.
|
||||
"""
|
||||
docs_and_scores = self.max_marginal_relevance_search_with_score_by_vector(
|
||||
embedding,
|
||||
k=k,
|
||||
fetch_k=fetch_k,
|
||||
lambda_mult=lambda_mult,
|
||||
filter=filter,
|
||||
**kwargs,
|
||||
)
|
||||
|
||||
return _results_to_docs(docs_and_scores)
|
||||
|
||||
async def amax_marginal_relevance_search_by_vector(
|
||||
self,
|
||||
embedding: List[float],
|
||||
k: int = 4,
|
||||
fetch_k: int = 20,
|
||||
lambda_mult: float = 0.5,
|
||||
filter: Optional[Dict[str, str]] = None,
|
||||
**kwargs: Any,
|
||||
) -> List[Document]:
|
||||
"""Return docs selected using the maximal marginal relevance."""
|
||||
|
||||
# This is a temporary workaround to make the similarity search
|
||||
# asynchronous. The proper solution is to make the similarity search
|
||||
# asynchronous in the vector store implementations.
|
||||
func = partial(
|
||||
self.max_marginal_relevance_search_by_vector,
|
||||
embedding,
|
||||
k=k,
|
||||
fetch_k=fetch_k,
|
||||
lambda_mult=lambda_mult,
|
||||
filter=filter,
|
||||
**kwargs,
|
||||
)
|
||||
return await asyncio.get_event_loop().run_in_executor(None, func)
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from .base import Redis, RedisVectorStoreRetriever
|
||||
from .base import Redis
|
||||
from .filters import (
|
||||
RedisFilter,
|
||||
RedisNum,
|
||||
@@ -6,11 +6,4 @@ from .filters import (
|
||||
RedisText,
|
||||
)
|
||||
|
||||
__all__ = [
|
||||
"Redis",
|
||||
"RedisFilter",
|
||||
"RedisTag",
|
||||
"RedisText",
|
||||
"RedisNum",
|
||||
"RedisVectorStoreRetriever",
|
||||
]
|
||||
__all__ = ["Redis", "RedisFilter", "RedisTag", "RedisText", "RedisNum"]
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user