blob42
/
langchain
forked from Archives/langchain
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Add Qdrant named arguments (#1386)

Browse Source 
This PR:
- Increases `qdrant-client` version to 1.0.4
- Introduces custom content and metadata keys (as requested in #1087)
- Moves all the `QdrantClient` parameters into the method parameters to
simplify code completion
searx-doc
Kacper Łukawski 1 year ago committed by GitHub
parent 34abcd31b9
commit 9ac442624c
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
15 changed files with 1128 additions and 849 deletions
Show Stats Download Patch File Download Diff File

18
docs/modules/agents/examples/load_from_hub.ipynb
Unescape Escape View File

@ -29,16 +29,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3m2016 · SUI · Stan Wawrinka ; 2017 · ESP · Rafael Nadal ; 2018 · SRB · Novak Djokovic ; 2019 · ESP · Rafael Nadal.\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mSo the reigning men's U.S. Open champion is Rafael Nadal.\n",
"Follow up: What is Rafael Nadal's hometown?\u001b[0m\n",
"Intermediate answer: \u001b[36;1m\u001b[1;3mIn 2016, he once again showed his deep ties to Mallorca and opened the Rafa Nadal Academy in his hometown of Manacor.\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mSo the final answer is: Manacor, Mallorca, Spain.\u001b[0m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m Yes.\n",
"Follow up: Who is the reigning men's U.S. Open champion?\u001B[0m\n",
"Intermediate answer: \u001B[36;1m\u001B[1;3m2016 · SUI · Stan Wawrinka ; 2017 · ESP · Rafael Nadal ; 2018 · SRB · Novak Djokovic ; 2019 · ESP · Rafael Nadal.\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mSo the reigning men's U.S. Open champion is Rafael Nadal.\n",
"Follow up: What is Rafael Nadal's hometown?\u001B[0m\n",
"Intermediate answer: \u001B[36;1m\u001B[1;3mIn 2016, he once again showed his deep ties to Mallorca and opened the Rafa Nadal Academy in his hometown of Manacor.\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mSo the final answer is: Manacor, Mallorca, Spain.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

4
docs/modules/chains/async_chain.ipynb
Unescape Escape View File

@ -39,7 +39,7 @@
"\n",
"\n",
"SparkleSmile Toothpaste\n",
"\u001b[1mConcurrent executed in 1.54 seconds.\u001b[0m\n",
"\u001B[1mConcurrent executed in 1.54 seconds.\u001B[0m\n",
"\n",
"\n",
"BrightSmile Toothpaste Co.\n",
@ -55,7 +55,7 @@
"\n",
"\n",
"BrightSmile Toothpaste.\n",
"\u001b[1mSerial executed in 6.38 seconds.\u001b[0m\n"
"\u001B[1mSerial executed in 6.38 seconds.\u001B[0m\n"
]
}
],

24
docs/modules/chains/examples/pal.ipynb
Unescape Escape View File

@ -71,17 +71,17 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mdef solution():\n",
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mdef solution():\n",
" \"\"\"Jan has three times the number of pets as Marcia. Marcia has two more pets than Cindy. If Cindy has four pets, how many total pets do the three have?\"\"\"\n",
" cindy_pets = 4\n",
" marcia_pets = cindy_pets + 2\n",
" jan_pets = marcia_pets * 3\n",
" total_pets = cindy_pets + marcia_pets + jan_pets\n",
" result = total_pets\n",
" return result\u001b[0m\n",
" return result\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -139,8 +139,8 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m# Put objects into a list to record ordering\n",
"objects = []\n",
"objects += [('booklet', 'blue')] * 2\n",
"objects += [('booklet', 'purple')] * 2\n",
@ -151,9 +151,9 @@
"\n",
"# Count number of purple objects\n",
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
"answer = num_purple\u001b[0m\n",
"answer = num_purple\u001B[0m\n",
"\n",
"\u001b[1m> Finished PALChain chain.\u001b[0m\n"
"\u001B[1m> Finished PALChain chain.\u001B[0m\n"
]
},
{
@ -212,8 +212,8 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new PALChain chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m# Put objects into a list to record ordering\n",
"\u001B[1m> Entering new PALChain chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m# Put objects into a list to record ordering\n",
"objects = []\n",
"objects += [('booklet', 'blue')] * 2\n",
"objects += [('booklet', 'purple')] * 2\n",
@ -224,9 +224,9 @@
"\n",
"# Count number of purple objects\n",
"num_purple = len([object for object in objects if object[1] == 'purple'])\n",
"answer = num_purple\u001b[0m\n",
"answer = num_purple\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
}
],

8
docs/modules/chains/generic/from_hub.ipynb
Unescape Escape View File

@ -34,10 +34,10 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMMathChain chain...\u001b[0m\n",
"whats 2 raised to .12\u001b[32;1m\u001b[1;3m\n",
"Answer: 1.0791812460476249\u001b[0m\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Entering new LLMMathChain chain...\u001B[0m\n",
"whats 2 raised to .12\u001B[32;1m\u001B[1;3m\n",
"Answer: 1.0791812460476249\u001B[0m\n",
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

14
docs/modules/chains/generic/llm_chain.ipynb
Unescape Escape View File

@ -42,13 +42,13 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mQuestion: What NFL team won the Super Bowl in the year Justin Beiber was born?\n",
"\u001B[32;1m\u001B[1;3mQuestion: What NFL team won the Super Bowl in the year Justin Beiber was born?\n",
"\n",
"Answer: Let's think step by step.\u001b[0m\n",
"Answer: Let's think step by step.\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n"
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n"
]
},
{
@ -95,11 +95,11 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mWrite a sad poem about ducks.\u001b[0m\n",
"\u001B[32;1m\u001B[1;3mWrite a sad poem about ducks.\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n"
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n"
]
},
{

16
docs/modules/chains/generic/serialization.ipynb
Unescape Escape View File

@ -136,13 +136,13 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mQuestion: whats 2 + 2\n",
"\u001B[32;1m\u001B[1;3mQuestion: whats 2 + 2\n",
"\n",
"Answer: Let's think step by step.\u001b[0m\n",
"Answer: Let's think step by step.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -319,13 +319,13 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mQuestion: whats 2 + 2\n",
"\u001B[32;1m\u001B[1;3mQuestion: whats 2 + 2\n",
"\n",
"Answer: Let's think step by step.\u001b[0m\n",
"Answer: Let's think step by step.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

10
docs/modules/indexes/chain_examples/graph_qa.ipynb
Unescape Escape View File

@ -178,16 +178,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new GraphQAChain chain...\u001b[0m\n",
"\u001B[1m> Entering new GraphQAChain chain...\u001B[0m\n",
"Entities Extracted:\n",
"\u001b[32;1m\u001b[1;3m Intel\u001b[0m\n",
"\u001B[32;1m\u001B[1;3m Intel\u001B[0m\n",
"Full Context:\n",
"\u001b[32;1m\u001b[1;3mIntel is going to build $20 billion semiconductor \"mega site\"\n",
"\u001B[32;1m\u001B[1;3mIntel is going to build $20 billion semiconductor \"mega site\"\n",
"Intel is building state-of-the-art factories\n",
"Intel is creating 10,000 new good-paying jobs\n",
"Intel is helping build Silicon Valley\u001b[0m\n",
"Intel is helping build Silicon Valley\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

14
docs/modules/llms/examples/fake_llm.ipynb
Unescape Escape View File

@ -80,14 +80,14 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3mAction: Python REPL\n",
"Action Input: print(2 + 2)\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3m4\n",
"\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3mFinal Answer: 4\u001b[0m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3mAction: Python REPL\n",
"Action Input: print(2 + 2)\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3m4\n",
"\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3mFinal Answer: 4\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

112
docs/modules/memory/examples/chatgpt_clone.ipynb
Unescape Escape View File

@ -24,9 +24,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -36,9 +36,9 @@
"\n",
"\n",
"Human: I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"```\n",
"$ pwd\n",
@ -93,9 +93,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -110,9 +110,9 @@
"/\n",
"```\n",
"Human: ls ~\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"```\n",
"$ ls ~\n",
@ -138,9 +138,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -161,9 +161,9 @@
"Desktop Documents Downloads Music Pictures Public Templates Videos\n",
"```\n",
"Human: cd ~\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
" \n",
"```\n",
"$ cd ~\n",
@ -190,9 +190,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -214,9 +214,9 @@
"/home/user\n",
"```\n",
"Human: {Please make a file jokes.txt inside and put some jokes inside}\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -245,9 +245,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -272,9 +272,9 @@
"$ echo \"Why did the scarecrow win the Nobel Prize? Because he was outstanding in his field!\" >> jokes.txt\n",
"```\n",
"Human: echo -e \"x=lambda y:y*5+3;print('Result:' + str(x(6)))\" > run.py && python3 run.py\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -304,9 +304,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -332,9 +332,9 @@
"Result: 33\n",
"```\n",
"Human: echo -e \"print(list(filter(lambda x: all(x%d for d in range(2,x)),range(2,3**10)))[:10])\" > run.py && python3 run.py\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -362,9 +362,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -391,9 +391,9 @@
"Human: echo -e \"echo 'Hello from Docker\" > entrypoint.sh && echo -e \"FROM ubuntu:20.04\n",
"COPY entrypoint.sh entrypoint.sh\n",
"ENTRYPOINT [\"/bin/sh\",\"entrypoint.sh\"]\">Dockerfile && docker build . -t my_docker_image && docker run -t my_docker_image\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -426,9 +426,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -459,9 +459,9 @@
"Hello from Docker\n",
"```\n",
"Human: nvidia-smi\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -502,9 +502,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -548,9 +548,9 @@
"|=============================================================================|\n",
"\n",
"Human: ping bbc.com\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -584,9 +584,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -630,9 +630,9 @@
"round-trip min/avg/max/stddev = 14.945/14.945/14.945/0.000 ms\n",
"```\n",
"Human: curl -fsSL \"https://api.github.com/repos/pytorch/pytorch/releases/latest\" | jq -r '.tag_name' | sed 's/[^0-9\\.\\-]*//g'\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -659,9 +659,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -691,9 +691,9 @@
"1.8.1\n",
"```\n",
"Human: lynx https://www.deepmind.com/careers\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -726,9 +726,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -757,9 +757,9 @@
"Explore our current openings and apply today. We look forward to hearing from you.\n",
"```\n",
"Human: curl https://chat.openai.com/chat\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
" \n",
"\n",
"```\n",
@ -799,9 +799,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -843,9 +843,9 @@
"</html>\n",
"```\n",
"Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"What is artificial intelligence?\"}' https://chat.openai.com/chat\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
"\n",
"\n",
"```\n",
@ -875,9 +875,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new LLMChain chain...\u001b[0m\n",
"\u001B[1m> Entering new LLMChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mAssistant is a large language model trained by OpenAI.\n",
"\u001B[32;1m\u001B[1;3mAssistant is a large language model trained by OpenAI.\n",
"\n",
"Assistant is designed to be able to assist with a wide range of tasks, from answering simple questions to providing in-depth explanations and discussions on a wide range of topics. As a language model, Assistant is able to generate human-like text based on the input it receives, allowing it to engage in natural-sounding conversations and provide responses that are coherent and relevant to the topic at hand.\n",
"\n",
@ -916,9 +916,9 @@
"}\n",
"```\n",
"Human: curl --header \"Content-Type:application/json\" --request POST --data '{\"message\": \"I want you to act as a Linux terminal. I will type commands and you will reply with what the terminal should show. I want you to only reply with the terminal output inside one unique code block, and nothing else. Do not write explanations. Do not type commands unless I instruct you to do so. When I need to tell you something in English I will do so by putting text inside curly brackets {like this}. My first command is pwd.\"}' https://chat.openai.com/chat\n",
"Assistant:\u001b[0m\n",
"Assistant:\u001B[0m\n",
"\n",
"\u001b[1m> Finished LLMChain chain.\u001b[0m\n",
"\u001B[1m> Finished LLMChain chain.\u001B[0m\n",
" \n",
"\n",
"```\n",

52
docs/modules/memory/examples/conversational_agent.ipynb
Unescape Escape View File

@ -76,12 +76,12 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? No\n",
"AI: Hi Bob, nice to meet you! How can I help you today?\u001b[0m\n",
"AI: Hi Bob, nice to meet you! How can I help you today?\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -111,12 +111,12 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? No\n",
"AI: Your name is Bob!\u001b[0m\n",
"AI: Your name is Bob!\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -146,12 +146,12 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? No\n",
"AI: If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!\u001b[0m\n",
"AI: If you like Thai food, some great dinner options this week could include Thai green curry, Pad Thai, or a Thai-style stir-fry. You could also try making a Thai-style soup or salad. Enjoy!\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -181,16 +181,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? Yes\n",
"Action: Current Search\n",
"Action Input: Who won the World Cup in 1978\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mThe Cup was won by the host nation, Argentina, who defeated the Netherlands 3–1 in the final, after extra time. The final was held at River Plate's home stadium ... Amid Argentina's celebrations, there was sympathy for the Netherlands, runners-up for the second tournament running, following a 3-1 final defeat at the Estadio ... The match was won by the Argentine squad in extra time by a score of 3–1. Mario Kempes, who finished as the tournament's top scorer, was named the man of the ... May 21, 2022 ... Argentina won the World Cup for the first time in their history, beating Netherlands 3-1 in the final. This edition of the World Cup was full of ... The adidas Golden Ball is presented to the best player at each FIFA World Cup finals. Those who finish as runners-up in the vote receive the adidas Silver ... Holders West Germany failed to beat Holland and Italy and were eliminated when Berti Vogts' own goal gave Austria a 3-2 victory. Holland thrashed the Austrians ... Jun 14, 2018 ... On a clear afternoon on 1 June 1978 at the revamped El Monumental stadium in Buenos Aires' Belgrano barrio, several hundred children in white ... Dec 15, 2022 ... The tournament couldn't have gone better for the ruling junta. Argentina went on to win the championship, defeating the Netherlands, 3-1, in the ... Nov 9, 2022 ... Host: Argentina Teams: 16. Format: Group stage, second round, third-place playoff, final. Matches: 38. Goals: 102. Winner: Argentina Feb 19, 2009 ... Argentina sealed their first World Cup win on home soil when they defeated the Netherlands in an exciting final that went to extra-time. For the ...\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
"AI: The last letter in your name is 'b'. Argentina won the World Cup in 1978.\u001b[0m\n",
"Action Input: Who won the World Cup in 1978\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mThe Cup was won by the host nation, Argentina, who defeated the Netherlands 3–1 in the final, after extra time. The final was held at River Plate's home stadium ... Amid Argentina's celebrations, there was sympathy for the Netherlands, runners-up for the second tournament running, following a 3-1 final defeat at the Estadio ... The match was won by the Argentine squad in extra time by a score of 3–1. Mario Kempes, who finished as the tournament's top scorer, was named the man of the ... May 21, 2022 ... Argentina won the World Cup for the first time in their history, beating Netherlands 3-1 in the final. This edition of the World Cup was full of ... The adidas Golden Ball is presented to the best player at each FIFA World Cup finals. Those who finish as runners-up in the vote receive the adidas Silver ... Holders West Germany failed to beat Holland and Italy and were eliminated when Berti Vogts' own goal gave Austria a 3-2 victory. Holland thrashed the Austrians ... Jun 14, 2018 ... On a clear afternoon on 1 June 1978 at the revamped El Monumental stadium in Buenos Aires' Belgrano barrio, several hundred children in white ... Dec 15, 2022 ... The tournament couldn't have gone better for the ruling junta. Argentina went on to win the championship, defeating the Netherlands, 3-1, in the ... Nov 9, 2022 ... Host: Argentina Teams: 16. Format: Group stage, second round, third-place playoff, final. Matches: 38. Goals: 102. Winner: Argentina Feb 19, 2009 ... Argentina sealed their first World Cup win on home soil when they defeated the Netherlands in an exciting final that went to extra-time. For the ...\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m Do I need to use a tool? No\n",
"AI: The last letter in your name is 'b'. Argentina won the World Cup in 1978.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -220,16 +220,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
"\u001b[32;1m\u001b[1;3m\n",
"\u001B[1m> Entering new AgentExecutor chain...\u001B[0m\n",
"\u001B[32;1m\u001B[1;3m\n",
"Thought: Do I need to use a tool? Yes\n",
"Action: Current Search\n",
"Action Input: Current temperature in Pomfret\u001b[0m\n",
"Observation: \u001b[36;1m\u001b[1;3mA mixture of rain and snow showers. High 39F. Winds NNW at 5 to 10 mph. Chance of precip 50%. Snow accumulations less than one inch. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Pomfret Center Weather Forecasts. ... Pomfret Center, CT Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be COOLER than today. It is 46 degrees fahrenheit, or 8 degrees celsius and feels like 46 degrees fahrenheit. The barometric pressure is 29.78 - measured by inch of mercury units - ... Pomfret Weather Forecasts. ... Pomfret, MD Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be MUCH COOLER than today. Additional Headlines. En Español · Share |. Current conditions at ... Pomfret CT. Tonight ... Past Weather Information · Interactive Forecast Map. Pomfret MD detailed current weather report for 20675 in Charles county, Maryland. ... Pomfret, MD weather condition is Mostly Cloudy and 43°F. Mostly Cloudy. Hazardous Weather Conditions. Hazardous Weather Outlook · En Español · Share |. Current conditions at ... South Pomfret VT. Tonight. Pomfret Center, CT Weather. Current Report for Thu Jan 5 2023. As of 2:00 PM EST. 5-Day Forecast | Road Conditions. 45°F 7°c. Feels Like 44°F. Pomfret Center CT. Today. Today: Areas of fog before 9am. Otherwise, cloudy, with a ... Otherwise, cloudy, with a temperature falling to around 33 by 5pm.\u001b[0m\n",
"Thought:\u001b[32;1m\u001b[1;3m Do I need to use a tool? No\n",
"AI: The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.\u001b[0m\n",
"Action Input: Current temperature in Pomfret\u001B[0m\n",
"Observation: \u001B[36;1m\u001B[1;3mA mixture of rain and snow showers. High 39F. Winds NNW at 5 to 10 mph. Chance of precip 50%. Snow accumulations less than one inch. Pomfret, CT Weather Forecast, with current conditions, wind, air quality, and what to expect for the next 3 days. Pomfret Center Weather Forecasts. ... Pomfret Center, CT Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be COOLER than today. It is 46 degrees fahrenheit, or 8 degrees celsius and feels like 46 degrees fahrenheit. The barometric pressure is 29.78 - measured by inch of mercury units - ... Pomfret Weather Forecasts. ... Pomfret, MD Weather Conditionsstar_ratehome ... Tomorrow's temperature is forecast to be MUCH COOLER than today. Additional Headlines. En Español · Share |. Current conditions at ... Pomfret CT. Tonight ... Past Weather Information · Interactive Forecast Map. Pomfret MD detailed current weather report for 20675 in Charles county, Maryland. ... Pomfret, MD weather condition is Mostly Cloudy and 43°F. Mostly Cloudy. Hazardous Weather Conditions. Hazardous Weather Outlook · En Español · Share |. Current conditions at ... South Pomfret VT. Tonight. Pomfret Center, CT Weather. Current Report for Thu Jan 5 2023. As of 2:00 PM EST. 5-Day Forecast | Road Conditions. 45°F 7°c. Feels Like 44°F. Pomfret Center CT. Today. Today: Areas of fog before 9am. Otherwise, cloudy, with a ... Otherwise, cloudy, with a temperature falling to around 33 by 5pm.\u001B[0m\n",
"Thought:\u001B[32;1m\u001B[1;3m Do I need to use a tool? No\n",
"AI: The current temperature in Pomfret is 45°F (7°C) and it feels like 44°F.\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

136
docs/modules/memory/getting_started.ipynb
Unescape Escape View File

@ -51,16 +51,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi there!\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -90,18 +90,18 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi there!\n",
"AI: Hi there! It's nice to meet you. How can I help you today?\n",
"Human: I'm doing well! Just having a conversation with an AI.\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -131,9 +131,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
@ -142,9 +142,9 @@
"Human: I'm doing well! Just having a conversation with an AI.\n",
"AI: That's great! It's always nice to have a conversation with someone new. What would you like to talk about?\n",
"Human: Tell me about yourself.\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -195,16 +195,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi, what's up?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -239,17 +239,17 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"The human greets the AI and the AI responds, saying it is doing well and is currently helping a customer with a technical issue.\n",
"Human: Tell me more about it!\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -279,18 +279,18 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"\n",
"The human greets the AI and the AI responds, saying it is doing well and is currently helping a customer with a technical issue. The customer is having trouble with their computer not connecting to the internet, and the AI is helping them troubleshoot the issue by resetting the router and checking the network settings. They are still looking into other possible causes.\n",
"Human: Very cool -- what is the scope of the project?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -342,16 +342,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi, what's up?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -387,17 +387,17 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"Human: Hi, what's up?\n",
"AI: Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\n",
"Human: What's their issues?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -427,9 +427,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"Human: Hi, what's up?\n",
@ -437,9 +437,9 @@
"Human: What's their issues?\n",
"AI: The customer is having trouble connecting to their Wi-Fi network. I'm helping them troubleshoot the issue and get them connected.\n",
"Human: Is it going well?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -469,9 +469,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"Human: What's their issues?\n",
@ -479,9 +479,9 @@
"Human: Is it going well?\n",
"AI: Yes, it's going well so far. We've already identified the problem and are now working on a solution.\n",
"Human: What's the solution?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -534,16 +534,16 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"Human: Hi, what's up?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -579,17 +579,17 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"Human: Hi, what's up?\n",
"AI: Hi there! I'm doing great. I'm currently helping a customer with a technical issue. How about you?\n",
"Human: Just working on writing some documentation!\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -619,9 +619,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
@ -629,9 +629,9 @@
"Human: Just working on writing some documentation!\n",
"AI: That sounds like a lot of work. What kind of documentation are you writing?\n",
"Human: For LangChain! Have you heard of it?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -662,18 +662,18 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. If the AI does not know the answer to a question, it truthfully says it does not know.\n",
"\n",
"Current conversation:\n",
"\n",
"The human asked the AI what it was up to, and the AI responded that it was helping a customer with a technical issue. The human then mentioned they were writing documentation for LangChain, a blockchain-based language learning platform, and the AI revealed they had heard of it and asked the human to tell them more about the documentation they were writing.\n",
"\n",
"Human: Haha nope, although a lot of people confuse it for that\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished ConversationChain chain.\u001b[0m\n"
"\u001B[1m> Finished ConversationChain chain.\u001B[0m\n"
]
},
{
@ -755,9 +755,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
@ -766,9 +766,9 @@
"\n",
"Conversation:\n",
"Human: Hi, what's up?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -798,9 +798,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
@ -809,9 +809,9 @@
"\n",
"Conversation:\n",
"Human: My name is James and I'm helping Will. He's an engineer.\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{
@ -841,9 +841,9 @@
"text": [
"\n",
"\n",
"\u001b[1m> Entering new ConversationChain chain...\u001b[0m\n",
"\u001B[1m> Entering new ConversationChain chain...\u001B[0m\n",
"Prompt after formatting:\n",
"\u001b[32;1m\u001b[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"\u001B[32;1m\u001B[1;3mThe following is a friendly conversation between a human and an AI. The AI is talkative and provides lots of specific details from its context. \n",
"If the AI does not know the answer to a question, it truthfully says it does not know. The AI ONLY uses information contained in the \"Relevant Information\" section and does not hallucinate.\n",
"\n",
"Relevant Information:\n",
@ -852,9 +852,9 @@
"\n",
"Conversation:\n",
"Human: What do you know about Will?\n",
"AI:\u001b[0m\n",
"AI:\u001B[0m\n",
"\n",
"\u001b[1m> Finished chain.\u001b[0m\n"
"\u001B[1m> Finished chain.\u001B[0m\n"
]
},
{

181
langchain/vectorstores/qdrant.py
Unescape Escape View File

@ -1,11 +1,10 @@
"""Wrapper around Qdrant vector database."""
import uuid
from operator import itemgetter
from typing import Any, Callable, Iterable, List, Optional, Tuple
from typing import Any, Callable, Iterable, List, Optional, Tuple, cast
from langchain.docstore.document import Document
from langchain.embeddings.base import Embeddings
from langchain.utils import get_from_dict_or_env
from langchain.vectorstores import VectorStore
from langchain.vectorstores.utils import maximal_marginal_relevance
@ -28,7 +27,14 @@ class Qdrant(VectorStore):
CONTENT_KEY = "page_content"
METADATA_KEY = "metadata"
def __init__(self, client: Any, collection_name: str, embedding_function: Callable):
def __init__(
self,
client: Any,
collection_name: str,
embedding_function: Callable,
content_payload_key: str = CONTENT_KEY,
metadata_payload_key: str = METADATA_KEY,
):
"""Initialize with necessary components."""
try:
import qdrant_client
@ -47,6 +53,8 @@ class Qdrant(VectorStore):
self.client: qdrant_client.QdrantClient = client
self.collection_name = collection_name
self.embedding_function = embedding_function
self.content_payload_key = content_payload_key or self.CONTENT_KEY
self.metadata_payload_key = metadata_payload_key or self.METADATA_KEY
def add_texts(
self,
@ -71,7 +79,12 @@ class Qdrant(VectorStore):
points=rest.Batch(
ids=ids,
vectors=[self.embedding_function(text) for text in texts],
payloads=self._build_payloads(texts, metadatas),
payloads=self._build_payloads(
texts,
metadatas,
self.content_payload_key,
self.metadata_payload_key,
),
),
)
@ -113,7 +126,9 @@ class Qdrant(VectorStore):
)
return [
(
self._document_from_scored_point(result),
self._document_from_scored_point(
result, self.content_payload_key, self.metadata_payload_key
),
result.score,
)
for result in results
@ -145,7 +160,54 @@ class Qdrant(VectorStore):
)
embeddings = [result.vector for result in results]
mmr_selected = maximal_marginal_relevance(embedding, embeddings, k=k)
return [self._document_from_scored_point(results[i]) for i in mmr_selected]
return [
self._document_from_scored_point(
results[i], self.content_payload_key, self.metadata_payload_key
)
for i in mmr_selected
]
@classmethod
def from_documents(
cls,
documents: List[Document],
embedding: Embeddings,
url: Optional[str] = None,
port: Optional[int] = 6333,
grpc_port: int = 6334,
prefer_grpc: bool = False,
https: Optional[bool] = None,
api_key: Optional[str] = None,
prefix: Optional[str] = None,
timeout: Optional[float] = None,
host: Optional[str] = None,
collection_name: Optional[str] = None,
distance_func: str = "Cosine",
content_payload_key: str = CONTENT_KEY,
metadata_payload_key: str = METADATA_KEY,
**kwargs: Any,
) -> "Qdrant":
return cast(
Qdrant,
super().from_documents(
documents,
embedding,
url=url,
port=port,
grpc_port=grpc_port,
prefer_grpc=prefer_grpc,
https=https,
api_key=api_key,
prefix=prefix,
timeout=timeout,
host=host,
collection_name=collection_name,
distance_func=distance_func,
content_payload_key=content_payload_key,
metadata_payload_key=metadata_payload_key,
**kwargs,
),
)
@classmethod
def from_texts(
@ -153,10 +215,60 @@ class Qdrant(VectorStore):
texts: List[str],
embedding: Embeddings,
metadatas: Optional[List[dict]] = None,
url: Optional[str] = None,
port: Optional[int] = 6333,
grpc_port: int = 6334,
prefer_grpc: bool = False,
https: Optional[bool] = None,
api_key: Optional[str] = None,
prefix: Optional[str] = None,
timeout: Optional[float] = None,
host: Optional[str] = None,
collection_name: Optional[str] = None,
distance_func: str = "Cosine",
content_payload_key: str = CONTENT_KEY,
metadata_payload_key: str = METADATA_KEY,
**kwargs: Any,
) -> "Qdrant":
"""Construct Qdrant wrapper from raw documents.
Args:
texts: A list of texts to be indexed in Qdrant.
embedding: A subclass of `Embeddings`, responsible for text vectorization.
metadatas:
An optional list of metadata. If provided it has to be of the same
length as a list of texts.
url: either host or str of "Optional[scheme], host, Optional[port],
Optional[prefix]". Default: `None`
port: Port of the REST API interface. Default: 6333
grpc_port: Port of the gRPC interface. Default: 6334
prefer_grpc:
If `true` - use gPRC interface whenever possible in custom methods.
https: If `true` - use HTTPS(SSL) protocol. Default: `None`
api_key: API key for authentication in Qdrant Cloud. Default: `None`
prefix:
If not `None` - add `prefix` to the REST URL path.
Example: `service/v1` will result in
`http://localhost:6333/service/v1/{qdrant-endpoint}` for REST API.
Default: `None`
timeout:
Timeout for REST and gRPC API requests.
Default: 5.0 seconds for REST and unlimited for gRPC
host:
Host name of Qdrant service. If url and host are None, set to
'localhost'. Default: `None`
collection_name:
Name of the Qdrant collection to be used. If not provided,
will be created randomly.
distance_func:
Distance function. One of the: "Cosine" / "Euclid" / "Dot".
content_payload_key:
A payload key used to store the content of the document.
metadata_payload_key:
A payload key used to store the metadata of the document.
**kwargs:
Additional arguments passed directly into REST client initialization
This is a user friendly interface that:
1. Embeds documents.
2. Creates an in memory docstore
@ -170,7 +282,7 @@ class Qdrant(VectorStore):
from langchain import Qdrant
from langchain.embeddings import OpenAIEmbeddings
embeddings = OpenAIEmbeddings()
qdrant = Qdrant.from_texts(texts, embeddings)
qdrant = Qdrant.from_texts(texts, embeddings, "localhost")
"""
try:
import qdrant_client
@ -186,12 +298,21 @@ class Qdrant(VectorStore):
partial_embeddings = embedding.embed_documents(texts[:1])
vector_size = len(partial_embeddings[0])
qdrant_host = get_from_dict_or_env(kwargs, "host", "QDRANT_HOST")
kwargs.pop("host")
collection_name = kwargs.pop("collection_name", uuid.uuid4().hex)
distance_func = kwargs.pop("distance_func", "Cosine").upper()
client = qdrant_client.QdrantClient(host=qdrant_host, **kwargs)
collection_name = collection_name or uuid.uuid4().hex
distance_func = distance_func.upper()
client = qdrant_client.QdrantClient(
url=url,
port=port,
grpc_port=grpc_port,
prefer_grpc=prefer_grpc,
https=https,
api_key=api_key,
prefix=prefix,
timeout=timeout,
host=host,
**kwargs,
)
client.recreate_collection(
collection_name=collection_name,
@ -209,15 +330,27 @@ class Qdrant(VectorStore):
points=rest.Batch(
ids=[uuid.uuid4().hex for _ in texts],
vectors=embeddings,
payloads=cls._build_payloads(texts, metadatas),
payloads=cls._build_payloads(
texts, metadatas, content_payload_key, metadata_payload_key
),
),
)
return cls(client, collection_name, embedding.embed_query)
return cls(
client=client,
collection_name=collection_name,
embedding_function=embedding.embed_query,
content_payload_key=content_payload_key,
metadata_payload_key=metadata_payload_key,
)
@classmethod
def _build_payloads(
cls, texts: Iterable[str], metadatas: Optional[List[dict]]
cls,
texts: Iterable[str],
metadatas: Optional[List[dict]],
content_payload_key: str,
metadata_payload_key: str,
) -> List[dict]:
payloads = []
for i, text in enumerate(texts):
@ -226,18 +359,24 @@ class Qdrant(VectorStore):
"At least one of the texts is None. Please remove it before "
"calling .from_texts or .add_texts on Qdrant instance."
)
metadata = metadatas[i] if metadatas is not None else None
payloads.append(
{
cls.CONTENT_KEY: text,
cls.METADATA_KEY: metadatas[i] if metadatas is not None else None,
content_payload_key: text,
metadata_payload_key: metadata,
}
)
return payloads
@classmethod
def _document_from_scored_point(cls, scored_point: Any) -> Document:
def _document_from_scored_point(
cls,
scored_point: Any,
content_payload_key: str,
metadata_payload_key: str,
) -> Document:
return Document(
page_content=scored_point.payload.get(cls.CONTENT_KEY),
metadata=scored_point.payload.get(cls.METADATA_KEY) or {},
page_content=scored_point.payload.get(content_payload_key),
metadata=scored_point.payload.get(metadata_payload_key) or {},
)

1335
poetry.lock generated
View File

File diff suppressed because it is too large Load Diff

2
pyproject.toml
Unescape Escape View File

@ -35,7 +35,7 @@ weaviate-client = {version = "^3", optional = true}
google-api-python-client = {version = "2.70.0", optional = true}
wolframalpha = {version = "5.0.0", optional = true}
anthropic = {version = "^0.2.2", optional = true}
qdrant-client = {version = "^0.11.7", optional = true}
qdrant-client = {version = "^1.0.4", optional = true, python = ">=3.8.1,<3.12"}
dataclasses-json = "^0.5.7"
tensorflow-text = {version = "^2.11.0", optional = true, python = "^3.10, <3.12"}
tenacity = "^8.1.0"

51
tests/integration_tests/vectorstores/test_qdrant.py
Unescape Escape View File

@ -1,18 +1,46 @@
"""Test Qdrant functionality."""
import pytest
from langchain.docstore.document import Document
from langchain.vectorstores import Qdrant
from tests.integration_tests.vectorstores.fake_embeddings import FakeEmbeddings
def test_qdrant() -> None:
@pytest.mark.parametrize(
["content_payload_key", "metadata_payload_key"],
[
(Qdrant.CONTENT_KEY, Qdrant.METADATA_KEY),
("foo", "bar"),
(Qdrant.CONTENT_KEY, "bar"),
("foo", Qdrant.METADATA_KEY),
],
)
def test_qdrant(content_payload_key: str, metadata_payload_key: str) -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
docsearch = Qdrant.from_texts(texts, FakeEmbeddings(), host="localhost")
docsearch = Qdrant.from_texts(
texts,
FakeEmbeddings(),
host="localhost",
content_payload_key=content_payload_key,
metadata_payload_key=metadata_payload_key,
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo")]
def test_qdrant_with_metadatas() -> None:
@pytest.mark.parametrize(
["content_payload_key", "metadata_payload_key"],
[
(Qdrant.CONTENT_KEY, Qdrant.METADATA_KEY),
("test_content", "test_payload"),
(Qdrant.CONTENT_KEY, "payload_test"),
("content_test", Qdrant.METADATA_KEY),
],
)
def test_qdrant_with_metadatas(
content_payload_key: str, metadata_payload_key: str
) -> None:
"""Test end to end construction and search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
@ -21,12 +49,25 @@ def test_qdrant_with_metadatas() -> None:
FakeEmbeddings(),
metadatas=metadatas,
host="localhost",
content_payload_key=content_payload_key,
metadata_payload_key=metadata_payload_key,
)
output = docsearch.similarity_search("foo", k=1)
assert output == [Document(page_content="foo", metadata={"page": 0})]
def test_qdrant_max_marginal_relevance_search() -> None:
@pytest.mark.parametrize(
["content_payload_key", "metadata_payload_key"],
[
(Qdrant.CONTENT_KEY, Qdrant.METADATA_KEY),
("test_content", "test_payload"),
(Qdrant.CONTENT_KEY, "payload_test"),
("content_test", Qdrant.METADATA_KEY),
],
)
def test_qdrant_max_marginal_relevance_search(
content_payload_key: str, metadata_payload_key: str
) -> None:
"""Test end to end construction and MRR search."""
texts = ["foo", "bar", "baz"]
metadatas = [{"page": i} for i in range(len(texts))]
@ -35,6 +76,8 @@ def test_qdrant_max_marginal_relevance_search() -> None:
FakeEmbeddings(),
metadatas=metadatas,
host="localhost",
content_payload_key=content_payload_key,
metadata_payload_key=metadata_payload_key,
)
output = docsearch.max_marginal_relevance_search("foo", k=2, fetch_k=3)
assert output == [

Write Preview
Loading…
Cancel
Save