As a leader in vector databases, Milvus is suitable for a variety of AI applications that require efficient and scalable vector search capabilities.
For example, if you want to build a data management process for a chatbot, Milvus must be the vector database of choice. So how to make this application development easier to manage and better understood, you need to use Towhee ( https://towhee.io/ ). Towhee is an emerging machine learning (ML) framework that simplifies the process of implementing and orchestrating complex ML models.
Next, I will introduce how to use Milvus + Towhee to build a basic AI chatbot through Python. This article will focus on how to process and analyze unstructured data and store and query vector data.
01. Set up the environment
First, create a Python virtual environment to run the chatbot.
The following is a Linux shell session. Create and activate the environment with the help of Shell session, and upgrade pip to the latest version.
[egoebelbecker@ares milvus_chatbot]$ python -m venv ./chatbot_venv
[egoebelbecker@ares milvus_chatbot]$ source chatbot_venv/bin/activate
(chatbot_venv) [egoebelbecker@ares milvus_chatbot]$ pip install --upgrade pip
Requirement already satisfied: pip in ./chatbot_venv/lib64/python3.11/site-packages (22.2.2)
Collecting pip
Using cached pip-23.1.2-py3-none-any.whl (2.1 MB)
Installing collected packages: pip
Attempting uninstall: pip
Found existing installation: pip 22.2.2
Uninstalling pip-22.2.2:
Successfully uninstalled pip-22.2.2
Successfully installed pip-23.1.2
Next, install the packages required to run your code: Pandas, Jupyter, Langchain, Towhee, Unstructured, Milvus, PymMilvus, sentence_transformers, and Gradio.
(chatbot_venv) [egoebelbecker@ares milvus_chatbot]$ pip install pandas jupyter langchain towhee unstructured milvus pymilvus sentence_transformers gradio
Collecting pandas
Obtaining dependency information for pandas from https://files.pythonhosted.org/packages/d0/28/88b81881c056376254618fad622a5e94b5126db8c61157ea1910cd1c040a/pandas-2.0.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata
Using cached pandas-2.0.3-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (18 kB)
Collecting jupyter
Using cached jupyter-1.0.0-py2.py3-none-any.whl (2.7 kB)
(snip)
Installing collected packages: webencodings, wcwidth, pytz, pure-eval, ptyprocess, pickleshare, json5, ipython-genutils, filetype, fastjsonschema, executing, backcall, zipp, XlsxWriter, xlrd, widgetsnbextension, websocket-client, webcolors, urllib3, uri-template, tzdata, typing-extensions, traitlets, tqdm, tornado, tinycss2, tenacity, tabulate, soupsieve, sniffio, six, send2trash, rpds-py, rfc3986-validator, rfc3986, regex, pyzmq, PyYAML, python-magic, python-json-logger, pypandoc, pygments, pycparser, psutil, prompt-toolkit, prometheus-client, platformdirs, pkginfo, pillow, pexpect, parso, pandocfilters, packaging, overrides, olefile, numpy, nest-asyncio, mypy-extensions, multidict, more-itertools, mistune, mdurl, markupsafe, markdown, lxml, jupyterlab-widgets, jupyterlab-pygments, jsonpointer, joblib, jeepney, idna, greenlet, frozenlist, fqdn, et-xmlfile, docutils, defusedxml, decorator, debugpy, click, charset-normalizer, chardet, certifi, babel, attrs, async-timeout, async-lru, yarl, typing-inspect, terminado, SQLAlchemy, rfc3339-validator, requests, referencing, qtpy, python-pptx, python-docx, python-dateutil, pydantic, pdf2image, openpyxl, numexpr, nltk, msg-parser, matplotlib-inline, marshmallow, markdown-it-py, jupyter-core, jinja2, jedi, jaraco.classes, importlib-metadata, comm, cffi, bleach, beautifulsoup4, asttokens, anyio, aiosignal, stack-data, rich, requests-toolbelt, readme-renderer, pandas, openapi-schema-pydantic, langsmith, jupyter-server-terminals, jupyter-client, jsonschema-specifications, dataclasses-json, cryptography, arrow, argon2-cffi-bindings, aiohttp, SecretStorage, pdfminer.six, langchain, jsonschema, isoduration, ipython, argon2-cffi, unstructured, nbformat, keyring, ipykernel, twine, qtconsole, nbclient, jupyter-events, jupyter-console, ipywidgets, towhee, nbconvert, jupyter-server, notebook-shim, jupyterlab-server, jupyter-lsp, jupyterlab, notebook, jupyter
Successfully installed PyYAML-6.0.1 SQLAlchemy-2.0.19 SecretStorage-3.3.3 XlsxWriter-3.1.2 aiohttp-3.8.5 aiosignal-1.3.1 anyio-3.7.1 argon2-cffi-21.3.0 argon2-cffi-bindings-21.2.0 arrow-1.2.3 asttokens-2.2.1 async-lru-2.0.4 async-timeout-4.0.2 attrs-23.1.0 babel-2.12.1 backcall-0.2.0 beautifulsoup4-4.12.2 bleach-6.0.0 certifi-2023.7.22 cffi-1.15.1 chardet-5.1.0 charset-normalizer-3.2.0 click-8.1.6 comm-0.1.3 cryptography-41.0.2 dataclasses-json-0.5.14 debugpy-1.6.7 decorator-5.1.1 defusedxml-0.7.1 docutils-0.20.1 et-xmlfile-1.1.0 executing-1.2.0 fastjsonschema-2.18.0 filetype-1.2.0 fqdn-1.5.1 frozenlist-1.4.0 greenlet-2.0.2 idna-3.4 importlib-metadata-6.8.0 ipykernel-6.25.0 ipython-8.14.0 ipython-genutils-0.2.0 ipywidgets-8.0.7 isoduration-20.11.0 jaraco.classes-3.3.0 jedi-0.19.0 jeepney-0.8.0 jinja2-3.1.2 joblib-1.3.1 json5-0.9.14 jsonpointer-2.4 jsonschema-4.18.4 jsonschema-specifications-2023.7.1 jupyter-1.0.0 jupyter-client-8.3.0 jupyter-console-6.6.3 jupyter-core-5.3.1 jupyter-events-0.7.0 jupyter-lsp-2.2.0 jupyter-server-2.7.0 jupyter-server-terminals-0.4.4 jupyterlab-4.0.3 jupyterlab-pygments-0.2.2 jupyterlab-server-2.24.0 jupyterlab-widgets-3.0.8 keyring-24.2.0 langchain-0.0.248 langsmith-0.0.15 lxml-4.9.3 markdown-3.4.4 markdown-it-py-3.0.0 markupsafe-2.1.3 marshmallow-3.20.1 matplotlib-inline-0.1.6 mdurl-0.1.2 mistune-3.0.1 more-itertools-10.0.0 msg-parser-1.2.0 multidict-6.0.4 mypy-extensions-1.0.0 nbclient-0.8.0 nbconvert-7.7.3 nbformat-5.9.2 nest-asyncio-1.5.7 nltk-3.8.1 notebook-7.0.1 notebook-shim-0.2.3 numexpr-2.8.4 numpy-1.25.2 olefile-0.46 openapi-schema-pydantic-1.2.4 openpyxl-3.1.2 overrides-7.3.1 packaging-23.1 pandas-2.0.3 pandocfilters-1.5.0 parso-0.8.3 pdf2image-1.16.3 pdfminer.six-20221105 pexpect-4.8.0 pickleshare-0.7.5 pillow-10.0.0 pkginfo-1.9.6 platformdirs-3.10.0 prometheus-client-0.17.1 prompt-toolkit-3.0.39 psutil-5.9.5 ptyprocess-0.7.0 pure-eval-0.2.2 pycparser-2.21 pydantic-1.10.12 pygments-2.15.1 pypandoc-1.11 python-dateutil-2.8.2 python-docx-0.8.11 python-json-logger-2.0.7 python-magic-0.4.27 python-pptx-0.6.21 pytz-2023.3 pyzmq-25.1.0 qtconsole-5.4.3 qtpy-2.3.1 readme-renderer-40.0 referencing-0.30.0 regex-2023.6.3 requests-2.31.0 requests-toolbelt-1.0.0 rfc3339-validator-0.1.4 rfc3986-2.0.0 rfc3986-validator-0.1.1 rich-13.5.1 rpds-py-0.9.2 send2trash-1.8.2 six-1.16.0 sniffio-1.3.0 soupsieve-2.4.1 stack-data-0.6.2 tabulate-0.9.0 tenacity-8.2.2 terminado-0.17.1 tinycss2-1.2.1 tornado-6.3.2 towhee-1.1.1 tqdm-4.65.0 traitlets-5.9.0 twine-4.0.2 typing-extensions-4.7.1 typing-inspect-0.9.0 tzdata-2023.3 unstructured-0.8.7 uri-template-1.3.0 urllib3-2.0.4 wcwidth-0.2.6 webcolors-1.13 webencodings-0.5.1 websocket-client-1.6.1 widgetsnbextension-4.0.8 xlrd-2.0.1 yarl-1.9.2 zipp-3.16.2
(chatbot_venv) [egoebelbecker@ares milvus_chatbot]$
Visit the link https://gist.github.com/egoebelbecker/07059b88a1c4daa96ec07937f8ca77b3 to get the Jupyter Notebook covering all the code for this tutorial. Download the Notebook, start Jupyter and load the Notebook.
chatbot_venv) [egoebelbecker@ares milvus_chatbot]$ jupyter notebook milvus_chatbot.ipynb
[I 2023-07-31 11:29:01.748 ServerApp] Package notebook took 0.0000s to import
[I 2023-07-31 11:29:01.759 ServerApp] Package jupyter_lsp took 0.0108s to import
[W 2023-07-31 11:29:01.759 ServerApp] A `_jupyter_server_extension_points` function was not found in jupyter_lsp. Instead, a `_jupyter_server_extension_paths` function was found and will be used for now. This function name will be deprecated in future releases of Jupyter Server.
[I 2023-07-31 11:29:01.764 ServerApp] Package jupyter_server_terminals took 0.0045s to import
[I 2023-07-31 11:29:01.765 ServerApp] Package jupyterlab took 0.0000s to import
[I 2023-07-31 11:29:02.124 ServerApp] Package notebook_shim took 0.0000s to import
02. Build a chatbot
Once everything is ready, you can build the chatbot.
Document storage
The robot needs to store the document block and the document block vector extracted using Towhee. In this step, we need to use Milvus.
Install the lightweight version of Milvus Lite and run the Milvus server using the following command:
(chatbot_venv) [egoebelbecker@ares milvus_chatbot]$ milvus-server
__ _________ _ ____ ______
/ |/ / _/ /| | / / / / / __/
/ /|_/ // // /_| |/ / /_/ /\ \
/_/ /_/___/____/___/\____/___/ {Lite}
Welcome to use Milvus!
Version: v2.2.12-lite
Process: 139309
Started: 2023-07-31 12:43:43
Config: /home/egoebelbecker/.milvus.io/milvus-server/2.2.12/configs/milvus.yaml
Logs: /home/egoebelbecker/.milvus.io/milvus-server/2.2.12/logs
Ctrl+C to exit …
Or, run the code in the notebook:
from milvus import default_server
# 启动 Milvus 服务
default_server.start()
# 停止 Milvus 服务
default_server.stop()
Set application variables and obtain OpenAI API key
Next, set the variables and clean up the old SQLite files, we will use SQLite to store the chat history.
-
MILVUS_URI - Milvus server connection information, resolved to host and port.
-
MILVUS_HOST - The host where Milvus is running.
-
MILVUS_PORT - The port the server listens on.
-
DROP_EXIST - Removes existing Milvus collections on startup.
-
EMBED_MODEL - sentence_transformers model used to generate embedding vectors
-
COLLECTION_NAME - the name of the Milvus collection used to store vector data
-
DIM - Dimensions of text vectors generated by the model
-
OPENAI_API_KEY - Key for the Large Language Model (LLM) API
import getpass
import os
MILVUS_URI = 'http://localhost:19530'
[MILVUS_HOST, MILVUS_PORT] = MILVUS_URI.split('://')[1].split(':')
DROP_EXIST = True
EMBED_MODEL = 'all-mpnet-base-v2'
COLLECTION_NAME = 'chatbot_demo'
DIM = 768
OPENAI_API_KEY = getpass.getpass('Enter your OpenAI API key: ')
if os.path.exists('./sqlite.db'):
os.remove('./sqlite.db')
Run the above code to define the variables and enter the OpenAI API key.
Example pipeline
Next, the data needs to be downloaded and stored in Milvus. But before that, let's learn how to use pipeline to process unstructured data.
I will use the Towhee official website homepage as an example of a document source for demonstration. You can also try other different document websites to understand how the pipeline processes different data sets.
The following code uses the Towhee pipeline:
-
input - Create a new pipeline and pass in source data.
-
map - Use ops.text_loader() to parse the URL and map it to 'doc'.
-
flat_map - Use ops.text_splitter() to split the document into fragments for subsequent storage.
-
output - Select the data output, ready for use.
Pass this pipeline into the DataCollection and observe how it works.
from towhee import pipe, ops, DataCollectionpipe_load = (
from towhee import pipe, ops, DataCollection
pipe_load = (
pipe.input('source')
.map('source', 'doc', ops.text_loader())
.flat_map('doc', 'doc_chunks', ops.text_splitter(chunk_size=300))
.output('source', 'doc_chunks')
)
DataCollection(pipe_load('https://towhee.io')).show()
The following is the output:
Example Embedding pipeline
Next, refer to the following example embedding pipeline to convert these document blocks into vectors. The pipeline runs ops.sentence_embedding.sbert() on each document block via map(). In the example, we passed in 1 text block.
pipe_embed = (
pipe.input('doc_chunk')
.map('doc_chunk', 'vec', ops.sentence_embedding.sbert(model_name=EMBED_MODEL))
.map('vec', 'vec', ops.np_normalize())
.output('doc_chunk', 'vec')
)
text = '''SOTA Models
We provide 700+ pre-trained embedding models spanning 5 fields (CV, NLP, Multimodal, Audio, Medical), 15 tasks, and 140+ model architectures.
These include BERT, CLIP, ViT, SwinTransformer, data2vec, etc.
'''
DataCollection(pipe_embed(text)).show()
Run this code to see how this pipeline converts individual document fragments into vectors.
Setting up Milvus
Create a Collection to store data.
In the following code, we use MILVUS_HOST and MILVUS_PORT to connect to Milvus, delete all existing Collections, and define the create_collection() function to create a new Collection.
The Schema of the new Collection is as follows:
-
id - identifier, data type is integer.
-
embedding - vector, data type float vector.
-
text - the text of the document block corresponding to the vector, the data type is string.
from pymilvus import (
connections, utility, Collection,
CollectionSchema, FieldSchema, DataType
)
def create_collection(collection_name):
connections.connect(host=MILVUS_HOST, port=MILVUS_PORT)
has_collection = utility.has_collection(collection_name)
if has_collection:
collection = Collection(collection_name)
if DROP_EXIST:
collection.drop()
else:
return collection
# 创建 collection
fields = [
FieldSchema(name='id', dtype=DataType.INT64, is_primary=True, auto_id=True),
FieldSchema(name='embedding', dtype=DataType.FLOAT_VECTOR, dim=DIM),
FieldSchema(name='text', dtype=DataType.VARCHAR, max_length=500)
]
schema = CollectionSchema(
fields=fields,
description="Towhee demo",
enable_dynamic_field=True
)
collection = Collection(name=collection_name, schema=schema)
index_params = {
'metric_type': 'IP',
'index_type': 'IVF_FLAT',
'params': {'nlist': 1024}
}
collection.create_index(
field_name='embedding',
index_params=index_params
)
return collection
Insert Pipeline
Now, insert the text vector into Milvus.
The following code works:
-
Create new Collection
-
Load new document data
-
Cut new document into chunks
-
Use EMBED_MODEL to generate vectors for text blocks
-
Insert text block vector and corresponding text block data into Milvus
load_data = (
pipe.input('collection_name', 'source')
.map('collection_name', 'collection', create_collection)
.map('source', 'doc', ops.text_loader())
.flat_map('doc', 'doc_chunk', ops.text_splitter(chunk_size=300))
.map('doc_chunk', 'vec', ops.sentence_embedding.sbert(model_name=EMBED_MODEL))
.map('vec', 'vec', ops.np_normalize())
.map(('collection_name', 'vec', 'doc_chunk'), 'mr',
ops.ann_insert.osschat_milvus(host=MILVUS_HOST, port=MILVUS_PORT))
.output('mr')
)
Through the following code, we convert the content of Frodo Baggins' encyclopedia page into a text fast vector and insert it into Milvus.
project_name = 'towhee_demo'
data_source = 'https://en.wikipedia.org/wiki/Frodo_Baggins'
mr = load_data(COLLECTION_NAME, data_source)
print('Doc chunks inserted:', len(mr.to_list()))
Finally, a total of 408 text block vectors were inserted:
2023-07-31 16:50:53,369 - 139993906521792 - node.py-node:167 - INFO: Begin to run Node-_input2023-07-31 16:50:53,371 - 139993906521792 - node.py-node:167 - INFO: Begin to run Node-create_collection-02023-07-31 16:50:53,373 - 139993881343680 - node.py-node:167 - INFO: Begin to run Node-text-loader-12023-07-31 16:50:53,374 - 139993898129088 - node.py-node:167 - INFO: Begin to run Node-text-splitter-22023-07-31 16:50:53,376 - 139993872950976 - node.py-node:167 - INFO: Begin to run Node-sentence-embedding/sbert-32023-07-31 16:50:53,377 - 139993385268928 - node.py-node:167 - INFO: Begin to run Node-np-normalize-42023-07-31 16:50:53,378 - 139993376876224 - node.py-node:167 - INFO: Begin to run Node-ann-insert/osschat-milvus-52023-07-31 16:50:53,379 - 139993368483520 - node.py-node:167 - INFO: Begin to run Node-_output
(snip)
Categories:
2023-07-31 18:07:53,530 - 140552729257664 - logger.py-logger:14 - DETAIL: Skipping sentence because does not exceed 5 word tokens
Categories
2023-07-31 18:07:53,532 - 140552729257664 - logger.py-logger:14 - DETAIL: Skipping sentence because does not exceed 3 word tokens
Hidden categories
2023-07-31 18:07:53,533 - 140552729257664 - logger.py-logger:14 - DETAIL: Skipping sentence because does not exceed 3 word tokens
Hidden categories
2023-07-31 18:07:53,533 - 140552729257664 - logger.py-logger:14 - DETAIL: Not narrative. Text does not contain a verb:
Hidden categories:
2023-07-31 18:07:53,534 - 140552729257664 - logger.py-logger:14 - DETAIL: Skipping sentence because does not exceed 5 word tokens
Hidden categories
Doc chunks inserted: 408
03. Search the knowledge base
Text block vectors have been stored in Milvus and vector queries can now be performed.
The following function creates a query pipeline. Note that this is the most critical step in this tutorial!
ops.ann_search.osschat_milvus(host=MILVUS_HOST, port=MILVUS_PORT,
**{'metric_type': 'IP', 'limit': 3, 'output_fields': ['text']}))
OSSChat_milvus ( https://towhee.io/ann-search/osschat-milvus) queries the Milvus vector database for document fragments that match the query text.
The following is the entire query pipeline code:
pipe_search = (
pipe.input('collection_name', 'query')
.map('query', 'query_vec', ops.sentence_embedding.sbert(model_name=EMBED_MODEL))
.map('query_vec', 'query_vec', ops.np_normalize())
.map(('collection_name', 'query_vec'), 'search_res',
ops.ann_search.osschat_milvus(host=MILVUS_HOST, port=MILVUS_PORT,
**{'metric_type': 'IP', 'limit': 3, 'output_fields': ['text']}))
.flat_map('search_res', ('id', 'score', 'text'), lambda x: (x[0], x[1], x[2]))
.output('query', 'text', 'score')
)
Now, you can try to query the following questions:
query = 'Who is Frodo Baggins?'
DataCollection(pipe_search(project_name, query)).show()
It is not difficult to find that the model we used returned 3 matching results (note: limit=3 was specified in ann_search.osschat_milvus earlier):
04. Add large language model (LLM)
Next, LLM needs to be added to the chatbot. In this way, users can start a conversation with the chatbot. In this example, we will use the model service behind OpenAI ChatGPT: GPT-3.5.
chat record
In order to make LLM answers more accurate, we need to store the chat records of users and robots, and call these records when querying. SQLite can be used to manage chat records.
The following functions are used to retrieve chat records:
<section id="nice" data-tool="mdnice编辑器" data-website="https://www.mdnice.com" style="font-size: 16px; padding: 0 10px; line-height: 1.6; word-spacing: 0px; letter-spacing: 0px; word-break: break-word; word-wrap: break-word; text-align: left; color: #3E3E3E; font-family: Optima-Regular, Optima, PingFangSC-light, PingFangTC-light, 'PingFang SC', Cambria, Cochin, Georgia, Times, 'Times New Roman', serif;"><pre class="custom" data-tool="mdnice编辑器" style="margin-top: 10px; margin-bottom: 10px; border-radius: 5px; box-shadow: rgba(0, 0, 0, 0.55) 0px 2px 10px; text-align: left;"><span style="display: block; background: url(https://files.mdnice.com/user/3441/876cad08-0422-409d-bb5a-08afec5da8ee.svg); height: 30px; width: 100%; background-size: 40px; background-repeat: no-repeat; background-color: #282c34; margin-bottom: -7px; border-radius: 5px; background-position: 10px 10px;"></span><code class="hljs" style="overflow-x: auto; padding: 16px; color: #abb2bf; display: -webkit-box; font-family: Operator Mono, Consolas, Monaco, Menlo, monospace; font-size: 12px; -webkit-overflow-scrolling: touch; padding-top: 15px; background: #282c34; border-radius: 5px;">query = 'Who is Frodo Baggins?'
DataCollection(pipe_search(project_name, query)).show()
</code></pre>
</section>
The following function user stores chat history:
pipe_add_history = (
pipe.input('collection_name', 'session', 'question', 'answer')
.map(('collection_name', 'session', 'question', 'answer'), 'history', ops.chat_message_histories.sql(method='add'))
.output('history')
)
LLM Query Pipeline
Build a Pipeline to pass the query to LLM.
This LLM query Pipeline can:
-
Search the Milvus vector database based on user query questions
-
Retrieve and store the current chat history
-
Transfer user query questions, Milvus search results, and chat records to ChatGPT
-
Record the questions and answers for this round
-
Return to final answer
chat = (
pipe.input('collection_name', 'query', 'session')
.map('query', 'query_vec', ops.sentence_embedding.sbert(model_name=EMBED_MODEL))
.map('query_vec', 'query_vec', ops.np_normalize())
.map(('collection_name', 'query_vec'), 'search_res',
ops.ann_search.osschat_milvus(host=MILVUS_HOST,
port=MILVUS_PORT,
**{'metric_type': 'IP', 'limit': 3, 'output_fields': ['text']}))
.map('search_res', 'knowledge', lambda y: [x[2] for x in y])
.map(('collection_name', 'session'), 'history', ops.chat_message_histories.sql(method='get'))
.map(('query', 'knowledge', 'history'), 'messages', ops.prompt.question_answer())
.map('messages', 'answer', ops.LLM.OpenAI(api_key=OPENAI_API_KEY,
model_name='gpt-3.5-turbo',
temperature=0.8))
.map(('collection_name', 'session', 'query', 'answer'), 'new_history', ops.chat_message_histories.sql(method='add'))
.output('query', 'history', 'answer', )
)
Before connecting to the graphical user interface (GUI), we need to test the following Pipeline.
new_query = 'Where did Frodo take the ring?'
DataCollection(chat(COLLECTION_NAME, new_query, session_id)).show()
The following is the output and results:
congratulations! This Pipeline was built successfully! Next, you can build the Gradio interface!
Gradio interface
First, some functions are needed to create a session ID through UUID, accept and respond to user queries on the interface.
import uuidimport io
def create_session_id():
uid = str(uuid.uuid4())
suid = ''.join(uid.split('-'))
return 'sess_' + suid
def respond(session, query):
res = chat(COLLECTION_NAME, query, session).get_dict()
answer = res['answer']
response = res['history']
response.append((query, answer))
return response
Then, the Gradio interface builds a chatbot through these functions. Blocks API is used to build chatbot interfaces. The Send Message button sends the request to ChatGPT through the response function.
import gradio as gr
with gr.Blocks() as demo:
session_id = gr.State(create_session_id)
with gr.Row():
with gr.Column(scale=2):
gr.Markdown('''## Chat''')
conversation = gr.Chatbot(label='conversation').style(height=300)
question = gr.Textbox(label='question', value=None)
send_btn = gr.Button('Send Message')
send_btn.click(
fn=respond,
inputs=[
session_id,
question
],
outputs=conversation,
)
demo.launch(server_name='127.0.0.1', server_port=8902)
The interface is as follows:
At this point, an intelligent chatbot that combines vector retrieval and LLM generation is completed!
05. Summary
To recap, we first created the Towhee pipeline to process unstructured data, convert it into vectors and store it in the Milvus vector database. Then, a query pipeline was built and LLM was connected to the chatbot. Finally, a basic chatbot interface is built.
In short, Milvus is highly scalable, provides efficient vector similarity search functions, and can help developers easily build ML and AI applications such as chat robots, recommendation systems, image or text recognition, etc. I look forward to everyone using Milvus to build better applications!
- Author of this article
Eric Goebelbecker currently lives in New York and has 25 years of experience in the financial markets. He is responsible for building the infrastructure for the Financial Information Exchange (FIX) protocol network and market data analysis systems. Eric is passionate about exploring tools and software that improve team productivity.
-
If you have any problems using Milvus or Zilliz products, you can add the assistant WeChat "zilliz-tech" to join the communication group.
-
Welcome to follow the WeChat public account "Zilliz" to learn the latest information.