BambooAI
A Python library powered by Language Models (LLMs) for conversational data discovery and analysis.
Stars: 525
BambooAI is a lightweight library utilizing Large Language Models (LLMs) to provide natural language interaction capabilities, much like a research and data analysis assistant enabling conversation with your data. You can either provide your own data sets, or allow the library to locate and fetch data for you. It supports Internet searches and external API interactions.
README:
An open-source library that lets you analyze and explore data through natural language conversations using LLMs. Works with your local datasets or can fetch data from external sources and APIs.
The BambooAI library is an experimental tool that utilizes Large Language Models (LLMs) to facilitate data analysis, making it more accessible to users, including those without programming expertise. It functions as an assistant for research and data analysis, allowing users to interact with their data through natural language. Users can supply their own datasets or BambooAI can assist in sourcing the necessary data. The tool also integrates internet searches and accesses external APIs to enhance its functionality.
BambooAI processes natural language queries about datasets and can generate and execute Python code for data analysis and visualization. This enables users to derive insights from their data without extensive coding knowledge. Users simply input their dataset, ask questions in simple English, and BambooAI provides the answers, along with visualizations if needed, to help understand the data better.
BambooAI aims to augment the capabilities of data analysts across all levels. It simplifies data analysis and visualization, helping to streamline workflows. The library is designed to be user-friendly, efficient, and adaptable to meet various needs.
Try it out in Google Colab:
A Machine Learning Example using supplied dataframe:
!pip install pandas
!pip install bambooai
import pandas as pd
from bambooai import BambooAI
df = pd.read_csv('titanic.csv')
bamboo = BambooAI(df, debug=False, vector_db=False, search_tool=True)
bamboo.pd_agent_converse()
Jupyter Notebook:
Task: Can you please devise a machine learnig model to predict the survival of passengers on the Titanic? Output the accuracy of the model. Plot the confusion matrix, correlation matrix, and other relevant metrics. Search internet for the best approach to this task.
https://github.com/user-attachments/assets/59ef810c-80d8-4ef1-8edf-82ba64178b85
Web UI:
Task: Various queries related to sports data
https://github.com/user-attachments/assets/5d013ea0-cb44-4044-9cf4-3efa155288b8
The BambooAI agent operates through several key steps to interact with users and generate responses:
1. Initiation
- The user launches the BambooAI agent with a question.
- If no initial question is provided, the agent prompts the user for a question or an 'exit' command to terminate the program.
- The agent then enters a loop where it responds to each question provided, and upon completion, prompts the user for the next question. This loop continues until the user chooses to exit the program.
2. Task Routing
- The agent stores the received question and utilizes the Large Language Model (LLM) to classify it.
- The LLM determines whether the question necessitates a textual response, additional information (Google search: https://serper.dev/), or can be resolved using code.
- Depending on the task evaluation and classification the task is routed to the appropriate agent.
3. Dynamic Prompt Build
- If the question can be resolved by code, the agent determines whether the necessary data is contained within the provided dataset, requires downloading from an external source, or if the question is of a generic nature and data is not required.
- The agent then chooses its approach accordingly. It can formulate a plan to serve as a blueprint for the analysis.
- The original question is modified to align with this algorithm. The agent performs a semantic search against a vector database for similar questions.
- Any matching questions found are appended to the prompt as examples. A selected LLM model is then used to generate code based on the algorithm.
4. Debugging, Execution, and Error Correction
- The code is executed, and if errors occur, the agent logs the error message and refers it back to the LLM for correction.
- This process continues until successful code execution or the error correction limit is reached.
5. Results, Ranking, and Knowledge Base Build
- Post successful execution, user can rank the answer.
- If the rank surpasses a set threshold, the question, answer, code, and rank are stored in the Pinecone vector database.
- Regardless of the rank, the final answer or visualization is formatted and presented to the user.
Throughout this process, the agent continuously solicits user input, stores messages for context, and generates and executes code to ensure optimal results. Various AI models and a vector database are employed in this process to provide accurate and helpful responses to user's questions.
Flow chart (General agent flow):
The library is vendoe agnistic and supports use of various open source or proprietary models, either via API or localy.
API:
- OpenAI - All models
- Google - Gemini Models
- Anthropic - All Models
- Groq - All Models
- Mistral - All Models
Local:
- Ollama - All Models
- A Selection of local models(more info below)
You can specify what vendor/model you want to use for a specific agent by modifying the content of LLM_CONFIG file, replacing the default OpenAI model name with the model and vendor of your choicee. eg. {"agent": "Code Generator", "details": {"model": "open-mixtral-8x22b", "provider":"mistral","max_tokens": 4000, "temperature": 0}}. The purpose of LLM_CONFIG is described in more detail below.
Installation
pip install bambooai
Usage
- Parameters
df: pd.DataFrame - Dataframe (It will try to source the data from internet, if 'df' is not provided)
max_conversations: int - Number of "user:assistant" conversation pairs to keep in memory for a context. Default=4
debug: bool - If True, the received code is sent back to the LLM for evaluation of its relevance to the user's question, along with code error checking and debugging.
search_tool: bool - If True, the Planner agent will use a "google search API: https://serper.dev/" if the required information is not available or satisfactory. By default it only support HTML sites, but can be enhanced with Selenium if the ChromeDriver exists on the system (details below).
vector_db: bool - If True, each answer will first be ranked from 1 to 10. If the rank surpasses a certain threshold (8), the corresponding question (vectorised), plan, code, and rank (metadata) are all stored in the Pinecone database. Each time a new question is asked, these records will be searched. If the similarity score is above 0.9, they will be offered as examples and included in the prompt (in a one-shot learning scenario)
df_onthology: bool - If True, the onthology defined in the module `df_onthology.py` will be used to inform LLM of the dataframe structure, metrics, record frequency, keys, joins, abstract functions etc. The onthology is custom for each dataframe type, and needs to be defined by the user. Sample onthology is included. This feature signifficantly improves performance, and quality of the solutions.
exploratory: bool - If set to True, the LLM will evaluate the user's question and select an "Expert" that is best suited to address the question (experts: Research Specialist, Data Analyst). In addition, if the task involves code generation/execution, it will generate a task list detailing the steps, which will subsequently be sent to the LLM as a part of the prompt for the next action. This method is particularly effective for vague user prompts, but it might not perform as efficiently with more specific prompts. The default setting is True.
e.g. bamboo = BambooAI(df, debug=True, vector_db=True, search_tool=True, exploratory=True)
bamboo = BambooAI(df,debug=False, vector_db=False, exploratory=True, search_tool=True)
- LLM Config
The agent specific llm configuration is stored in LLM_CONFIG environment variable, or in the "LLM_CONFIG.json file which needs to be stored in the BambooAI's working directory. The config is in a form of JSON list of dictionaries and specifies model name, provider, temperature and max_tokens for each agent. You can use the provided LLM_CONFIG_sample.json as a starting point, and modify the config to reflect your preferences. If neither "ENV VAR" nor "LLM_CONFIG.json" is present, BambooAI will use the default hardcoded configuration that uses "gpt-3.5-turbo" for all agents.
- Prompt Templates
The BambooAI library uses default hand crafted set of prompt templates for each agent. If you want to experiment with them, you can modify the provided "PROMPT_TEMPLATES_sample.json" file, remove the "_sample from its name and store in the working directory. Subsequently, the content of the modified "PROMPT_TEMPLATES.json" will be used instead of the defaults. You can always revert back to default prompts by removing/renaming the modified "PROMPT_TEMPLATES.json".
- Example usage: Run in a loop
# Run in a loop remembering the conversation history
import pandas as pd
from bambooai import BambooAI
df = pd.read_csv('test_activity_data.csv')
bamboo = BambooAI(df)
bamboo.pd_agent_converse()
- Example Usage: Single execution
# Run programaticaly (Single execution).
import pandas as pd
from bambooai import BambooAI
df = pd.read_csv('test_activity_data.csv')
bamboo = BambooAI(df)
bamboo.pd_agent_converse("Calculate 30, 50, 75 and 90 percentiles of the heart rate column")
Environment Variables
The library requires an OpenAI API account and the API key to connect to OpenAI LLMs. The OpenAI API key needs to be stored in a OPENAI_API_KEY environment variable.
The key can be obtained from here: https://platform.openai.com/account/api-keys.
In addition to OpenAI models a selection of models from different providers is also supported (Groq, Gemini, Mistral, Anthropic). The API keys needs to be stored in environment variables in the following format <VENDOR_NAME>_API_KEY.
You need to use GEMINI_API_KEY for Google Gemini models.
As mentioned above, the llm config can be stored in a string format in the LLM_CONFIG environment variable. You can use the content of the provided LLM_CONFIG_sample.json as a starting point and modify to your preference, depending on what models you have access to.
The Pincone vector db is optional. If you don want to use it, you dont need to do anything. If you have an account with Pinecone and would like to use the knowledge base and ranking features, you will be required to setup PINECONE_API_KEY envirooment variable, and set the 'vector_db' parameter to True. The vector db index is created upon first execution.
The Google Search is also optional. If you don want to use it, you dont need to do anything. If you have an account with Serper and would like to use the Google Search functionality, you will be required to setup and account with ": https://serper.dev/", and set SERPER_API_KEY environment variable, and set the 'search_tool' parameter to True. By default bambooai can only scrape websites with HTML content. However it is also capable of using Selenium with ChromeDriver, which is much more powerfull. To enable this functionality you will need to manualy download a version of ChromeDriver that matches your version of the Chrome browser, store it on the filesystem and create an environment variable SELENIUM_WEBDRIVER_PATH with a path to your ChromeDriver. BambooAI wil pick it up automaticaly, and use Selenium for all scraping tasks.
Local Open Source Models
The library currently directly supports the following open-source models. I have selected the models that currently score the highest on the HumanEval benchmark.
- WizardCoder(WizardLM): WizardCoder-15B-V1.0, WizardCoder-Python-7B-V1.0, WizardCoder-Python-13B-V1.0, WizardCoder-Python-34B-V1.0
- WizardCoder GPTQ(TheBloke): WizardCoder-15B-1.0-GPTQ, WizardCoder-Python73B-V1.0-GPTQ, WizardCoder-Python-13B-V1.0-GPTQ, WizardCoder-Python-34B-V1.0-GPTQ
- CodeLlama Instruct(TheBloke): CodeLlama-7B-Instruct-fp16, CodeLlama-13B-Instruct-fp16, CodeLlama-34B-Instruct-fp16
- CodeLlama Instruct(Phind): Phind-CodeLlama-34B-v2
- CodeLlama Completion(TheBloke): CodeLlama-7B-Python-fp16, CodeLlama-13B-Python-fp16, CodeLlama-34B-Python-fp16
If you want to use the local model for a specific agent, modify the LLM_CONFIG content replacing the OpenAI model name with the local model name and change the provider value to 'local'. eg. {"agent": "Code Generator", "details": {"model": "Phind-CodeLlama-34B-v2", "provider":"local","max_tokens": 2000, "temperature": 0}}
At present it is recommended to use local models only for code generation tasks, all other tasks like pseudo code generaration, summarisation, error correction and ranking should be still handled by OpenAI models of choice. The model is downloaded from Huggingface and cached localy for subsequent executions. For a reasonable performance it requires CUDA enabled GPU and the pytorch library compatible with the CUDA version. Below are the required libraries that are not included in the package and will need to be installed independently:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu118 (Adjust to match your CUDA version. This library is already included in Colab notebooks)
pip install auto-gptq (Only required if using WizardCoder-15B-1.0-GPTQ model)
pip install accelerate
pip install einops
pip install xformers
pip install bitsandbytes
The settings and parameters for local models are located in local_models.py module and can be adjusted to match your particular configuration or preferences.
Ollama
The library also supports the use of Ollama https://ollama.com/ and all of it's models. If you want to use a local Ollama model for a specific agent, modify the LLM_CONFIG content replacing the OpenAI model name with the Ollama model name and change the provider value to 'ollama'. eg. {"agent": "Code Generator", "details": {"model": "llama3:70b", "provider":"ollama","max_tokens": 2000, "temperature": 0}}
Logging
All LLM interactions (local or via APIs) are logged in the bambooai_consolidated_log.json file. When the size of the log file reaches 5 MB, a new log file is created. A total of 3 log files are kept on the file system before the oldest file gets overwritten.
The following details are captured:
- Chain ID
- All LLM calls (steps) within the chain, including details of each call eg. agent name, timestamp, model, prompt (context memory), response, token use, cost, tokens per second etc.
- Chain summary, including token use, cost, count of llm calls, tokens per second etc.
- Summary per LLM, including token use, cost, number of calls, tokens per second etc.
Log Structure:
- chain_id: 1695375585
├─ chain_details (LLM Calls)
│ ├─ List of Dictionaries (Multiple Steps)
│ ├─ Call 1
│ │ ├─ agent (String)
│ │ ├─ chain_id (Integer)
│ │ ├─ timestamp (String)
│ │ ├─ model (String)
│ │ ├─ messages (List)
│ │ │ └─ role (String)
│ │ │ └─ content (String)
│ │ └─ Other Fields (content, prompt_tokens, completion_tokens, total_tokens, elapsed_time, tokens_per_second, cost)
│ ├─ Call 2
│ │ └─ ... (Similar Fields)
│ └─ ... (Call 3, Call 4, Call 5 ...)
│
├─ chain_summary
│ ├─ Dictionary
│ ├─ Total LLM Calls (Integer)
│ ├─ Prompt Tokens (Integer)
│ ├─ Completion Tokens (Integer)
│ ├─ Total Tokens (Integer)
│ ├─ Total Time (Float)
│ ├─ Tokens per Second (Float)
│ ├─ Total Cost (Float)
│
├─ summary_per_model
├─ Dictionary
├─ LLM 1 (Dictionary)
│ ├─ LLM Calls (Integer)
│ ├─ Prompt Tokens (Integer)
│ ├─ Completion Tokens (Integer)
│ ├─ Total Tokens (Integer)
│ ├─ Total Time (Float)
│ ├─ Tokens per Second (Float)
│ ├─ Total Cost (Float)
├─ LLM 2
| └─ ... (Similar Fields)
└─ ... (LLM 3, LLM 4, LLM 5 ...)
Task: Devise a machine learning model to predict the survival of passengers on the Titanic. The output should include the accuracy of the model and visualizations of the confusion matrix, correlation matrix, and other relevant metrics.
Dataset: Titanic.csv
Model: GPT-4-Turbo
-
Result:
-
Confusion Matrix:
- True Negative (TN): 90 passengers were correctly predicted as not surviving.
- True Positive (TP): 56 passengers were correctly predicted as surviving.
- False Negative (FN): 18 passengers were incorrectly predicted as not surviving.
- False Positive (FP): 15 passengers were incorrectly predicted as surviving.
-
Confusion Matrix:
| Metric | Value |
|---|---|
| Execution Time | 77.12 seconds |
| Input Tokens | 7128 |
| Output Tokens | 1215 |
| Total Cost | $0.1077 |
-
Result:
-
Confusion Matrix:
- True Negative (TN): 92 passengers were correctly predicted as not surviving.
- True Positive (TP): 55 passengers were correctly predicted as surviving.
- False Negative (FN): 19 passengers were incorrectly predicted as not surviving.
- False Positive (FP): 13 passengers were incorrectly predicted as surviving.
-
Confusion Matrix:
| Metric | Value |
|---|---|
| Execution Time | 47.39 seconds |
| Input Tokens | 722 |
| Output Tokens | 931 |
| Total Cost | $0.0353 |
Objective Assessment of AI Tools for Sports Data Analytics_ Maxwell-v2 vs. Generic LLMs.pdf
- The library currently suports models from various vendors OpenAI, Anthropic, Google, Mistral, Groq served through their APIs. It also supports all Ollama models.
- The library executes LLM generated Python code, this can be bad if the LLM generated Python code is harmful. Use cautiously.
- Be sure to monitor your token usage. The cummulative summary is displayed after each interaction.*
Contributions are welcome; please feel free to open a pull request. Keep in mind that our goal is to maintain a concise codebase with high readability.
- A lot :-)
For Tasks:
Click tags to check more tools for each tasksFor Jobs:
Alternative AI tools for BambooAI
Similar Open Source Tools
BambooAI
BambooAI is a lightweight library utilizing Large Language Models (LLMs) to provide natural language interaction capabilities, much like a research and data analysis assistant enabling conversation with your data. You can either provide your own data sets, or allow the library to locate and fetch data for you. It supports Internet searches and external API interactions.
SheetCopilot
SheetCopilot is an assistant agent that manipulates spreadsheets by following user commands. It leverages Large Language Models (LLMs) to interact with spreadsheets like a human expert, enabling non-expert users to complete tasks on complex software such as Google Sheets and Excel via a language interface. The tool observes spreadsheet states, polishes generated solutions based on external action documents and error feedback, and aims to improve success rate and efficiency. SheetCopilot offers a dataset with diverse task categories and operations, supporting operations like entry & manipulation, management, formatting, charts, and pivot tables. Users can interact with SheetCopilot in Excel or Google Sheets, executing tasks like calculating revenue, creating pivot tables, and plotting charts. The tool's evaluation includes performance comparisons with leading LLMs and VBA-based methods on specific datasets, showcasing its capabilities in controlling various aspects of a spreadsheet.
gepa
GEPA (Genetic-Pareto) is a framework for optimizing arbitrary systems composed of text components like AI prompts, code snippets, or textual specs against any evaluation metric. It employs LLMs to reflect on system behavior, using feedback from execution and evaluation traces to drive targeted improvements. Through iterative mutation, reflection, and Pareto-aware candidate selection, GEPA evolves robust, high-performing variants with minimal evaluations, co-evolving multiple components in modular systems for domain-specific gains. The repository provides the official implementation of the GEPA algorithm as proposed in the paper titled 'GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning'.
mosec
Mosec is a high-performance and flexible model serving framework for building ML model-enabled backend and microservices. It bridges the gap between any machine learning models you just trained and the efficient online service API. * **Highly performant** : web layer and task coordination built with Rust 🦀, which offers blazing speed in addition to efficient CPU utilization powered by async I/O * **Ease of use** : user interface purely in Python 🐍, by which users can serve their models in an ML framework-agnostic manner using the same code as they do for offline testing * **Dynamic batching** : aggregate requests from different users for batched inference and distribute results back * **Pipelined stages** : spawn multiple processes for pipelined stages to handle CPU/GPU/IO mixed workloads * **Cloud friendly** : designed to run in the cloud, with the model warmup, graceful shutdown, and Prometheus monitoring metrics, easily managed by Kubernetes or any container orchestration systems * **Do one thing well** : focus on the online serving part, users can pay attention to the model optimization and business logic
Trace
Trace is a new AutoDiff-like tool for training AI systems end-to-end with general feedback. It generalizes the back-propagation algorithm by capturing and propagating an AI system's execution trace. Implemented as a PyTorch-like Python library, users can write Python code directly and use Trace primitives to optimize certain parts, similar to training neural networks.
llms
The 'llms' repository is a comprehensive guide on Large Language Models (LLMs), covering topics such as language modeling, applications of LLMs, statistical language modeling, neural language models, conditional language models, evaluation methods, transformer-based language models, practical LLMs like GPT and BERT, prompt engineering, fine-tuning LLMs, retrieval augmented generation, AI agents, and LLMs for computer vision. The repository provides detailed explanations, examples, and tools for working with LLMs.
CogAgent
CogAgent is an advanced intelligent agent model designed for automating operations on graphical interfaces across various computing devices. It supports platforms like Windows, macOS, and Android, enabling users to issue commands, capture device screenshots, and perform automated operations. The model requires a minimum of 29GB of GPU memory for inference at BF16 precision and offers capabilities for executing tasks like sending Christmas greetings and sending emails. Users can interact with the model by providing task descriptions, platform specifications, and desired output formats.
LLMeBench
LLMeBench is a flexible framework designed for accelerating benchmarking of Large Language Models (LLMs) in the field of Natural Language Processing (NLP). It supports evaluation of various NLP tasks using model providers like OpenAI, HuggingFace Inference API, and Petals. The framework is customizable for different NLP tasks, LLM models, and datasets across multiple languages. It features extensive caching capabilities, supports zero- and few-shot learning paradigms, and allows on-the-fly dataset download and caching. LLMeBench is open-source and continuously expanding to support new models accessible through APIs.
knowledge-graph-of-thoughts
Knowledge Graph of Thoughts (KGoT) is an innovative AI assistant architecture that integrates LLM reasoning with dynamically constructed knowledge graphs (KGs). KGoT extracts and structures task-relevant knowledge into a dynamic KG representation, iteratively enhanced through external tools such as math solvers, web crawlers, and Python scripts. Such structured representation of task-relevant knowledge enables low-cost models to solve complex tasks effectively. The KGoT system consists of three main components: the Controller, the Graph Store, and the Integrated Tools, each playing a critical role in the task-solving process.
llamabot
LlamaBot is a Pythonic bot interface to Large Language Models (LLMs), providing an easy way to experiment with LLMs in Jupyter notebooks and build Python apps utilizing LLMs. It supports all models available in LiteLLM. Users can access LLMs either through local models with Ollama or by using API providers like OpenAI and Mistral. LlamaBot offers different bot interfaces like SimpleBot, ChatBot, QueryBot, and ImageBot for various tasks such as rephrasing text, maintaining chat history, querying documents, and generating images. The tool also includes CLI demos showcasing its capabilities and supports contributions for new features and bug reports from the community.
agentscript
AgentScript is an open-source framework for building AI agents that think in code. It prompts a language model to generate JavaScript code, which is then executed in a dedicated runtime with resumability, state persistence, and interactivity. The framework allows for abstract task execution without needing to know all the data beforehand, making it flexible and efficient. AgentScript supports tools, deterministic functions, and LLM-enabled functions, enabling dynamic data processing and decision-making. It also provides state management and human-in-the-loop capabilities, allowing for pausing, serialization, and resumption of execution.
kafka-ml
Kafka-ML is a framework designed to manage the pipeline of Tensorflow/Keras and PyTorch machine learning models on Kubernetes. It enables the design, training, and inference of ML models with datasets fed through Apache Kafka, connecting them directly to data streams like those from IoT devices. The Web UI allows easy definition of ML models without external libraries, catering to both experts and non-experts in ML/AI.
neuron-ai
Neuron AI is a PHP framework that provides an Agent class for creating fully functional agents to perform tasks like analyzing text for SEO optimization. The framework manages advanced mechanisms such as memory, tools, and function calls. Users can extend the Agent class to create custom agents and interact with them to get responses based on the underlying LLM. Neuron AI aims to simplify the development of AI-powered applications by offering a structured framework with documentation and guidelines for contributions under the MIT license.
zshot
Zshot is a highly customizable framework for performing Zero and Few shot named entity and relationships recognition. It can be used for mentions extraction, wikification, zero and few shot named entity recognition, zero and few shot named relationship recognition, and visualization of zero-shot NER and RE extraction. The framework consists of two main components: the mentions extractor and the linker. There are multiple mentions extractors and linkers available, each serving a specific purpose. Zshot also includes a relations extractor and a knowledge extractor for extracting relations among entities and performing entity classification. The tool requires Python 3.6+ and dependencies like spacy, torch, transformers, evaluate, and datasets for evaluation over datasets like OntoNotes. Optional dependencies include flair and blink for additional functionalities. Zshot provides examples, tutorials, and evaluation methods to assess the performance of the components.
rag-experiment-accelerator
The RAG Experiment Accelerator is a versatile tool that helps you conduct experiments and evaluations using Azure AI Search and RAG pattern. It offers a rich set of features, including experiment setup, integration with Azure AI Search, Azure Machine Learning, MLFlow, and Azure OpenAI, multiple document chunking strategies, query generation, multiple search types, sub-querying, re-ranking, metrics and evaluation, report generation, and multi-lingual support. The tool is designed to make it easier and faster to run experiments and evaluations of search queries and quality of response from OpenAI, and is useful for researchers, data scientists, and developers who want to test the performance of different search and OpenAI related hyperparameters, compare the effectiveness of various search strategies, fine-tune and optimize parameters, find the best combination of hyperparameters, and generate detailed reports and visualizations from experiment results.
OneKE
OneKE is a flexible dockerized system for schema-guided knowledge extraction, capable of extracting information from the web and raw PDF books across multiple domains like science and news. It employs a collaborative multi-agent approach and includes a user-customizable knowledge base to enable tailored extraction. OneKE offers various IE tasks support, data sources support, LLMs support, extraction method support, and knowledge base configuration. Users can start with examples using YAML, Python, or Web UI, and perform tasks like Named Entity Recognition, Relation Extraction, Event Extraction, Triple Extraction, and Open Domain IE. The tool supports different source formats like Plain Text, HTML, PDF, Word, TXT, and JSON files. Users can choose from various extraction models like OpenAI, DeepSeek, LLaMA, Qwen, ChatGLM, MiniCPM, and OneKE for information extraction tasks. Extraction methods include Schema Agent, Extraction Agent, and Reflection Agent. The tool also provides support for schema repository and case repository management, along with solutions for network issues. Contributors to the project include Ningyu Zhang, Haofen Wang, Yujie Luo, Xiangyuan Ru, Kangwei Liu, Lin Yuan, Mengshu Sun, Lei Liang, Zhiqiang Zhang, Jun Zhou, Lanning Wei, Da Zheng, and Huajun Chen.
For similar tasks
Azure-Analytics-and-AI-Engagement
The Azure-Analytics-and-AI-Engagement repository provides packaged Industry Scenario DREAM Demos with ARM templates (Containing a demo web application, Power BI reports, Synapse resources, AML Notebooks etc.) that can be deployed in a customer’s subscription using the CAPE tool within a matter of few hours. Partners can also deploy DREAM Demos in their own subscriptions using DPoC.
sorrentum
Sorrentum is an open-source project that aims to combine open-source development, startups, and brilliant students to build machine learning, AI, and Web3 / DeFi protocols geared towards finance and economics. The project provides opportunities for internships, research assistantships, and development grants, as well as the chance to work on cutting-edge problems, learn about startups, write academic papers, and get internships and full-time positions at companies working on Sorrentum applications.
tidb
TiDB is an open-source distributed SQL database that supports Hybrid Transactional and Analytical Processing (HTAP) workloads. It is MySQL compatible and features horizontal scalability, strong consistency, and high availability.
zep-python
Zep is an open-source platform for building and deploying large language model (LLM) applications. It provides a suite of tools and services that make it easy to integrate LLMs into your applications, including chat history memory, embedding, vector search, and data enrichment. Zep is designed to be scalable, reliable, and easy to use, making it a great choice for developers who want to build LLM-powered applications quickly and easily.
telemetry-airflow
This repository codifies the Airflow cluster that is deployed at workflow.telemetry.mozilla.org (behind SSO) and commonly referred to as "WTMO" or simply "Airflow". Some links relevant to users and developers of WTMO: * The `dags` directory in this repository contains some custom DAG definitions * Many of the DAGs registered with WTMO don't live in this repository, but are instead generated from ETL task definitions in bigquery-etl * The Data SRE team maintains a WTMO Developer Guide (behind SSO)
mojo
Mojo is a new programming language that bridges the gap between research and production by combining Python syntax and ecosystem with systems programming and metaprogramming features. Mojo is still young, but it is designed to become a superset of Python over time.
pandas-ai
PandasAI is a Python library that makes it easy to ask questions to your data in natural language. It helps you to explore, clean, and analyze your data using generative AI.
databend
Databend is an open-source cloud data warehouse that serves as a cost-effective alternative to Snowflake. With its focus on fast query execution and data ingestion, it's designed for complex analysis of the world's largest datasets.
For similar jobs
Azure-Analytics-and-AI-Engagement
The Azure-Analytics-and-AI-Engagement repository provides packaged Industry Scenario DREAM Demos with ARM templates (Containing a demo web application, Power BI reports, Synapse resources, AML Notebooks etc.) that can be deployed in a customer’s subscription using the CAPE tool within a matter of few hours. Partners can also deploy DREAM Demos in their own subscriptions using DPoC.
skyvern
Skyvern automates browser-based workflows using LLMs and computer vision. It provides a simple API endpoint to fully automate manual workflows, replacing brittle or unreliable automation solutions. Traditional approaches to browser automations required writing custom scripts for websites, often relying on DOM parsing and XPath-based interactions which would break whenever the website layouts changed. Instead of only relying on code-defined XPath interactions, Skyvern adds computer vision and LLMs to the mix to parse items in the viewport in real-time, create a plan for interaction and interact with them. This approach gives us a few advantages: 1. Skyvern can operate on websites it’s never seen before, as it’s able to map visual elements to actions necessary to complete a workflow, without any customized code 2. Skyvern is resistant to website layout changes, as there are no pre-determined XPaths or other selectors our system is looking for while trying to navigate 3. Skyvern leverages LLMs to reason through interactions to ensure we can cover complex situations. Examples include: 1. If you wanted to get an auto insurance quote from Geico, the answer to a common question “Were you eligible to drive at 18?” could be inferred from the driver receiving their license at age 16 2. If you were doing competitor analysis, it’s understanding that an Arnold Palmer 22 oz can at 7/11 is almost definitely the same product as a 23 oz can at Gopuff (even though the sizes are slightly different, which could be a rounding error!) Want to see examples of Skyvern in action? Jump to #real-world-examples-of- skyvern
pandas-ai
PandasAI is a Python library that makes it easy to ask questions to your data in natural language. It helps you to explore, clean, and analyze your data using generative AI.
vanna
Vanna is an open-source Python framework for SQL generation and related functionality. It uses Retrieval-Augmented Generation (RAG) to train a model on your data, which can then be used to ask questions and get back SQL queries. Vanna is designed to be portable across different LLMs and vector databases, and it supports any SQL database. It is also secure and private, as your database contents are never sent to the LLM or the vector database.
databend
Databend is an open-source cloud data warehouse that serves as a cost-effective alternative to Snowflake. With its focus on fast query execution and data ingestion, it's designed for complex analysis of the world's largest datasets.
Avalonia-Assistant
Avalonia-Assistant is an open-source desktop intelligent assistant that aims to provide a user-friendly interactive experience based on the Avalonia UI framework and the integration of Semantic Kernel with OpenAI or other large LLM models. By utilizing Avalonia-Assistant, you can perform various desktop operations through text or voice commands, enhancing your productivity and daily office experience.
marvin
Marvin is a lightweight AI toolkit for building natural language interfaces that are reliable, scalable, and easy to trust. Each of Marvin's tools is simple and self-documenting, using AI to solve common but complex challenges like entity extraction, classification, and generating synthetic data. Each tool is independent and incrementally adoptable, so you can use them on their own or in combination with any other library. Marvin is also multi-modal, supporting both image and audio generation as well using images as inputs for extraction and classification. Marvin is for developers who care more about _using_ AI than _building_ AI, and we are focused on creating an exceptional developer experience. Marvin users should feel empowered to bring tightly-scoped "AI magic" into any traditional software project with just a few extra lines of code. Marvin aims to merge the best practices for building dependable, observable software with the best practices for building with generative AI into a single, easy-to-use library. It's a serious tool, but we hope you have fun with it. Marvin is open-source, free to use, and made with 💙 by the team at Prefect.
activepieces
Activepieces is an open source replacement for Zapier, designed to be extensible through a type-safe pieces framework written in Typescript. It features a user-friendly Workflow Builder with support for Branches, Loops, and Drag and Drop. Activepieces integrates with Google Sheets, OpenAI, Discord, and RSS, along with 80+ other integrations. The list of supported integrations continues to grow rapidly, thanks to valuable contributions from the community. Activepieces is an open ecosystem; all piece source code is available in the repository, and they are versioned and published directly to npmjs.com upon contributions. If you cannot find a specific piece on the pieces roadmap, please submit a request by visiting the following link: Request Piece Alternatively, if you are a developer, you can quickly build your own piece using our TypeScript framework. For guidance, please refer to the following guide: Contributor's Guide