Skip to content

Commit

Permalink
add readme
Browse files Browse the repository at this point in the history
  • Loading branch information
alaeddine-13 committed Apr 16, 2023
1 parent ff11b06 commit 83fb432
Showing 1 changed file with 176 additions and 2 deletions.
178 changes: 176 additions & 2 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,2 +1,176 @@
# llm-tools
Agent techniques to augment your LLM and push it beyong its limits
# ThinkGPT 🧠🤖
ThinkGPT is a Python library aimed at implementing Chain of Thoughts for Large Language Models (LLMs), prompting the model to think, reason, and to create generative agents.
The library aims to help with the following:
* solve limited context with long memory
* enhance LLMs' one-shot reasoning with higher order reasoning primitives
* add intelligent decisions to your code base


## Key Features ✨
* Memory 🧠: GPTs that can remember experience
* Self-refinement 🔧: Improve model-generated content by addressing critics
* Abstraction 🌐: Encourages LLMs to generalize rules from examples or observations
* Inference 💡️: Make educated guesses based on available information
* Natural Language Conditions 📝: Easily express tasks and conditions in natural language

## Installation 💻
You can install ThinkGPT using pip:

```shell
pip install git+https://github.com/alaeddine-13/thinkgpt.git
```

## API Documentation 📚
### Basic usage:
```python
from thinkgpt.llm import ThinkGPT
llm = ThinkGPT(model_name="gpt-3.5-turbo")
# Make the llm object learn new concepts
llm.memorize(['DocArray is a library for representing, sending and storing multi-modal data.'])
llm.predict('what is DocArray ?', remember=llm.remember('DocArray definition'))
```

### Memorizing and Remembering information
```python
llm.memorize([
'DocArray allows you to send your data, in an ML-native way.',
'This means there is native support for Protobuf and gRPC, on top of HTTP and serialization to JSON, JSONSchema, Base64, and Bytes.',
...
])

print(llm.remember('Sending data with DocArray'))
```

### Predicting with context from long memory
```python
llm.predict('Implement a DocArray schema with 2 fields: image and TorchTensor', remember=llm.remember('DocArray schemas and types'))
```

### Self-refinement

```python
print(llm.refine(
content="""
import re
print('hello world')
""",
critics=[
'File "/Users/user/PyCharm2022.3/scratches/scratch_166.py", line 2',
" print('hello world')",
'IndentationError: unexpected indent'
],
instruction_hint="Fix the code snippet based on the error provided. Only provide the fixed code snippet between `` and nothing else."))

```

```text
import re
print('hello world')
```

### Induce rules from observations
```python
llm.abstract(observations=[
"in tunisian, I did not eat is \"ma khditech\"",
"I did not work is \"ma khdemtech\"",
"I did not go is \"ma mchitech\"",
])
```

```text
['Negation in Tunisian Arabic uses "ma" + verb + "tech" where "ma" means "not" and "tech" at the end indicates the negation in the past tense.']
```

### Natural language condition
```python
llm.condition(f'Does this represent an error message ? "IndentationError: unexpected indent"')
```
```text
True
```
### Natural language select
```python
llm.select(question="Which animal is the king of the jungle?", options=["Lion", "Elephant", "Tiger", "Giraffe"])
```
```text
Lion
```

For more detailed usage and code examples, please refer to the provided code snippets in the ThinkGPT repository.

## Use Cases 🚀
Find out below example demos you can do with `thinkgpt`
### Teaching GPT a new language
```python
from thinkgpt.llm import ThinkGPT

llm = ThinkGPT(model_name="gpt-3.5-turbo")

rules = llm.abstract(observations=[
"in tunisian, I did not eat is \"ma khditech\"",
"I did not work is \"ma khdemtech\"",
"I did not go is \"ma mchitech\"",
], instruction_hint="output the rule in french")
llm.memorize(rules)

llm.memorize("in tunisian, I studied is \"9rit\"")

task = "translate to Tunisian: I didn't study"
llm.predict(task, remember=llm.remember(task))
```
```text
The translation of "I didn't study" to Tunisian language would be "ma 9ritech".
```

### Teaching `thinkgpt` to the LLM
```python
from thinkgpt.llm import ThinkGPT
from examples.knowledge_base import knowledge

llm = ThinkGPT(model_name="gpt-3.5-turbo")

llm.memorize(knowledge)

task = 'Implement python code that uses thinkgpt to learn about docarray v2 code and then predict with remembered information about docarray v2. Only give the code between `` and nothing else'
print(llm.predict(task, remember=llm.remember(task, limit=10, sort_by_order=True)))
```

Code generated by the LLM:
```text
from thinkgpt.llm import ThinkGPT
from docarray import BaseDoc
from docarray.typing import TorchTensor, ImageUrl
llm = ThinkGPT(model_name="gpt-3.5-turbo")
# Memorize information
llm.memorize('DocArray V2 allows you to represent your data, in an ML-native way')
# Predict with the memory
memory = llm.remember('DocArray V2')
llm.predict('write python code about DocArray v2', remember=memory)
```
### Replay Agent memory and infer new observations
Refer to the following script for an example of an Agent that replays its memory and induces new observations.
This concept was introduced in [the Generative Agents: Interactive Simulacra of Human Behavior paper](https://arxiv.org/abs/2304.03442).

```shell
python -m examples.replay_expand_memory
```
```text
new thoughts:
Klaus Mueller is interested in multiple topics
Klaus Mueller may have a diverse range of interests and hobbies
```

### Replay Agent memory, criticize and refine the knowledge in memory
Refer to the following script for an example of an Agent that replays its memory, performs self-criticism and adjusts its memory knowledge based on the criticism.
```shell
python -m examples.replay_criticize_refine
```
```text
refined "the second number in Fibonacci sequence is 2" into "Observation: The second number in the Fibonacci sequence is actually 1, not 2, and the sequence starts with 0, 1."
...
```

0 comments on commit 83fb432

Please sign in to comment.