Commit Graph

12 Commits

Author SHA1 Message Date
ian_Cin
8e0779a22d Enforce all IO objects to be subclassed from Document (#88)
* enforce Document as IO

* Separate rerankers, splitters and extractors (#85)

* partially refractor importing

* add text to embedding outputs

---------

Co-authored-by: Nguyen Trung Duc (john) <trungduc1992@gmail.com>
2023-11-27 16:35:09 +07:00
Nguyen Trung Duc (john)
2186c5558f Separate rerankers, splitters and extractors (#85) 2023-11-27 14:25:54 +07:00
Nguyen Trung Duc (john)
0a3fc4b228 Correct the use of abstractmethod (#80)
* Correct abstractmethod usage

* Update interface

* Specify minimal llama-index version [ignore cache]

* Update examples
2023-11-20 11:18:53 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
9945afdf6f Add Reranker implementation and integration in Retrieving pipeline (#77)
* Add base Reranker
* Add LLM Reranker
* Add Cohere Reranker
* Add integration of Rerankers in Retrieving pipeline
2023-11-15 16:03:51 +07:00
Nguyen Trung Duc (john)
b159897ac6 Combine docstores and vectorstores within a storages component (#72) 2023-11-14 17:50:57 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
640962e916 Update retrieving + agent pipeline (#71) 2023-11-14 16:40:13 +07:00
Nguyen Trung Duc (john)
8532138842 Move Document and other interface into base/schema (#69) 2023-11-14 11:51:10 +07:00
Nguyen Trung Duc (john)
d79b3744cb Simplify the BaseComponent inteface (#64)
This change remove `BaseComponent`'s:

- run_raw
- run_batch_raw
- run_document
- run_batch_document
- is_document
- is_batch

Each component is expected to support multiple types of inputs and a single type of output. Since we want the component to work out-of-the-box with both standardized and customized use cases, supporting multiple types of inputs are expected. At the same time, to reduce the complexity of understanding how to use a component, we restrict a component to only have a single output type.

To accommodate these changes, we also refactor some components to remove their run_raw, run_batch_raw... methods, and to decide the common output interface for those components.

Tests are updated accordingly.

Commit changes:

* Add kwargs to vector store's query
* Simplify the BaseComponent
* Update tests
* Remove support for Python 3.8 and 3.9
* Bump version 0.3.0
* Fix github PR caching still use old environment after bumping version

---------

Co-authored-by: ian <ian@cinnamon.is>
2023-11-13 15:10:18 +07:00
Tuan Anh Nguyen Dang (Tadashi_Cin)
56bc41b673 Update Base interface of Index/Retrieval pipeline (#36)
* add base Tool

* minor update test_tool

* update test dependency

* update test dependency

* Fix namespace conflict

* update test

* add base Agent Interface, add ReWoo Agent

* minor update

* update test

* fix typo

* remove unneeded print

* update rewoo agent

* add LLMTool

* update BaseAgent type

* add ReAct agent

* add ReAct agent

* minor update

* minor update

* minor update

* minor update

* update base reader with BaseComponent

* add splitter

* update agent and tool

* update vectorstores

* update load/save for indexing and retrieving pipeline

* update test_agent for more use-cases

* add missing dependency for test

* update test case for in memory vectorstore

* add TextSplitter to BaseComponent

* update type hint basetool

---------

Co-authored-by: trducng <trungduc1992@gmail.com>
2023-10-04 14:27:44 +07:00
Nguyen Trung Duc (john)
c6dd01e820 [AUR-338, AUR-406, AUR-407] Export pipeline to config for PromptUI. Construct PromptUI dynamically based on config. (#16)
From pipeline > config > UI. Provide example project for promptui

- Pipeline to config: `kotaemon.contribs.promptui.config.export_pipeline_to_config`. The config follows schema specified in this document: https://cinnamon-ai.atlassian.net/wiki/spaces/ATM/pages/2748711193/Technical+Detail. Note: this implementation exclude the logs, which will be handled in AUR-408.
- Config to UI: `kotaemon.contribs.promptui.build_from_yaml`
- Example project is located at `examples/promptui/`
2023-09-21 14:27:23 +07:00
ian_Cin
b794051653 [AUR-421] base output post-processor that works using regex. (#20) 2023-09-19 19:54:44 +07:00
Nguyen Trung Duc (john)
620b2b03ca [AUR-392, AUR-413, AUR-414] Define base vector store, and make use of ChromaVectorStore from llama_index. Indexing and retrieving vectors with vector store (#18)
Design the base interface of vector store, and apply it to the Chroma Vector Store (wrapped around llama_index's implementation). Provide the pipelines to populate and retrieve from vector store.
2023-09-14 14:18:20 +07:00