1. Changed the implementation of add_texts interface for the AwaDB
vector store in order to improve the performance
2. Upgrade the AwaDB from 0.3.2 to 0.3.3
---------
Co-authored-by: vincent <awadb.vincent@gmail.com>
Fixes https://github.com/hwchase17/langchain/issues/6172
As described in https://github.com/hwchase17/langchain/issues/6172, I'd
love to help update the dev container in this project.
**Summary of changes:**
- Dev container now builds (the current container in this repo won't
build for me)
- Dockerfile updates
- Update image to our [currently-maintained Python
image](https://github.com/devcontainers/images/tree/main/src/python/.devcontainer)
(`mcr.microsoft.com/devcontainers/python`) rather than the deprecated
image from vscode-dev-containers
- Move Dockerfile to root of repo - in order for `COPY` to work
properly, it needs the files (in this case, `pyproject.toml` and
`poetry.toml`) in the same directory
- devcontainer.json updates
- Removed `customizations` and `remoteUser` since they should be covered
by the updated image in the Dockerfile
- Update comments
- Update docker-compose.yaml to properly point to updated Dockerfile
- Add a .gitattributes to avoid line ending conversions, which can
result in hundreds of pending changes
([info](https://code.visualstudio.com/docs/devcontainers/tips-and-tricks#_resolving-git-line-ending-issues-in-containers-resulting-in-many-modified-files))
- Add a README in the .devcontainer folder and info on the dev container
in the contributing.md
**Outstanding questions:**
- Is it expected for `poetry install` to take some time? It takes about
30 minutes for this dev container to finish building in a Codespace, but
a user should only have to experience this once. Through some online
investigation, this doesn't seem unusual
- Versions of poetry newer than 1.3.2 failed every time - based on some
of the guidance in contributing.md and other online resources, it seemed
changing poetry versions might be a good solution. 1.3.2 is from Jan
2023
---------
Co-authored-by: bamurtaugh <brmurtau@microsoft.com>
Co-authored-by: Samruddhi Khandale <samruddhikhandale@github.com>
This PR refactors the ArxivAPIWrapper class making
`doc_content_chars_max` parameter optional. Additionally, tests have
been added to ensure the functionality of the doc_content_chars_max
parameter.
Fixes#6027 (issue)
There will likely be another change or two coming over the next couple
weeks as we stabilize the API, but putting this one in now which just
makes the integration a bit more flexible with the response output
format.
```
(langchain) danielking@MML-1B940F4333E2 langchain % pytest tests/integration_tests/llms/test_mosaicml.py tests/integration_tests/embeddings/test_mosaicml.py
=================================================================================== test session starts ===================================================================================
platform darwin -- Python 3.10.11, pytest-7.3.1, pluggy-1.0.0
rootdir: /Users/danielking/github/langchain
configfile: pyproject.toml
plugins: asyncio-0.20.3, mock-3.10.0, dotenv-0.5.2, cov-4.0.0, anyio-3.6.2
asyncio: mode=strict
collected 12 items
tests/integration_tests/llms/test_mosaicml.py ...... [ 50%]
tests/integration_tests/embeddings/test_mosaicml.py ...... [100%]
=================================================================================== slowest 5 durations ===================================================================================
4.76s call tests/integration_tests/llms/test_mosaicml.py::test_retry_logic
4.74s call tests/integration_tests/llms/test_mosaicml.py::test_mosaicml_llm_call
4.13s call tests/integration_tests/llms/test_mosaicml.py::test_instruct_prompt
0.91s call tests/integration_tests/llms/test_mosaicml.py::test_short_retry_does_not_loop
0.66s call tests/integration_tests/llms/test_mosaicml.py::test_mosaicml_extra_kwargs
=================================================================================== 12 passed in 19.70s ===================================================================================
```
#### Who can review?
@hwchase17
@dev2049
the current implement put the doc itself as the metadata, but the
document chatgpt plugin retriever returned already has a `metadata`
field, it's better to use that instead.
the original code will throw the following exception when using
`RetrievalQAWithSourcesChain`, becuse it can not find the field
`metadata`:
```python
Exception has occurred: ValueError (note: full exception trace is shown but execution is paused at: _run_module_as_main)
Document prompt requires documents to have metadata variables: ['source']. Received document with missing metadata: ['source'].
File "/home/wangjie/anaconda3/envs/chatglm/lib/python3.10/site-packages/langchain/chains/combine_documents/base.py", line 27, in format_document
raise ValueError(
File "/home/wangjie/anaconda3/envs/chatglm/lib/python3.10/site-packages/langchain/chains/combine_documents/stuff.py", line 65, in <listcomp>
doc_strings = [format_document(doc, self.document_prompt) for doc in docs]
File "/home/wangjie/anaconda3/envs/chatglm/lib/python3.10/site-packages/langchain/chains/combine_documents/stuff.py", line 65, in _get_inputs
doc_strings = [format_document(doc, self.document_prompt) for doc in docs]
File "/home/wangjie/anaconda3/envs/chatglm/lib/python3.10/site-packages/langchain/chains/combine_documents/stuff.py", line 85, in combine_docs
inputs = self._get_inputs(docs, **kwargs)
File "/home/wangjie/anaconda3/envs/chatglm/lib/python3.10/site-packages/langchain/chains/combine_documents/base.py", line 84, in _call
output, extra_return_dict = self.combine_docs(
File "/home/wangjie/anaconda3/envs/chatglm/lib/python3.10/site-packages/langchain/chains/base.py", line 140, in __call__
raise e
```
Additionally, the `metadata` filed in the `chatgpt plugin retriever`
have these fileds by default:
```json
{
"source": "file", //email, file or chat
"source_id": "filename.docx", // the filename
"url": "",
...
}
```
so, we should set `source_id` to `source` in the langchain metadata.
```python
metadata = d.pop("metadata", d)
if(metadata.get("source_id")):
metadata["source"] = metadata.pop("source_id")
```
#### Who can review?
@dev2049
<!-- For a quicker response, figure out the right person to tag with @
@hwchase17 - project lead
Tracing / Callbacks
- @agola11
Async
- @agola11
DataLoaders
- @eyurtsev
Models
- @hwchase17
- @agola11
Agents / Tools / Toolkits
- @vowelparrot
VectorStores / Retrievers / Memory
- @dev2049
-->
---------
Co-authored-by: wangjie <wangjie@htffund.com>
**Short Description**
Added a new argument to AutoGPT class which allows to persist the chat
history to a file.
**Changes**
1. Removed the `self.full_message_history: List[BaseMessage] = []`
2. Replaced it with `chat_history_memory` which can take any subclasses
of `BaseChatMessageHistory`
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
adding new loader for [acreom](https://acreom.com) vaults. It's based on
the Obsidian loader with some additional text processing for acreom
specific markdown elements.
@eyurtsev please take a look!
---------
Co-authored-by: rlm <pexpresss31@gmail.com>
Trying to call `ChatOpenAI.get_num_tokens_from_messages` returns the
following error for the newly announced models `gpt-3.5-turbo-0613` and
`gpt-4-0613`:
```
NotImplementedError: get_num_tokens_from_messages() is not presently implemented for model gpt-3.5-turbo-0613.See https://github.com/openai/openai-python/blob/main/chatml.md for information on how messages are converted to tokens.
```
This adds support for counting tokens for those models, by counting
tokens the same way they're counted for the previous versions of
`gpt-3.5-turbo` and `gpt-4`.
#### reviewers
- @hwchase17
- @agola11
Confluence API supports difference format of page content. The storage
format is the raw XML representation for storage. The view format is the
HTML representation for viewing with macros rendered as though it is
viewed by users.
Add the `content_format` parameter to `ConfluenceLoader.load()` to
specify the content format, this is
set to `ContentFormat.STORAGE` by default.
#### Who can review?
Tag maintainers/contributors who might be interested: @eyurtsev
---------
Co-authored-by: Harrison Chase <hw.chase.17@gmail.com>
<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.
Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.
After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.
Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->
## Add Solidity programming language support for code splitter.
Twitter: @0xjord4n_
<!-- If you're adding a new integration, please include:
1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use
See contribution guidelines for more information on how to write tests,
lint
etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
#### Who can review?
Tag maintainers/contributors who might be interested:
@hwchase17
<!-- For a quicker response, figure out the right person to tag with @
@hwchase17 - project lead
Tracing / Callbacks
- @agola11
Async
- @agola11
DataLoaders
- @eyurtsev
Models
- @hwchase17
- @agola11
Agents / Tools / Toolkits
- @hwchase17
VectorStores / Retrievers / Memory
- @dev2049
-->
<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.
Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.
After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.
Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->
<!-- Remove if not applicable -->
Fixes # (issue)
#### Before submitting
<!-- If you're adding a new integration, please include:
1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use
See contribution guidelines for more information on how to write tests,
lint
etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
#### Who can review?
Tag maintainers/contributors who might be interested:
<!-- For a quicker response, figure out the right person to tag with @
@hwchase17 - project lead
Tracing / Callbacks
- @agola11
Async
- @agola11
DataLoaders
- @eyurtsev
Models
- @hwchase17
- @agola11
Agents / Tools / Toolkits
- @hwchase17
VectorStores / Retrievers / Memory
- @dev2049
-->
<!--
Thank you for contributing to LangChain! Your PR will appear in our
release under the title you set. Please make sure it highlights your
valuable contribution.
Replace this with a description of the change, the issue it fixes (if
applicable), and relevant context. List any dependencies required for
this change.
After you're done, someone will review your PR. They may suggest
improvements. If no one reviews your PR within a few days, feel free to
@-mention the same people again, as notifications can get lost.
Finally, we'd love to show appreciation for your contribution - if you'd
like us to shout you out on Twitter, please also include your handle!
-->
<!-- Remove if not applicable -->
Fixes # (issue)
#### Before submitting
<!-- If you're adding a new integration, please include:
1. a test for the integration - favor unit tests that does not rely on
network access.
2. an example notebook showing its use
See contribution guidelines for more information on how to write tests,
lint
etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
#### Who can review?
Tag maintainers/contributors who might be interested:
<!-- For a quicker response, figure out the right person to tag with @
@hwchase17 - project lead
Tracing / Callbacks
- @agola11
Async
- @agola11
DataLoaders
- @eyurtsev
Models
- @hwchase17
- @agola11
Agents / Tools / Toolkits
- @vowelparrot
VectorStores / Retrievers / Memory
- @dev2049
-->
This adds implementation of MMR search in pinecone; and I have two
semi-related observations about this vector store class:
- Maybe we should also have a
`similarity_search_by_vector_returning_embeddings` like in supabase, but
it's not in the base `VectorStore` class so I didn't implement
- Talking about the base class, there's
`similarity_search_with_relevance_scores`, but in pinecone it is called
`similarity_search_with_score`; maybe we should consider renaming it to
align with other `VectorStore` base and sub classes (or add that as an
alias for backward compatibility)
#### Who can review?
Tag maintainers/contributors who might be interested:
- VectorStores / Retrievers / Memory - @dev2049
# Introduces embaas document extraction api endpoints
In this PR, we add support for embaas document extraction endpoints to
Text Embedding Models (with LLMs, in different PRs coming). We currently
offer the MTEB leaderboard top performers, will continue to add top
embedding models and soon add support for customers to deploy thier own
models. Additional Documentation + Infomation can be found
[here](https://embaas.io).
While developing this integration, I closely followed the patterns
established by other langchain integrations. Nonetheless, if there are
any aspects that require adjustments or if there's a better way to
present a new integration, let me know! :)
Additionally, I fixed some docs in the embeddings integration.
Related PR: #5976
#### Who can review?
DataLoaders
- @eyurtsev
