This pull request aims to ensure that the `OpenAICallbackHandler` can
properly calculate the total cost for Azure OpenAI chat models. The
following changes have resolved this issue:
- The `model_name` has been added to the ChatResult llm_output. Without
this, the default values of `gpt-35-turbo` were applied. This was
causing the total cost for Azure OpenAI's GPT-4 to be significantly
inaccurate.
- A new parameter `model_version` has been added to `AzureChatOpenAI`.
Azure does not include the model version in the response. With the
addition of `model_name`, this is not a significant issue for GPT-4
models, but it's an issue for GPT-3.5-Turbo. Version 0301 (default) of
GPT-3.5-Turbo on Azure has a flat rate of 0.002 per 1k tokens for both
prompt and completion. However, version 0613 introduced a split in
pricing for prompt and completion tokens.
- The `OpenAICallbackHandler` implementation has been updated with the
proper model names, versions, and cost per 1k tokens.
Unit tests have been added to ensure the functionality works as
expected; the Azure ChatOpenAI notebook has been updated with examples.
Maintainers: @hwchase17, @baskaryan
Twitter handle: @jjczopek
---------
Co-authored-by: Jerzy Czopek <jerzy.czopek@avanade.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: a description of the change,
- Issue: the issue # it fixes (if applicable),
- Dependencies: any dependencies required for this change,
- Tag maintainer: for a quicker response, tag the relevant maintainer
(see below),
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!
Please make sure you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
---------
Co-authored-by: jacoblee93 <jacoblee93@gmail.com>
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Instruction for integration with Log10: an [open
source](https://github.com/log10-io/log10) proxiless LLM data management
and application development platform that lets you log, debug and tag
your Langchain calls
- Tag maintainer: @baskaryan
- Twitter handle: @log10io @coffeephoenix
Several examples showing the integration included
[here](https://github.com/log10-io/log10/tree/main/examples/logging) and
in the PR
Description: Adds Rockset as a chat history store
Dependencies: no changes
Tag maintainer: @hwchase17
This PR passes linting and testing.
I added a test for the integration and an example notebook showing its
use.
This PR adds 8 new loaders:
* `AirbyteCDKLoader` This reader can wrap and run all python-based
Airbyte source connectors.
* Separate loaders for the most commonly used APIs:
* `AirbyteGongLoader`
* `AirbyteHubspotLoader`
* `AirbyteSalesforceLoader`
* `AirbyteShopifyLoader`
* `AirbyteStripeLoader`
* `AirbyteTypeformLoader`
* `AirbyteZendeskSupportLoader`
## Documentation and getting started
I added the basic shape of the config to the notebooks. This increases
the maintenance effort a bit, but I think it's worth it to make sure
people can get started quickly with these important connectors. This is
also why I linked the spec and the documentation page in the readme as
these two contain all the information to configure a source correctly
(e.g. it won't suggest using oauth if that's avoidable even if the
connector supports it).
## Document generation
The "documents" produced by these loaders won't have a text part
(instead, all the record fields are put into the metadata). If a text is
required by the use case, the caller needs to do custom transformation
suitable for their use case.
## Incremental sync
All loaders support incremental syncs if the underlying streams support
it. By storing the `last_state` from the reader instance away and
passing it in when loading, it will only load updated records.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This PR defines an abstract interface for key value stores.
It provides 2 implementations:
1. Local File System
2. In memory -- used to facilitate testing
It also provides an encoder utility to help take care of serialization
from arbitrary data to data that can be stored by the given store
Proposal for an internal API to deprecate LangChain code.
This PR is heavily based on:
https://github.com/matplotlib/matplotlib/blob/main/lib/matplotlib/_api/deprecation.py
This PR only includes deprecation functionality (no renaming etc.).
Additional functionality can be added on a need basis (e.g., renaming
parameters), but best to roll out as an MVP to test this
out.
DeprecationWarnings are ignored by default. We can change the policy for
the deprecation warnings, but we'll need to make sure we're not creating
noise for users due to internal code invoking deprecated functionality.
- Description: consistent timeout at 60s for all calls to Vectara API
- Tag maintainer: @rlancemartin, @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Replace this comment with:
- Description: Improved query of BGE embeddings after talking with the
devs of BGE embeddings ,
- Dependencies: any dependencies required for this change,
- Tag maintainer: @hwchase17 ,
- Twitter handle: @ManabChetia3
---------
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
- Description: added filter to query methods in VectorStoreIndexWrapper
for filtering by metadata (i.e. search_kwargs)
- Tag maintainer: @rlancemartin, @eyurtsev
Updated the doc snippet on this topic as well. It took me a long while
to figure out how to filter the vectorstore by filename, so this might
help someone else out.
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: I have added an example showing how to pass a custom
template to ConversationRetrievalChain. Instead of
CONDENSE_QUESTION_PROMPT we can pass any prompt in the argument
condense_question_prompt. Look in Use cases -> QA over Documents -> How
to -> Store and reference chat history,
- Issue: #8864,
- Dependencies: NA,
- Tag maintainer: @hinthornw,
- Twitter handle:
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
This addresses some issues with introducing the Nebula LLM to LangChain
in this PR:
https://github.com/langchain-ai/langchain/pull/8876
This fixes the following:
- Removes `SYMBLAI` from variable names
- Fixes bug with `Bearer` for the API KEY
Thanks again in advance for your help!
cc: @hwchase17, @baskaryan
---------
Co-authored-by: dvonthenen <david.vonthenen@gmail.com>
### Description
Now, we can pass information like a JWT token using user_context:
```python
self.retriever = AmazonKendraRetriever(index_id=kendraIndexId, user_context={"Token": jwt_token})
```
- [x] `make lint`
- [x] `make format`
- [x] `make test`
Also tested by pip installing in my own project, and it allows access
through the token.
### Maintainers
@rlancemartin, @eyurtsev
### My twitter handle
[girlknowstech](https://twitter.com/girlknowstech)
Minor doc fix to awslambda tool notebook.
Add missing import for initialize_agent to awslambda agent example
Co-authored-by: Josh Hart <josharj@amazon.com>
- Description: The API doc passed to LLM only included the content of
responses but did not include the content of requestBody, causing the
agent to be unable to construct the correct request parameters based on
the requestBody information. Add two lines of code fixed the bug,
- Issue: the issue # it fixes (if applicable),
- Dependencies: any dependencies required for this change,
- Tag maintainer: @hinthornw ,
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!
Description:
Fixed inaccurate import in integrations:providers:bedrock documentation
In the current version of the bedrock documentation, page
https://python.langchain.com/docs/integrations/providers/bedrock it
states that the import is from langchain import Bedrock
This has been changed to from langchain.llms.bedrock import Bedrock as
stated in https://python.langchain.com/docs/integrations/llms/bedrock
Issue:
Not applicable
Dependencies
No dependencies required
Tag maintainer
@baskaryan
Twitter handle:
Not applicable
Adds Ollama as an LLM. Ollama can run various open source models locally
e.g. Llama 2 and Vicuna, automatically configuring and GPU-optimizing
them.
@rlancemartin @hwchase17
---------
Co-authored-by: Lance Martin <lance@langchain.dev>
## Description
I am excited to propose an integration with USearch, a lightweight
vector-search engine available for both Python and JavaScript, among
other languages.
## Dependencies
It introduces a new PyPi dependency - `usearch`. I am unsure if it must
be added to the Poetry file, as this would make the PR too clunky.
Please let me know.
## Profiles
- Maintainers: @ashvardanian @davvard
- Twitter handles: @ashvardanian @unum_cloud
---------
Co-authored-by: Davit Vardanyan <78792753+davvard@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
- fix install command
- change example notebook to use Metaphor autoprompt by default
<!-- Thank you for contributing to LangChain!
Replace this comment with:
- Description: a description of the change,
- Issue: the issue # it fixes (if applicable),
- Dependencies: any dependencies required for this change,
- Tag maintainer: for a quicker response, tag the relevant maintainer
(see below),
- Twitter handle: we announce bigger features on Twitter. If your PR
gets announced and you'd like a mention, we'll gladly shout you out!
Please make sure you're PR is passing linting and testing before
submitting. Run `make format`, `make lint` and `make test` to check this
locally.
If you're adding a new integration, please include:
1. a test for the integration, preferably unit tests that do not rely on
network access,
2. an example notebook showing its use.
Maintainer responsibilities:
- General / Misc / if you don't know who to tag: @baskaryan
- DataLoaders / VectorStores / Retrievers: @rlancemartin, @eyurtsev
- Models / Prompts: @hwchase17, @baskaryan
- Memory: @hwchase17
- Agents / Tools / Toolkits: @hinthornw
- Tracing / Callbacks: @agola11
- Async: @agola11
If no one reviews your PR within a few days, feel free to @-mention the
same people again.
See contribution guidelines for more information on how to write/run
tests, lint, etc:
https://github.com/hwchase17/langchain/blob/master/.github/CONTRIBUTING.md
-->
Update to #8528
Newlines and other special characters within markdown code blocks
returned as `action_input` should be handled correctly (in particular,
unescaped `"` => `\"` and `\n` => `\\n`) so they don't break JSON
parsing.
@baskaryan
when e.g. downloading a sitemap with a malformed url (e.g.
"ttp://example.com/index.html" with the h omitted at the beginning of
the url), this will ensure that the sitemap download does not crash, but
just emits a warning. (maybe should be optional with e.g. a
`skip_faulty_urls:bool=True` parameter, but this was the most
straightforward fix)
@rlancemartin, @eyurtsev
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Added async parsing functions for RetryOutputParser,
RetryWithErrorOutputParser and OutputFixingParser.
The async parse functions call the arun methods of the used LLMChains.
Fix for #7989
---------
Co-authored-by: Benjamin May <benjamin.may94@gmail.com>
