# Adds testing options to pytest
This PR adds the following options:
* `--only-core` will skip all extended tests, running all core tests.
* `--only-extended` will skip all core tests. Forcing alll extended
tests to be run.
Running `py.test` without specifying either option will remain
unaffected. Run
all tests that can be run within the unit_tests direction. Extended
tests will
run if required packages are installed.
## Before submitting
## Who can review?
[Text Generation
Inference](https://github.com/huggingface/text-generation-inference) is
a Rust, Python and gRPC server for generating text using LLMs.
This pull request add support for self hosted Text Generation Inference
servers.
feature: #4280
---------
Co-authored-by: Your Name <you@example.com>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Enhance the prompt to make the LLM generate right date for real today
Fixes # (issue)
Currently, if the user's question contains `today`, the clickhouse
always points to an old date. This may be related to the fact that the
GPT training data is relatively old.
### Add Invocation Params to Logged Run
Adds an llm type to each chat model as well as an override of the dict()
method to log the invocation parameters for each call
---------
Co-authored-by: Ankush Gola <ankush.gola@gmail.com>
# Your PR Title (What it does)
<!--
Thank you for contributing to LangChain! Your PR will appear in our next
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.
-->
<!-- Remove if not applicable -->
Fixes # (issue)
## Before submitting
<!-- If you're adding a new integration, include an integration test and
an example notebook showing its use! -->
## Who can review?
Community members can review the PR once tests pass. 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
DataLoader Abstractions
- @eyurtsev
LLM/Chat Wrappers
- @hwchase17
- @agola11
Tools / Toolkits
- @vowelparrot
-->
# Add `tiktoken` as dependency when installed as `langchain[openai]`
Fixes#4513 (issue)
## Who can review?
Community members can review the PR once tests pass. Tag
maintainers/contributors who might be interested:
@vowelparrot
<!-- 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
-->
### Add on_chat_message_start to callback manager and base tracer
Goal: trace messages directly to permit reloading as chat messages
(store in an integration-agnostic way)
Add an `on_chat_message_start` method. Fall back to `on_llm_start()` for
handlers that don't have it implemented.
Does so in a non-backwards-compat breaking way (for now)
# Make BaseStringMessagePromptTemplate.from_template return type generic
I use mypy to check type on my code that uses langchain. Currently after
I load a prompt and convert it to a system prompt I have to explicitly
cast it which is quite ugly (and not necessary):
```
prompt_template = load_prompt("prompt.yaml")
system_prompt_template = cast(
SystemMessagePromptTemplate,
SystemMessagePromptTemplate.from_template(prompt_template.template),
)
```
With this PR, the code would simply be:
```
prompt_template = load_prompt("prompt.yaml")
system_prompt_template = SystemMessagePromptTemplate.from_template(prompt_template.template)
```
Given how much langchain uses inheritance, I think this type hinting
could be applied in a bunch more places, e.g. load_prompt also return a
`FewShotPromptTemplate` or a `PromptTemplate` but without typing the
type checkers aren't able to infer that. Let me know if you agree and I
can take a look at implementing that as well.
@hwchase17 - project lead
DataLoaders
- @eyurtsev
Rebased Mahmedk's PR with the callback refactor and added the example
requested by hwchase plus a couple minor fixes
---------
Co-authored-by: Ahmed K <77802633+mahmedk@users.noreply.github.com>
Co-authored-by: Ahmed K <mda3k27@gmail.com>
Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com>
Co-authored-by: Corey Zumar <39497902+dbczumar@users.noreply.github.com>
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
We're fans of the LangChain framework thus we wanted to make sure we
provide an easy way for our customers to be able to utilize this
framework for their LLM-powered applications at our platform.
# Parameterize Redis vectorstore index
Redis vectorstore allows for three different distance metrics: `L2`
(flat L2), `COSINE`, and `IP` (inner product). Currently, the
`Redis._create_index` method hard codes the distance metric to COSINE.
I've parameterized this as an argument in the `Redis.from_texts` method
-- pretty simple.
Fixes#4368
## Before submitting
I've added an integration test showing indexes can be instantiated with
all three values in the `REDIS_DISTANCE_METRICS` literal. An example
notebook seemed overkill here. Normal API documentation would be more
appropriate, but no standards are in place for that yet.
## Who can review?
Not sure who's responsible for the vectorstore module... Maybe @eyurtsev
/ @hwchase17 / @agola11 ?
# Fix minor issues in self-query retriever prompt formatting
I noticed a few minor issues with the self-query retriever's prompt
while using it, so here's PR to fix them 😇
## Who can review?
Community members can review the PR once tests pass. 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
DataLoader Abstractions
- @eyurtsev
LLM/Chat Wrappers
- @hwchase17
- @agola11
Tools / Toolkits
- @vowelparrot
-->
# Add option to `load_huggingface_tool`
Expose a method to load a huggingface Tool from the HF hub
---------
Co-authored-by: Dev 2049 <dev.dev2049@gmail.com>
# Refactor the test workflow
This PR refactors the tests to run using a single test workflow. This
makes it easier to relaunch failing tests and see in the UI which test
failed since the jobs are grouped together.
## Before submitting
## Who can review?
Thanks to @anna-charlotte and @jupyterjazz for the contribution! Made
few small changes to get it across the finish line
---------
Signed-off-by: anna-charlotte <charlotte.gerhaher@jina.ai>
Signed-off-by: jupyterjazz <saba.sturua@jina.ai>
Co-authored-by: anna-charlotte <charlotte.gerhaher@jina.ai>
Co-authored-by: jupyterjazz <saba.sturua@jina.ai>
Co-authored-by: Saba Sturua <45267439+jupyterjazz@users.noreply.github.com>
# Add action to test with all dependencies installed
PR adds a custom action for setting up poetry that allows specifying a
cache key:
https://github.com/actions/setup-python/issues/505#issuecomment-1273013236
This makes it possible to run 2 types of unit tests:
(1) unit tests with only core dependencies
(2) unit tests with extended dependencies (e.g., those that rely on an
optional pdf parsing library)
As part of this PR, we're moving some pdf parsing tests into the
unit-tests section and making sure that these unit tests get executed
when running with extended dependencies.
# ODF File Loader
Adds a data loader for handling Open Office ODT files. Requires
`unstructured>=0.6.3`.
### Testing
The following should work using the `fake.odt` example doc from the
[`unstructured` repo](https://github.com/Unstructured-IO/unstructured).
```python
from langchain.document_loaders import UnstructuredODTLoader
loader = UnstructuredODTLoader(file_path="fake.odt", mode="elements")
loader.load()
loader = UnstructuredODTLoader(file_path="fake.odt", mode="single")
loader.load()
```
Any import that touches langchain.retrievers currently requires Lark.
Here's one attempt to fix. Not very pretty, very open to other ideas.
Alternatives I thought of are 1) make Lark requirement, 2) put
everything in parser.py in the try/except. Neither sounds much better
Related to #4316, #4275
Fixed two small bugs (as reported in issue #1619 ) in the filtering by
metadata for `chroma` databases :
- ```langchain.vectorstores.chroma.similarity_search``` takes a
```filter``` input parameter but do not forward it to
```langchain.vectorstores.chroma.similarity_search_with_score```
- ```langchain.vectorstores.chroma.similarity_search_by_vector```
doesn't take this parameter in input, although it could be very useful,
without any additional complexity - and it would thus be coherent with
the syntax of the two other functions.
Co-authored-by: Davis Chase <130488702+dev2049@users.noreply.github.com>
Currently, MultiPromptChain instantiates a ChatOpenAI LLM instance for
the default chain to use if none of the prompts passed match. This seems
like an error as it means that you can't use your choice of LLM, or
configure how to instantiate the default LLM (e.g. passing in an API key
that isn't in the usual env variable).
Fixes#4153
If the sender of a message in a group chat isn't in your contact list,
they will appear with a ~ prefix in the exported chat. This PR adds
support for parsing such lines.
