Commit Graph

3993 Commits

Author SHA1 Message Date
Eugene Yurtsev
c8f18a2524
langchain[patch]: Update import handling in adapters (#21079) 2024-04-30 10:55:29 -04:00
William FH
5c63ac3dd7
[Patch] Dedent docstring (#20959)
Technically a slight prompt breaking change, but I think positive EV in
that it saves tokens and results in more sane / in-distribution prompts
2024-04-30 07:40:57 -07:00
Eugene Yurtsev
845d8e0025
langchain[patch]: Update handling of deprecation warnings (#21083)
Chains should not be emitting deprecation warnings.
2024-04-30 10:30:23 -04:00
Christophe Bornet
5c77f45b06
community[minor]: Add async methods to CassandraCache and CassandraSemanticCache (#20654) 2024-04-30 10:27:44 -04:00
William FH
db14d4326d
[Core] Feat Pretty Print Tool calls (#20997)
Right now, `tool_calls` are not included in the `pretty_print()` output.
Would be nice to show!


![image](https://github.com/langchain-ai/langchain/assets/13333726/6a0ffca3-d02f-4e18-bc76-513eeca2e964)
2024-04-30 07:14:43 -07:00
Kuro Denjiro
fa4124b821
community[minor]: add mintbase loader to langchain (#20089)
- [x] **Add Near NFT loader**: "community: Load NFT near block chain
using mintbase graph API"

- [x] **PR message**: 
    - **Description:** a description of the change
    - **Twitter handle:**Kurodenjiro

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-30 04:11:56 +00:00
Alexander Dicke
d7e12750df
community[patch]: allows using text-generation-inference /generate route with HuggingFaceEndpoint (#20100)
- **Description:** allows to use the /generate route of
`text-generation-inference` with the `HuggingFaceEndpoint`
2024-04-29 23:09:55 -04:00
davidkgp
28b0b0d863
community[patch]: Fix for github issue #17690 (#20117)
…/17690

Thank you for contributing to LangChain!

- [x] **Fix Google Lens knowledge graph issue**: "langchain: community"
- Fix for [No "knowledge_graph" property in Google Lens API call from
SerpAPI](https://github.com/langchain-ai/langchain/issues/17690)


- [x] **PR message**: ***Delete this entire checklist*** and replace
with
- **Description:** handled the existence of keys in the json response of
Google Lens
- **Issue:** [No "knowledge_graph" property in Google Lens API call from
SerpAPI](https://github.com/langchain-ai/langchain/issues/17690)



- [x] **Lint and test**: Run `make format`, `make lint` and `make test`
from the root of the package(s) you've modified. See contribution
guidelines for more: https://python.langchain.com/docs/contributing/


If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-04-30 00:10:08 +00:00
高远
a7a4630bf4
community[patch]: Modify the text field type and add new exception handling (#20116)
Co-authored-by: gaoyuan <gaoyuan.20001218@bytedance.com>
2024-04-29 20:06:00 -04:00
Rahul Triptahi
c172611647
community[patch]: Add classifier_url argument in PebbloSafeLoader and documentation update. (#21030)
Description: Add classifier_url argument in PebbloSafeLoader.
Documentation: Updated PebbloSafeLoader documentation with above change
and new links for pebblo github pages.

---------

Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
2024-04-29 17:41:09 -04:00
Leonid Ganeline
08d08d7c83
docs: langchain docstrings updates (#21032)
Added missed docstings. Formatted docstrings into a consistent format.
2024-04-29 17:40:44 -04:00
Leonid Ganeline
85094cbb3a
docs: community docstring updates (#21040)
Added missed docstrings. Updated docstrings to consistent format.
2024-04-29 17:40:23 -04:00
Rodrigo Nogueira
90f19028e5
community[patch]: Add maritalk streaming (sync and async) (#19203)
Co-authored-by: RosevalJr <rdmalajr@gmail.com>
Co-authored-by: Roseval Donisete Malaquias Junior <roseval@maritaca.ai>
2024-04-29 21:31:14 +00:00
Cahid Arda Öz
cc6191cb90
community[minor]: Add support for Upstash Vector (#20824)
## Description

Adding `UpstashVectorStore` to utilize [Upstash
Vector](https://upstash.com/docs/vector/overall/getstarted)!

#17012 was opened to add Upstash Vector to langchain but was closed to
wait for filtering. Now filtering is added to Upstash vector and we open
a new PR. Additionally, [embedding
feature](https://upstash.com/docs/vector/features/embeddingmodels) was
added and we add this to our vectorstore aswell.

## Dependencies

[upstash-vector](https://pypi.org/project/upstash-vector/) should be
installed to use `UpstashVectorStore`. Didn't update dependencies
because of [this comment in the previous
PR](https://github.com/langchain-ai/langchain/pull/17012#pullrequestreview-1876522450).

## Tests

Tests are added and they pass. Tests are naturally network bound since
Upstash Vector is offered through an API.

There was [a discussion in the previous PR about mocking the
unittests](https://github.com/langchain-ai/langchain/pull/17012#pullrequestreview-1891820567).
We didn't make changes to this end yet. We can update the tests if you
can explain how the tests should be mocked.

---------

Co-authored-by: ytkimirti <yusuftaha9@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-29 17:25:01 -04:00
Leonid Ganeline
1a2ff56cd8
core[patch[: docstring update (#21036)
Added missed docstrings. Updated docstrings to consistent format.
2024-04-29 15:35:34 -04:00
Eugene Yurtsev
f479a337cc
langchain[patch]: replace deprecated imports with imports from langchain_core (#21033)
* Output of running the migration script.
* Ran only against langchain code itself and not the unit tests.
2024-04-29 15:34:31 -04:00
Eugene Yurtsev
82d4afcac0
langchain[minor]: Code to handle dynamic imports (#20893)
Proposing to centralize code for handling dynamic imports. This allows treating langchain-community as an optional dependency.

---

The proposal is to scan the code base and to replace all existing imports with dynamic imports using this functionality.
2024-04-29 15:34:03 -04:00
Erick Friis
854ae3e1de
mistralai: release 0.1.5, allow client passing in (#21034) 2024-04-29 17:14:26 +00:00
chyroc
3e241956d3
community[minor]: add coze chat model (#20770)
add coze chat model, to call coze.com apis
2024-04-29 12:26:16 -04:00
Eugene Yurtsev
29493bb598
cli[minor]: improve confirmation message with more details (#21027)
Improve confirmation message with more details
2024-04-29 12:20:42 -04:00
Eugene Yurtsev
aab78a37f3
cli[patch]: Ignore imports that change the name of the class (#21026)
Not currently handeled by migration script
2024-04-29 12:20:30 -04:00
Massimiliano Pronesti
ce89b34fc0
community[patch]: support hybrid search with threshold in Azure AI Search Retriever (#20907)
Support hybrid search with a score threshold -- similar to what we do
for similarity search.
2024-04-29 12:11:44 -04:00
Andrei Panferov
b3efa38cc0
community[patch]: GigaChat model selection fix (#20988)
Fixed the error that the model name is never actually put into GigaChat
request payload, always defaulting to `GigaChat-Lite`.

With this fix, model selection through
```python
import os
from langchain.chat_models.gigachat import GigaChat

chat = GigaChat(
    name="GigaChat-Pro", # <- HERE!!!!!
    ...
)
```
should actually work, as intended in
[here](804390ba4b/libs/community/langchain_community/llms/gigachat.py (L36)).

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-04-29 16:08:26 +00:00
Patrick McFadin
3331865f6b
community[minor]: add Cassandra Database Toolkit (#20246)
**Description**: ToolKit and Tools for accessing data in a Cassandra
Database primarily for Agent integration. Initially, this includes the
following tools:
- `cassandra_db_schema` Gathers all schema information for the connected
database or a specific schema. Critical for the agent when determining
actions.
- `cassandra_db_select_table_data` Selects data from a specific keyspace
and table. The agent can pass paramaters for a predicate and limits on
the number of returned records.
- `cassandra_db_query` Expiriemental alternative to
`cassandra_db_select_table_data` which takes a query string completely
formed by the agent instead of parameters. May be removed in future
versions.

Includes unit test and two notebooks to demonstrate usage. 

**Dependencies**: cassio
**Twitter handle**: @PatrickMcFadin

---------

Co-authored-by: Phil Miesle <phil.miesle@datastax.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-29 15:51:43 +00:00
Igor Brai
b3e74f2b98
community[minor]: add mojeek search util (#20922)
**Description:** This pull request introduces a new feature to community
tools, enhancing its search capabilities by integrating the Mojeek
search engine
**Dependencies:** None

---------

Co-authored-by: Igor Brai <igor@mojeek.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: ccurme <chester.curme@gmail.com>
2024-04-29 15:49:53 +00:00
hmn falahi
4822beb298
Ignore self/cls from required args of class functions in convert_to_openai_tool (#20691)
Removed redundant self/cls from required args of class functions in
_get_python_function_required_args:

```python
class MemberTool:
    def search_member(
            self,
            keyword: str,
            *args,
            **kwargs,
    ):
        """Search on members with any keyword like first_name, last_name, email

        Args:
            keyword: Any keyword of member
        """

        headers = dict(authorization=kwargs['token'])
        members = []
        try:
            members = request_(
                method='SEARCH',
                url=f'{service_url}/apiv1/members',
                headers=headers,
                json=dict(query=keyword),
            )

        except Exception as e:
            logger.info(e.__doc__)

        return members

convert_to_openai_tool(MemberTool.search_member)
```
expected result:
```
{'type': 'function', 'function': {'name': 'search_member', 'description': 'Search on members with any keyword like first_name, last_name, username, email', 'parameters': {'type': 'object', 'properties': {'keyword': {'type': 'string', 'description': 'Any keyword of member'}}, 'required': ['keyword']}}}
```

#20685

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-29 11:46:26 -04:00
Eugene Yurtsev
4f4ee8e2cf
cli[patch]: Update migrations file manually (#21021)
We need to replace occurrences in the code of RunnableMap not just the
import,
so for now, we don't replace RunnableMap.
2024-04-29 10:53:31 -04:00
Tomaz Bratanic
67428c4052
community[patch]: Neo4j enhanced schema (#20983)
Scan the database for example values and provide them to an LLM for
better inference of Text2cypher
2024-04-29 10:45:55 -04:00
aditya thomas
8b59bddc03
anthropic[patch]: add tests for secret_str for api key (#20986)
**Description:** Add tests to check API keys are masked
**Issue:** Resolves
https://github.com/langchain-ai/langchain/issues/12165 for Anthropic
models
**Dependencies:** None
2024-04-29 10:39:14 -04:00
Pengcheng Liu
1fad39be1c
community[minor]: Add LarkSuite wiki document loader. (#21016)
**Description:** Add LarkSuite wiki document loader. Refer to [LarkSuite
api document
](https://open.feishu.cn/document/server-docs/docs/wiki-v2/space-node/list)for
details.
**Issue:** None
**Dependencies:** None
**Twitter handle:** None
2024-04-29 10:37:50 -04:00
Leonid Ganeline
dc7c06bc07
community[minor]: import fix (#20995)
Issue: When the third-party package is not installed, whenever we need
to `pip install <package>` the ImportError is raised.
But sometimes, the `ValueError` or `ModuleNotFoundError` is raised. It
is bad for consistency.
Change: replaced the `ValueError` or `ModuleNotFoundError` with
`ImportError` when we raise an error with the `pip install <package>`
message.
Note: Ideally, we replace all `try: import... except... raise ... `with
helper functions like `import_aim` or just use the existing
[langchain_core.utils.utils.guard_import](https://api.python.langchain.com/en/latest/utils/langchain_core.utils.utils.guard_import.html#langchain_core.utils.utils.guard_import)
But it would be much bigger refactoring. @baskaryan Please, advice on
this.
2024-04-29 10:32:50 -04:00
Karim Lalani
2ddac9a7c3
experimental[minor]: Add bind_tools and with_structured_output functions to OllamaFunctions (#20881)
Implemented bind_tools for OllamaFunctions.
Made OllamaFunctions sub class of ChatOllama.
Implemented with_structured_output for OllamaFunctions.

integration unit test has been updated.
notebook has been updated.

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-29 14:13:33 +00:00
Eugene Yurtsev
d781560722
cli[minor]: Add ipynb support, add text_splitters (#20963) 2024-04-29 10:11:21 -04:00
WilliamEspegren
804390ba4b
community: Spider integration (#20937)
Added the [Spider.cloud](https://spider.cloud) document loader.
[Spider](https://github.com/spider-rs/spider) is the
[fastest](https://github.com/spider-rs/spider/blob/main/benches/BENCHMARKS.md)
and cheapest crawler that returns LLM-ready data.

```
- **Description:** Adds Spider data loader
- **Dependencies:** spider-client
- **Twitter handle:** @WilliamEspegren 
```

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: = <=>
Co-authored-by: Chester Curme <chester.curme@gmail.com>
2024-04-27 21:45:03 +00:00
ccurme
9ec7151317
fireworks: fix integration tests (#20973) 2024-04-27 19:49:46 +00:00
William FH
9fa9f05e5d
Catch System Error in ast parse (#20961)
I can't seem to reproduce, but i got this:

```
SystemError: AST constructor recursion depth mismatch (before=102, after=37)
```

And the operation isn't critical for the actual forward pass so seems
preferable to expand our caught exceptions
2024-04-26 19:31:55 -07:00
YH
2aca7fcdcf
core[patch]: Enhance link extraction with query parameters (#20259)
**Description**: This update enhances the `extract_sub_links` function
within the `langchain_core/utils/html.py` module to include query
parameters in the extracted URLs.

**Issue**: N/A

**Dependencies**: No additional dependencies required for this change.

**Twitter handle**: N/A

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-04-27 02:22:36 +00:00
Chip Davis
e818c75f8a
infra: test directory loader multithreaded (#20281)
This is a unit test for #20230 which was a fix for using multithreaded
mode with directory loader @eyurtsev
2024-04-26 19:16:47 -07:00
Guilherme Zanotelli
f931a9ce60
community[patch]: Pass kwargs to SPARQLStore from RdfGraph (#20385)
This introduces `store_kwargs` which behaves similarly to `graph_kwargs`
on the `RdfGraph` object, which will enable users to pass `headers` and
other arguments to the underlying `SPARQLStore` object. I have also made
a [PR in `rdflib` to support passing
`default_graph`](https://github.com/RDFLib/rdflib/pull/2761).

Example usage:
```python
from langchain_community.graphs import RdfGraph

graph = RdfGraph(
    query_endpoint="http://localhost/sparql",
    standard="rdf",
    store_kwargs=dict(
        default_graph="http://example.com/mygraph"
    )
)
```

<!--If no one reviews your PR within a few days, please @-mention one of
baskaryan, efriis, eyurtsev, hwchase17.-->

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-27 01:38:29 +00:00
Jorge Piedrahita Ortiz
40b2e2916b
community[minor]: Sambanova llm integration (#20955)
- **Description:** Added [Sambanova systems](https://sambanova.ai/)
integration, including sambaverse and sambastudio LLMs
- **Dependencies:**   sseclient-py  (optional)

---------

Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-27 01:05:13 +00:00
Rahul Triptahi
955cf186d2
community[patch]: Ingest source, owner and full_path if present in Document's metadata. (#20949)
Description: The PebbloSafeLoader should first check for owner,
full_path and size in metadata before implementing its own logic.
Dependencies: None
Documentation: NA.

Signed-off-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
Co-authored-by: Rahul Tripathi <rauhl.psit.ec@gmail.com>
2024-04-26 17:50:57 -07:00
Amine Djeghri
790ea75cf7
community[minor]: add exllamav2 library for GPTQ & EXL2 models (#17817)
Added 3 files : 
- Library : ExLlamaV2 
- Test integration
- Notebook

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-04-27 00:44:43 +00:00
Naveen Tatikonda
8bbdb4f6a0
community[patch]: Add OpenSearch as semantic cache (#20254)
### Description
Use OpenSearch vector store as Semantic Cache.

### Twitter Handle
**@OpenSearchProj**

---------

Signed-off-by: Naveen Tatikonda <navtat@amazon.com>
Co-authored-by: Harish Tatikonda <harishtatikonda@Harishs-MacBook-Air.local>
Co-authored-by: EC2 Default User <ec2-user@ip-172-31-31-155.ec2.internal>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-27 00:20:24 +00:00
Mayank Solanki
8c085fc697
community[patch]: Added a function from_existing_collection in Qdrant vector database. (#20779)
Issue: #20514 
The current implementation of `construct_instance` expects a `texts:
List[str]` that will call the embedding function. This might not be
needed when we already have a client with collection and `path, you
don't want to add any text.

This PR adds a class method that returns a qdrant instance with an
existing client.

Here everytime
cb6e5e56c2/libs/community/langchain_community/vectorstores/qdrant.py (L1592)
`construct_instance` is called, this line sends some text for embedding
generation.

---------

Co-authored-by: Anush <anushshetty90@gmail.com>
2024-04-26 15:34:09 -07:00
Leonid Kuligin
893a924b90
core[minor], community[patch], langchain[patch]: move BaseChatLoader to core (#19607)
Thank you for contributing to LangChain!

- [ ] **PR title**: "core: move BaseChatLoader and BaseToolkit from
community"


- [ ] **PR message**: move BaseChatLoader and BaseToolkit

---------

Co-authored-by: Bagatur <baskaryan@gmail.com>
2024-04-26 21:45:51 +00:00
Erick Friis
d4befd0cfb
core: fix batch ordering test (#20952) 2024-04-26 21:17:26 +00:00
Eugene Yurtsev
8ed150b2fe
cli[minor]: Fix bug to account for name changes (#20948)
* Fix bug to account for name changes / aliases
* Generate migration list from langchain to langchain_core
2024-04-26 15:45:11 -04:00
Eugene Yurtsev
2fa0ff1a2d
cli[minor]: update code to generate migrations from langchain to community (#20946)
Updates code that generates migrations from langchain to community
2024-04-26 15:11:32 -04:00
ccurme
bf16cefd18
langchain: deprecate create_structured_output_runnable (#20933) 2024-04-26 14:00:40 -04:00
Erick Friis
38eccab3ae
upstage: release 0.1.3 (#20941) 2024-04-26 10:36:11 -07:00