Nicolas
ad04585e30
community[minor]: Firecrawl.dev integration ( #20364 )
...
Added the [FireCrawl](https://firecrawl.dev ) document loader. Firecrawl
crawls and convert any website into LLM-ready data. It crawls all
accessible subpages and give you clean markdown for each.
- **Description:** Adds FireCrawl data loader
- **Dependencies:** firecrawl-py
- **Twitter handle:** @mendableai
ccing contributors: (@ericciarla @nickscamara)
---------
Co-authored-by: Bagatur <baskaryan@gmail.com>
Co-authored-by: Bagatur <22008038+baskaryan@users.noreply.github.com>
2024-04-12 19:13:48 +00:00
Tomaz Bratanic
a1b105ac00
experimental[patch]: Skip pydantic validation for llm graph transformer and fix JSON response where possible ( #19915 )
...
LLMs might sometimes return invalid response for LLM graph transformer.
Instead of failing due to pydantic validation, we skip it and manually
check and optionally fix error where we can, so that more information
gets extracted
2024-04-12 11:29:25 -07:00
Erick Friis
20f5cd7c95
docs: langchain-chroma package ( #20394 )
2024-04-12 11:17:05 -07:00
Haris Ali
6786fa9186
docs: Adding api documentation link at the end of each output parser class description page. ( #20391 )
...
- **Description:** Added cross-links for easy access of api
documentation of each output parser class from it's description page.
- **Issue:** related to issue #19969
Co-authored-by: Haris Ali <haris.ali@formulatrix.com>
2024-04-12 17:58:18 +00:00
P. Taylor Goetz
9317df7f16
community[patch]: Add "model" attribute to the payload sent to Ollama in ChatOllama ( #20354 )
...
Example Ollama API calls:
Request without "model":
```
curl --location 'http://localhost:11434/api/chat ' \
--header 'Content-Type: application/json' \
--data '{
"messages": [
{
"role": "user",
"content": "What is the capitol of PA?"
}
],
"stream": false
}'
```
Response:
```
{"error":"model is required"}
```
Request with "model":
```
curl --location 'http://localhost:11434/api/chat ' \
--header 'Content-Type: application/json' \
--data '{
"model": "openchat",
"messages": [
{
"role": "user",
"content": "What is the capitol of PA?"
}
],
"stream": false
}'
```
Response:
```
{
"eval_duration" : 733248000,
"created_at" : "2024-04-11T23:04:08.735766843Z",
"model" : "openchat",
"message" : {
"content" : " The capital city of Pennsylvania is Harrisburg.",
"role" : "assistant"
},
"total_duration" : 3138731168,
"prompt_eval_count" : 25,
"load_duration" : 466562959,
"done" : true,
"prompt_eval_duration" : 1938495000,
"eval_count" : 10
}
```
2024-04-12 13:32:53 -04:00
Bagatur
57bb940c17
docs: vertexai tool call update ( #20362 )
2024-04-12 10:09:54 -07:00
Alex Sherstinsky
fad0962643
community: for Predibase -- enable both Predibase-hosted and HuggingFace-hosted fine-tuned adapter repositories ( #20370 )
2024-04-12 08:32:00 -07:00
ccurme
5395c409cb
docs: add Cohere to ChatModelTabs ( #20386 )
2024-04-12 10:35:10 -04:00
Eugene Yurtsev
6470b30173
langchain[patch]: Add deprecation warning to extraction chains ( #20224 )
...
Add deprecation warnings to extraction chains
2024-04-12 10:24:32 -04:00
Eugene Yurtsev
b65a1d4cfd
langchain[patch]: Add another unit test for indexing code ( #20387 )
...
Add another unit test for indexing
2024-04-12 10:19:18 -04:00
Erick Friis
29282371db
core: bind_tools interface on basechatmodel ( #20360 )
2024-04-12 01:32:19 +00:00
Erick Friis
e6806a08d4
multiple: standard chat model tests ( #20359 )
2024-04-11 18:23:13 -07:00
Bagatur
f78564d75c
docs: show tool msg in tool call docs ( #20358 )
2024-04-11 16:42:04 -07:00
Isak Nyberg
bac9fb9a7c
community: add gpt-4 pricing in callback ( #20292 )
...
Added the pricing for `gpt-4-turbo` and `gpt-4-turbo-2024-04-09` in the
callback method.
related to issue #17173
https://openai.com/pricing#language-models
2024-04-11 18:02:39 -04:00
Ikko Eltociear Ashimine
cb29b42285
docs: Update ibm_watsonx.ipynb ( #20329 )
...
avaliable -> available
- **Description:** fixed typo
- **Issue:** the issue # it fixes, if applicable
- **Dependencies:** any dependencies required for this change
- **Twitter handle:** if your PR gets announced, and you'd like a
mention, we'll gladly shout you out!
2024-04-11 17:59:23 -04:00
Jack Wotherspoon
204a16addc
docs: add Cloud SQL for MySQL vector store integration docs ( #20278 )
...
Adding docs page for `Google Cloud SQL for MySQL` vector store
integration. This was recently released as part of the Cloud SQL for
MySQL LangChain package
([release](https://github.com/googleapis/langchain-google-cloud-sql-mysql-python/releases/tag/v0.2.0 ))
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-11 21:57:46 +00:00
Leonid Ganeline
7cf2d2759d
community[patch]: docstrings update ( #20301 )
...
Added missed docstrings. Format docstings to the consistent form.
2024-04-11 16:23:27 -04:00
Eugene Yurtsev
2900720cd3
core[patch]: Update documentation for base retriever ( #20345 )
...
Updating in code documentation for base retriever to direct folks toward
the .invoke and .ainvoke methods + explain how to implement
2024-04-11 16:20:14 -04:00
Bagatur
d2f4153fe6
docs: tool call nits ( #20356 )
2024-04-11 12:56:36 -07:00
Bagatur
eafd8c580b
docs: tool agent nit ( #20353 )
2024-04-11 19:41:31 +00:00
Erick Friis
ec0273fc92
chroma: release 0.1.0 ( #20355 )
2024-04-11 12:39:52 -07:00
Bagatur
a889cd14f3
docs: use vertexai in chat model tabs ( #20352 )
2024-04-11 12:34:19 -07:00
Bagatur
9d302c1b57
docs: update anthropic tool call ( #20344 )
2024-04-11 11:38:26 -07:00
Erick Friis
da707d0755
chroma: remove relevance score int test ( #20346 )
...
deprecating feature in #20302
2024-04-11 11:29:33 -07:00
Eugene Yurtsev
de938a4451
docs: Update chat model providers include package information ( #20336 )
...
Include package information
2024-04-11 13:29:42 -04:00
Bagatur
56fe4ab382
docs: update tool-calling table ( #20338 )
2024-04-11 09:50:20 -07:00
Bagatur
43a98592c1
docs: tool agent nit ( #20337 )
2024-04-11 09:43:12 -07:00
Bagatur
562b546bcc
docs: update chat openai ( #20331 )
2024-04-11 09:29:46 -07:00
Bagatur
2c4741b5ed
docs: add tool-calling agent ( #20328 )
2024-04-11 09:29:40 -07:00
ccurme
f02e55aaf7
docs: add component page for tool calls ( #20282 )
...
Note: includes links to API reference pages for ToolCall and other
objects that currently don't exist (e.g.,
https://api.python.langchain.com/en/latest/messages/langchain_core.messages.tool.ToolCall.html#langchain_core.messages.tool.ToolCall ).
2024-04-11 09:29:25 -07:00
Bagatur
6608089030
langchain[patch]: Release 0.1.16 ( #20335 )
2024-04-11 09:28:37 -07:00
Eugene Yurtsev
0e74fb4ec1
docs: Update list of chat models tool calling providers ( #20330 )
...
Will follow up with a few missing providers
2024-04-11 12:22:49 -04:00
Eugene Yurtsev
653489a1a9
docs: Update documentation for custom LLMs ( #19972 )
...
Update documentation for customizing LLMs
2024-04-11 12:21:27 -04:00
Bagatur
799714c629
release anthropic, fireworks, openai, groq, mistral ( #20333 )
2024-04-11 09:19:52 -07:00
Bagatur
e72330aacc
core[patch]: Release 0.1.42 ( #20332 )
2024-04-11 09:10:27 -07:00
ccurme
795c728f71
mistral[patch]: add IDs to tool calls ( #20299 )
...
Mistral gives us one ID per response, no individual IDs for tool calls.
```python
from langchain.agents import AgentExecutor, create_tool_calling_agent, tool
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain_mistralai import ChatMistralAI
prompt = ChatPromptTemplate.from_messages(
[
("system", "You are a helpful assistant"),
("human", "{input}"),
MessagesPlaceholder("agent_scratchpad"),
]
)
model = ChatMistralAI(model="mistral-large-latest", temperature=0)
@tool
def magic_function(input: int) -> int:
"""Applies a magic function to an input."""
return input + 2
tools = [magic_function]
agent = create_tool_calling_agent(model, tools, prompt)
agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
agent_executor.invoke({"input": "what is the value of magic_function(3)?"})
```
---------
Co-authored-by: Eugene Yurtsev <eyurtsev@gmail.com>
2024-04-11 11:09:30 -04:00
Eugene Yurtsev
22fd844e8a
community[patch]: Add deprecation warnings to postgres implementation ( #20222 )
...
Add deprecation warnings to postgres implementation that are in langchain-postgres.
2024-04-11 10:33:22 -04:00
Eugene Yurtsev
f02f708f52
core[patch]: For now remove user warning ( #20321 )
...
Remove warning since it creates a lot of noise.
2024-04-11 10:33:01 -04:00
Mayank Solanki
f709ab4cdf
docs: added backtick on RunnablePassthrough ( #20310 )
...
added backtick on RunnablePassthrough
Isuue: #20094
2024-04-11 08:39:10 -04:00
Bagatur
c706689413
openai[patch]: use tool_calls in request ( #20272 )
2024-04-11 03:55:52 -07:00
Bagatur
e936fba428
langchain[patch]: agents check prompt partial vars ( #20303 )
2024-04-11 03:55:09 -07:00
Bagatur
cb25fa0d55
core[patch]: fix ChatGeneration.text with content blocks ( #20294 )
2024-04-10 15:54:06 -07:00
Bagatur
03b247cca1
core[patch]: include tool_calls in ai msg chunk serialization ( #20291 )
2024-04-10 22:27:40 +00:00
Erick Friis
0fa551c278
chroma: bump rc, keep optional ( #20298 )
2024-04-10 14:22:56 -07:00
Erick Friis
16f8fff14f
chroma: add required fastapi dep to restrict to <1 ( #20297 )
2024-04-10 14:16:13 -07:00
Erick Friis
991fd82532
chroma: add optional fastapi dep to restrict to <1 ( #20295 )
2024-04-10 12:49:44 -07:00
killind-dev
f8a54d1d73
chroma: Add chroma partner package ( #19292 )
...
**Description:** Adds chroma to the partners package. Tests & code
mirror those in the community package.
**Dependencies:** None
**Twitter handle:** @akiradev0x
---------
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-10 19:33:45 +00:00
Yuki Watanabe
eef19954f3
core[patch]: fix duplicated kwargs in _load_sql_databse_chain ( #19908 )
...
`kwargs` is specified twice in [this
line](3218463f6a/libs/langchain/langchain/chains/loading.py (L386)
2024-04-10 12:20:28 -07:00
ccurme
39471a9c87
docs: update tool calling cookbook ( #20290 )
...
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-10 15:06:33 -04:00
Nuno Campos
15271ac832
core: mustache prompt templates ( #19980 )
...
Co-authored-by: Erick Friis <erick@langchain.dev>
2024-04-10 11:25:32 -07:00
