> ## Documentation Index
> Fetch the complete documentation index at: https://langchat.neurobrains.co/llms.txt
> Use this file to discover all available pages before exploring further.

# Configuration

> Configure LLM providers, vector databases, and all LangChat settings.

## The pattern

All providers live in `langchat.providers`. Every provider reads credentials from environment variables automatically — you don't pass keys in code.

```python theme={null}
from langchat import LangChat
from langchat.providers import OpenAI, Pinecone, Supabase

lc = LangChat(
    llm=OpenAI("gpt-4o-mini"),      # reads OPENAI_API_KEY
    vector_db=Pinecone("my-index"), # reads PINECONE_API_KEY
    db=Supabase(),                  # reads SUPABASE_URL + SUPABASE_KEY
)
```

You can also pass credentials explicitly when environment variables aren't available:

```python theme={null}
lc = LangChat(
    llm=OpenAI("gpt-4o-mini", api_key="sk-..."),
    vector_db=Pinecone("my-index", api_key="pcsk-..."),
    db=Supabase(url="https://xxxx.supabase.co", key="eyJ..."),
)
```

***

## LLM providers

### OpenAI

```python theme={null}
from langchat.providers import OpenAI

llm = OpenAI("gpt-4o-mini")                    # default
llm = OpenAI("gpt-4o", temperature=0.3)        # more deterministic
llm = OpenAI("gpt-4o-mini", temperature=1.0)   # more creative (default)
```

**Environment variable:** `OPENAI_API_KEY`

**Available models:** `gpt-4o-mini` · `gpt-4o` · `gpt-4-turbo` · `gpt-3.5-turbo` · any valid OpenAI chat model

**Multiple API keys** (automatic rotation on failure):

```python theme={null}
llm = OpenAI("gpt-4o-mini", api_keys=["sk-key1", "sk-key2", "sk-key3"])
```

<ParamField path="model" type="str" default="gpt-4o-mini">
  OpenAI model name. First positional argument.
</ParamField>

<ParamField path="api_key" type="str | None" default="None">
  API key. Defaults to `OPENAI_API_KEY` environment variable.
</ParamField>

<ParamField path="api_keys" type="list[str] | None" default="None">
  Multiple API keys for automatic rotation. Takes precedence over `api_key`.
</ParamField>

<ParamField path="temperature" type="float" default="1.0">
  Sampling temperature. Lower = more deterministic.
</ParamField>

<ParamField path="max_retries_per_key" type="int" default="2">
  Retries per key before rotating to the next one.
</ParamField>

***

### Anthropic

```python theme={null}
from langchat.providers import Anthropic

llm = Anthropic("claude-3-5-sonnet-20241022")
llm = Anthropic("claude-3-5-haiku-20241022")   # faster, cheaper
llm = Anthropic("claude-3-opus-20240229")       # most capable
```

**Environment variable:** `ANTHROPIC_API_KEY`

***

### Google Gemini

```python theme={null}
from langchat.providers import Gemini

llm = Gemini("gemini-1.5-flash")   # fast and efficient
llm = Gemini("gemini-1.5-pro")     # higher quality
llm = Gemini("gemini-2.0-flash")   # latest
```

**Environment variables:** `GEMINI_API_KEY` or `GOOGLE_API_KEY` (either works)

***

### Mistral

```python theme={null}
from langchat.providers import Mistral

llm = Mistral("mistral-large-latest")
llm = Mistral("mistral-small-latest")   # faster, cheaper
```

**Environment variable:** `MISTRAL_API_KEY`

***

### Cohere

```python theme={null}
from langchat.providers import Cohere

llm = Cohere("command-r-plus")
llm = Cohere("command-r")        # faster, cheaper
```

**Environment variable:** `COHERE_API_KEY`

***

### Ollama (local)

No API key required. Ollama runs on your own machine.

```python theme={null}
from langchat.providers import Ollama

llm = Ollama("llama3.2")                                  # default endpoint
llm = Ollama("llama3.2", base_url="http://192.168.1.5:11434")  # remote instance
```

[Install Ollama](https://ollama.ai) and pull a model first:

```bash theme={null}
ollama pull llama3.2
```

***

## Vector database

### Pinecone

```python theme={null}
from langchat.providers import Pinecone

vector_db = Pinecone("my-index")                              # default embedding model
vector_db = Pinecone("my-index", embedding_model="text-embedding-3-small")  # smaller, cheaper
```

**Environment variables:** `PINECONE_API_KEY` and `OPENAI_API_KEY` (for embeddings)

<ParamField path="index" type="str" required>
  Pinecone index name. First positional argument.
</ParamField>

<ParamField path="api_key" type="str | None" default="None">
  Pinecone API key. Defaults to `PINECONE_API_KEY`.
</ParamField>

<ParamField path="embedding_api_key" type="str | None" default="None">
  OpenAI API key for embeddings. Defaults to `OPENAI_API_KEY`.
</ParamField>

<ParamField path="embedding_model" type="str" default="text-embedding-3-large">
  OpenAI embedding model. Use `text-embedding-3-small` for lower cost.
</ParamField>

<Warning>
  Your Pinecone index dimensions must match the embedding model:

  * `text-embedding-3-large` → **3072** dimensions
  * `text-embedding-3-small` → **1536** dimensions
</Warning>

***

## History database

### Supabase

```python theme={null}
from langchat.providers import Supabase

db = Supabase()                                              # reads from env
db = Supabase(url="https://xxxx.supabase.co", key="eyJ...")  # explicit
```

**Environment variables:** `SUPABASE_URL` and `SUPABASE_KEY` (or `SUPABASE_SERVICE_ROLE_KEY`)

LangChat creates the required tables automatically on first run.

***

## LangChat settings

Pass these to `LangChat(...)` as keyword arguments:

<ParamField path="llm" type="Any" required>
  LLM provider instance.
</ParamField>

<ParamField path="vector_db" type="Any" required>
  Vector database provider instance.
</ParamField>

<ParamField path="db" type="Any" required>
  History database provider instance.
</ParamField>

<ParamField path="reranker" type="Any | None" default="None">
  Reranker instance. Defaults to `FlashrankRerankAdapter` with `ms-marco-MiniLM-L-12-v2`.
</ParamField>

<ParamField path="prompt_template" type="str | None" default="None">
  System prompt template. Must contain `{context}`, `{chat_history}`, `{question}`. See [Prompts guide](/guides/prompts).
</ParamField>

<ParamField path="standalone_question_prompt" type="str | None" default="None">
  Prompt for reformulating follow-up questions. Must contain `{chat_history}` and `{question}`.
</ParamField>

<ParamField path="verbose" type="bool" default="False">
  Enable verbose LangChain chain logging.
</ParamField>

<ParamField path="max_chat_history" type="int" default="20">
  Number of past exchanges to include in each prompt. One exchange = one user message + one AI response.
</ParamField>

***

## Complete example

```python theme={null}
import asyncio
from langchat import LangChat
from langchat.providers import OpenAI, Pinecone, Supabase

LangChat.load_env()

lc = LangChat(
    llm=OpenAI("gpt-4o-mini", temperature=0.7),
    vector_db=Pinecone("my-index"),
    db=Supabase(),
    max_chat_history=10,
    prompt_template="""You are a helpful assistant.

Context:
{context}

Conversation history:
{chat_history}

User: {question}
Assistant:""",
)

async def main():
    response = await lc.chat(query="Hello!", user_id="alice")
    print(response)

asyncio.run(main())
```